ICLR2026
试点 30 篇 · 正式论文集 5,351 篇
ICLR Proceedings ↗ICLR · NEURIPS · ICML
三大顶会，
从论文直接进入。
首批试点把论文标题、作者与正式来源放在同一处。PDF 仍由会议官方论文库托管；GitHub 只在官方论文页明确给出代码链接时展示。
OFFICIAL SOURCES · 2026-08-28
先把年份和来源说清楚。
ICLR 采用已发布的 2026 官方论文集；NeurIPS 2026 尚未举办，采用最新完整的 2025 主会论文集；ICML 2026 的 PMLR 正式卷尚未发布，采用最新完整的 2025 PMLR 267。
90首批可检索论文
84已接入官方摘要
17已匹配单位元数据
14,504对应正式论文集总量
NeurIPS2025
试点 30 篇 · 正式论文集 5,823 篇
NeurIPS Proceedings ↗ICML2025
试点 30 篇 · 正式论文集 3,330 篇
PMLR 267 ↗THREE-LAYER PAPER TAXONOMY
三层标注，不混淆来源。
会议、年份、论文赛道或分会场、英文摘要。仅在会议官方论文页公开时标注。
作者与单位。单位采用 OpenAlex 精确题名记录补充，并保留来源；没有可靠结果就明确留空。
研究大类、贡献类型、方法标签。由本站规则生成，用于检索导航，不等同于会议官方分类。
SEARCH THE PILOT INDEX
从标题、作者或研究方向开始。
首批数据按各官方论文集页面顺序收录，每会 30 篇。赛道与摘要来自官方论文页；单位来自 OpenAlex 精确题名匹配；研究大类、贡献类型和方法标签由本站规则辅助生成，均明确标注来源。
90 篇试点论文
ICLR2026官方赛道 · Conference
MAGREF: Masked Guidance for Any-Reference Video Generation with Subject DisentanglementMAGREF：采用主体解耦与掩码引导的任意参考视频生成
Yufan Deng, Yuanyang Yin, Xun Guo, Yizhi Wang, Zhiyuan Fang, Shenghai Yuan, Yiding Yang, Angtian Wang, Bo Liu, Haibin Huang, Chongyang Ma
单位当前公开元数据未提供，暂不推断
计算机视觉与视频生成式人工智能方法与模型
官方摘要 英文原文
We tackle the task of any-reference video generation, which aims to synthesize videos conditioned on arbitrary types and combinations of reference subjects, together with textual prompts. This task faces persistent challenges, including identity inconsistency, entanglement among multiple reference subjects, and copy-paste artifacts. To address these issues, we introduce MAGREF, a unified and effective framework for any-reference video generation. Our approach incorporates masked guidance and a subject disentanglement mechanism, enabling flexible synthesis conditioned on diverse reference images and textual prompts. Specifically, masked guidance employs a region-aware masking mechanism combined with pixel-wise channel concatenation to preserve appearance features of multiple subjects along the channel dimension. This design preserves identity consistency and maintains the capabilities of the pre-trained backbone, without requiring any architectural changes. To mitigate subject confusion, we introduce a subject disentanglement mechanism which injects the semantic values of each subject derived from the text condition into its corresponding visual region. Additionally, we establish a four-stage data pipeline to construct diverse training pairs, effectively alleviating copy-paste artifacts. Extensive experiments on a comprehensive benchmark demonstrate that MAGREF consistently outperforms existing state-of-the-art approaches, paving the way for scalable, controllable, and high-fidelity any-reference video synthesis. The code and video demos are available in the supplementary materials.
ICLR2026官方赛道 · Conference
LinguaMap: Which Layers of LLMs Speak Your Language and How to Tune Them?LinguaMap：大语言模型的哪些层“会说”你的语言，以及如何对其进行调优？
J. Ben Tamo, Daniel Carlander-Reuterfelt, Jonathan Rubin, Oleg Poliannikov, Dezhi Hong, Mingxian Wang
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型
ICLR2026官方赛道 · Conference
LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI AgentLongHorizonUI：面向 GUI 智能体稳健长时程任务自动化的统一框架
Bin Kang, Shaoguo Wen, YIFEI BI, Shunlong Wu, Xinbin Yuan, Rui Shao, Junle Wang, Zhuotao Tian
单位当前公开元数据未提供，暂不推断
强化学习与智能体自然语言与大语言模型多模态与视觉语言方法与模型推理与规划对齐、安全与隐私
官方摘要 英文原文
Although agents based on multimodal large language models (MLLMs) demonstrate proficiency in general short-term graphical user interface (GUI) tasks, their robustness remains a significant challenge for handling complex long-horizon tasks in dynamic environments . In response, the LongHorizonUI framework is proposed to improve the sustained reliability of agents in long-horizon GUI tasks. To overcome core limitations, we establish a comprehensive long-horizon benchmark, LongGUIBench, covering multiple categories of games and complex general applications, with long-horizon tasks defined as requiring more than 15 steps for rigorous evaluation of long-horizon reasoning capabilities. Based on this, a Multimodal Enhanced Perceiver is designed to incorporate element detection and text recognition models, assigning unique indices to interface elements, thereby reinforcing state representation. Furthermore, a Deep Reflection Decider engine is introduced, incorporating a structured multi-level feedback validation mechanism to enable progressive reasoning and ensure accurate action execution with predictable trajectories. Finally, we introduce a Compensatory Action Executor that combines multiple degradation compensation operations with a process rollback strategy based on execution progress monitoring to ensure operational effectiveness in long-horizon task logic. Experimental results demonstrate that LongHorizonUI achieves substantial long-horizon modeling improvements on LongGUIBench while retaining competitive performance on diverse public benchmarks. The code and models will be publicly available.
ICLR2026官方赛道 · Conference
DiffVax: Optimization-Free Image Immunization Against Diffusion-Based EditingDiffVax：抵御扩散模型图像编辑的免优化图像免疫方法
Tarik Can Ozden, Ozgur Kara, Oguzhan Akcin, Kerem Zaman, Shashank Srivastava, Sandeep Chinchali, James Rehg
单位当前公开元数据未提供，暂不推断
计算机视觉与视频机器学习基础与理论生成式人工智能方法与模型扩散与流模型
官方摘要 英文原文
Current image immunization defense techniques against diffusion-based editing embed imperceptible noise into target images to disrupt editing models. However, these methods face scalability challenges, as they require time-consuming optimization for each image separately, taking hours for small batches. To address these challenges, we introduce DiffVax, a scalable, lightweight, and optimization-free framework for image immunization, specifically designed to prevent diffusion-based editing. Our approach enables effective generalization to unseen content, reducing computational costs and cutting immunization time from days to milliseconds, achieving a speedup of 250,000x. This is achieved through a loss term that ensures the failure of editing attempts and the imperceptibility of the perturbations. Extensive qualitative and quantitative results demonstrate that our model is scalable, optimization-free, adaptable to various diffusion-based editing tools, robust against counter-attacks, and, for the first time, effectively protects video content from editing. More details are available in https://diffvax.github.io/.
ICLR2026官方赛道 · Conference
Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure逆转诅咒是绑定问题吗？从一种基本的泛化失败揭示 Transformer 的局限
Boshi Wang, Huan Sun
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型对齐、安全与隐私因果学习
官方摘要 英文原文
Despite their impressive capabilities, LLMs exhibit a basic generalization failure known as the Reversal Curse , where they struggle to learn reversible factual associations. Understanding why this occurs could help identify weaknesses in current models and advance their generalization and robustness. In this paper, we conjecture that the Reversal Curse in LLMs is a manifestation of the long-standing binding problem in cognitive science, neuroscience and AI. Specifically, we hypothesize two primary causes of the Reversal Curse stemming from transformers' limitations in conceptual binding: the inconsistency and entanglements of concept representations. We perform a series of experiments that support these conjectures. Our exploration leads to a model design based on JEPA (Joint-Embedding Predictive Architecture) that for the first time breaks the Reversal Curse without side-stepping it with specialized data augmentation or non-causal masking, and moreover, generalization could be further improved by incorporating special memory layers that support disentangled concept representations. Our research opens up the broader fundamental challenge of designing models capable of learning systematic conceptual binding with less human scaffolding.
ICLR2026官方赛道 · Conference
Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis平滑校准误差：一致收敛与函数梯度分析
Futoshi Futami, Atsushi Nitanda
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型理论与分析
官方摘要 英文原文
Calibration is a critical requirement for reliable probabilistic prediction, especially in high-risk applications. However, the theoretical understanding of which learning algorithms can simultaneously achieve high accuracy and good calibration remains limited, and many existing studies provide empirical validation or a theoretical guarantee in restrictive settings. To address this issue, in this work, we focus on the smooth calibration error (CE) and provide a uniform convergence bound, showing that the smooth CE is bounded by the sum of the smooth CE over the training dataset and a generalization gap. We further prove that the functional gradient of the loss function can effectively control the training smooth CE. Based on this framework, we analyze three representative algorithms: gradient boosting trees, kernel boosting, and two-layer neural networks. For each, we derive conditions under which both classification and calibration performances are simultaneously guaranteed. Our results offer new theoretical insights and practical guidance for designing reliable probabilistic models with provable calibration guarantees.
ICLR2026官方赛道 · Conference
EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion GenerationEasyTune：面向扩散式动作生成的高效步骤感知微调
Xiaofeng Tan, Wanjiang Weng, Haodong Lei, Hongsong Wang
单位当前公开元数据未提供，暂不推断
生成式人工智能方法与模型扩散与流模型高效训练与压缩
ICLR2026官方赛道 · Conference
Neural Posterior Estimation with Latent Basis Expansions基于潜在基展开的神经后验估计
Declan McNamara, Yicun Duan, Jeffrey Regier
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型高效训练与压缩
官方摘要 英文原文
Neural posterior estimation (NPE) is a likelihood-free amortized variational inference method that approximates projections of the posterior distribution. To date, NPE variational families have been either simple and interpretable (such as the Gaussian family) or highly flexible but black-box and potentially difficult to optimize (such as normalizing flows). In this work, we parameterize variational families via basis expansions of the latent variables. The log density of our variational distribution is a linear combination of latent basis functions (LBFs), which may be fixed a priori or adapted to the problem class of interest. Our training and inference procedures are computationally efficient even for problems with high-dimensional latent spaces, provided only a low-dimensional projection of the posterior is of interest, owing to NPE's automatic marginalization capabilities. In numerous inference problems, the proposed variational family exhibits better performance than existing variational families used with NPE, including mixtures of Gaussians (mixture density networks) and normalizing flows, as well as outperforming an existing basis expansion method for variational inference.
ICLR2026官方赛道 · Conference
MIMIC: Mask-Injected Manipulation Video Generation with Interaction ControlMIMIC：具有交互控制的掩码注入式操控视频生成
Tianxiao Chen, Jintao Rong, Huajin Chen, Jingya Wang, Tao Zhou, Jiming Chen, Qi Ye
单位当前公开元数据未提供，暂不推断
计算机视觉与视频生成式人工智能机器人与自动驾驶方法与模型扩散与流模型
官方摘要 英文原文
Embodied intelligence faces a fundamental bottleneck from limited large-scale interaction data. Video generation offers a scalable alternative, but manipulation videos remain particularly challenging, as they require capturing subtle, contact-rich dynamics. Despite recent advances, video diffusion models still struggle to balance semantic understanding with fine-grained visual details, restricting their effectiveness in manipulation scenarios. Our key insight is that reference videos provide rich semantic and motion cues that can effectively drive manipulation video generation. Building on this, we propose MIMIC, a two-stage image-to-video diffusion framework. (1) We first introduce an Interaction-Motion-Aware (IMA) module to fuse visual features from the reference video, producing coherent semantic masks that correspond to the target image. (2) then utilize these masks as semantic control signals to guide the video generation process. Moreover, considering the ambiguity of the motion attribution, we introduce a Pair Prompt Control mechanism to disentangle object and camera motion by adding the reference video as an additional input. Extensive experiments demonstrate that MIMIC significantly outperforms existing methods, effectively preserves manipulation intent and motion details, even when handling diverse and deformable objects. Our findings underscore the effectiveness of reference-driven semantics for controllable and realistic manipulation video generation.
ICLR2026官方赛道 · Conference
TIMESLIVER : SYMBOLIC-LINEAR DECOMPOSITION FOR EXPLAINABLE TIME SERIES CLASSIFICATIONTIMESLIVER：用于可解释时间序列分类的符号—线性分解
Akash Pandey, Payal Mohapatra, Wei Chen, Qi Zhu, Sinan Keten
单位Northwestern University , Evanston , IL , USAOpenAlex 论文记录 ↗
其他机器学习研究方法与模型
官方摘要 英文原文
Identifying the extent to which every temporal segment influences a model’s predictions is essential for explaining model decisions and increasing transparency. While post-hoc explainable methods based on gradients and feature-based attributions have been popular, they suffer from reference state sensitivity and struggle to generalize across time-series datasets, as they treat time points independently and ignore sequential dependencies. Another perspective on explainable time-series classification is through interpretable components of the model, for instance, leveraging self-attention mechanisms to estimate temporal attribution; however, recent findings indicate that these attention weights often fail to provide faithful measures of temporal importance. In this work, we advance this perspective and present a novel explainability-driven deep learning framework, TimeSliver, which jointly utilizes raw time-series data and its symbolic abstraction to construct a representation that maintains the original temporal structure. Each element in this representation linearly encodes the contribution of each temporal segment to the final prediction, allowing us to assign a meaningful importance score to every time point. For time-series classification, TimeSliver outperforms other temporal attribution methods by 11\% on 7 distinct synthetic and real-world multivariate time-series datasets. TimeSliver also achieves predictive performance within 2\% of state-of-the-art baselines across 26 UEA benchmark datasets, positioning it as a strong and explainable framework for general time-series classification.
ICLR2026官方赛道 · Conference
Consis-GCPO: Consistency-Preserving Group Causal Preference Optimization for Vision CustomizationConsis-GCPO：面向视觉定制的一致性保持组因果偏好优化
Qiaoqiao Jin, Dong She, Siming Fu, Hualiang Wang, weihao zhou, Jidong Jiang
单位当前公开元数据未提供，暂不推断
机器学习基础与理论计算机视觉与视频生成式人工智能方法与模型强化学习对齐、安全与隐私因果学习
官方摘要 英文原文
Subject-driven generation faces a fundamental challenge: achieving high subject fidelity while maintaining semantic alignment with textual descriptions. While recent GRPO-based approaches have shown promise in aligning generative models with human preferences, they apply uniform optimization across all denoising timesteps, ignoring the temporal dynamics of how textual and visual conditions influence generation. We present Consis-GCPO, a causal reinforcement learning framework that reformulates multi-modal condition generation through discrete-time causal modeling. Our key insight is that different conditioning signals exert varying influence throughout the denoising process—text guides semantic structure in early steps while visual references anchor details in later stages. By introducing decoupled causal intervention trajectories, we quantify instantaneous causal effects at each timestep, transforming these measurements into temporally-weighted advantages for targeted optimization. This approach enables precise tracking of textual and visual contributions, ensuring accurate credit assignment for each conditioning modality. Extensive experiments demonstrate that Consis-GCPO significantly advances personalized generation, achieving superior subject consistency while preserving strong text-following capabilities, particularly excelling in complex multi-subject scenarios.
ICLR2026官方赛道 · Conference
Test-Time Alignment for Large Language Models via Textual Model Predictive Control基于文本模型预测控制的大语言模型测试时对齐
Kuang-Da Wang, Teng-Ruei Chen, Yu Heng Hung, Guo-Xun Ko, Shuoyang Ding, Yueh-Hua Wu, Yu-Chiang Frank Wang, Chao-Han Huck Yang, Wen-Chih Peng, Ping-Chun Hsieh
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型生成式人工智能强化学习与智能体方法与模型强化学习推理与规划对齐、安全与隐私
官方摘要 英文原文
Aligning Large Language Models (LLMs) with human preferences through finetuning is resource-intensive, motivating lightweight alternatives at test time. We address test-time alignment through the lens of sequential decision making, a perspective that reveals two fundamental challenges. When actions are defined at the token level, as in guided decoding, alignment suffers from the curse of horizon. Conversely, when actions are at the response level, as in traditional iterative refinement, the curse of dimensionality emerges. To resolve this trade-off, we draw inspiration from Model Predictive Control (MPC) in control theory to propose Textual Model Predictive Control (TMPC), a novel predictive planning framework adapted for aligning LLMs at inference time. A key limitation of standard MPC is its reliance on predefined, hard segment boundaries, which are often absent in text generation. TMPC overcomes this by introducing two principles inspired by hierarchical reinforcement learning: (1) Hindsight Subgoal Identification, where TMPC analyzes generation subgoals to retrospectively identify high-reward intermediate outputs as subgoals. This allows the framework to discover meaningful, task-specific planning steps (e.g., a sentence in machine translation or a bug fix in code generation.). (2) Subgoal-Conditioned Re-Generation, where these identified subgoals are used to guide subsequent planning iterations. By conditioning on these proven, high-quality subgoals, TMPC ensures stable improvement by building upon previously validated successes. TMPC is evaluated on three tasks with distinct segmentation properties: discourse-level translation, long-form response generation, and program synthesis. The results demonstrate that TMPC consistently improves performance, highlighting the generality. Project page: https://rl-bandits-lab.github.io/TMPC/.
ICLR2026官方赛道 · Conference
Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks用于防御嵌入反演攻击的概念感知隐私机制
Yu-Che Tsai, Hsiang Hsiao, Kuan-Yu Chen, Shou-De Lin
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型对齐、安全与隐私
官方摘要 英文原文
Text embeddings enable numerous NLP applications but face severe privacy risks from embedding inversion attacks, which can expose sensitive attributes or reconstruct raw text. Existing differential privacy defenses assume uniform sensitivity across embedding dimensions, leading to excessive noise and degraded utility. We propose SPARSE, a user-centric framework for concept-specific privacy protection in text embeddings. SPARSE combines (1) differentiable mask learning to identify privacy-sensitive dimensions for user-defined concepts, and (2) the Mahalanobis mechanism that applies elliptical noise calibrated by dimension sensitivity. Unlike traditional spherical noise injection, SPARSE selectively perturbs privacy-sensitive dimensions while preserving non-sensitive semantics. Evaluated across six datasets with three embedding models and attack scenarios, SPARSE consistently reduces privacy leakage while achieving superior downstream performance compared to state-of-the-art DP methods.
ICLR2026官方赛道 · Conference
UniOD: A Universal Model for Outlier Detection across Diverse DomainsUniOD：适用于多样化领域的通用离群点检测模型
Dazhi Fu, Jicong Fan
单位当前公开元数据未提供，暂不推断
计算机视觉与视频机器学习基础与理论方法与模型理论与分析图神经网络
官方摘要 英文原文
Outlier detection (OD), distinguishing inliers and outliers in completely unlabeled datasets, plays a vital role in science and engineering. Although there have been many insightful OD methods, most of them require troublesome hyperparameter tuning (a challenge in unsupervised learning) and costly model training for every task or dataset. In this work, we propose UniOD, a universal OD framework that leverages labeled datasets to train a single model capable of detecting outliers of datasets with different feature dimensions and heterogeneous feature spaces from diverse domains. Specifically, UniOD extracts uniform and comparable features across different datasets by constructing and factorizing multi-scale point-wise similarity matrices. It then employs graph neural networks to capture comprehensive within-dataset and between-dataset information simultaneously, and formulates outlier detection tasks as node classification tasks. As a result, once the training is complete, UniOD can identify outliers in datasets from diverse domains without any further model/hyperparameter selection and parameter optimization, which greatly improves convenience and accuracy in real applications. More importantly, we provide theoretical guarantees for the effectiveness of UniOD, consistent with our numerical results. We evaluate UniOD on 30 benchmark OD datasets against 17 baselines, demonstrating its effectiveness and superiority.
ICLR2026官方赛道 · Conference
On The Geometry and Topology of Representations: the Manifolds of Modular Addition论表征的几何与拓扑：模加法的流形结构
Gabriela Moisescu-Pareja, Gavin McCracken, Harley Wiltzer, Colin Daniels, Vincent Létourneau, Doina Precup, Jonathan Love
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型
官方摘要 英文原文
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs can yield distinct circuits for modular addition. In this work, we show that this is not the case, and that both the uniform and trainable attention architectures implement the same algorithm via topologically and geometrically equivalent representations. Our methodology goes beyond the interpretation of individual neurons and weights. Instead, we identify all of the neurons corresponding to each learned representation and then study the collective group of neurons as one entity. This method reveals that each learned representation is a manifold that we can study utilizing tools from topology. Based on this insight, we can statistically analyze the learned representations across hundreds of circuits to demonstrate the similarity between learned modular addition circuits that arise naturally from common deep learning paradigms.
ICLR2026官方赛道 · Conference
Discrete Latent Features Ablate Adversarial Attack: A Robust Prompt Tuning Framework for VLMs离散潜在特征消解对抗攻击：面向视觉语言模型的稳健提示调优框架
YANG CHEN, Yanbin Wei, James Kwok, Yu Zhang
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型计算机视觉与视频方法与模型视觉语言模型对齐、安全与隐私
官方摘要 英文原文
While adversarial fine-tuning can enhance the robustness of vision-language models (VLMs), such approaches are computationally expensive. Adversarial prompt tuning has emerged as a practical alternative. However, existing methods are limited by their reliance on vulnerable continuous image features. To mitigate the vulnerability in the feature representation, we propose DEFEAT ( D iscrete Lat E nt F eatur E based A dversarial T raining), a robust prompt tuning framework for VLMs. Specifically, the DEFEAT method introduces a perturbation discrete shield module that reconstructs discrete latent features and designs a logits fusion strategy, substantially reducing the discrepancy between clean and adversarial image representations. Moreover, the DEFEAT method integrates prompt tuning with adversarial training while applying regularization from learnable prompts to hand-crafted prompts, further enhancing the adversarial robustness. Extensive experiments across 15 datasets validate the effectiveness of the proposed DEFEAT method among existing adversarial prompt tuning methods. The official code is available at https://github.com/cheny02/DEFEAT-ICLR2026.
ICLR2026官方赛道 · Conference
Neural Message-Passing on Attention Graphs for Hallucination Detection用于幻觉检测的注意力图神经消息传递
Fabrizio Frasca, Guy Bar-Shalom, Yftah Ziser, Haggai Maron
单位当前公开元数据未提供，暂不推断
计算机视觉与视频方法与模型
官方摘要 英文原文
Large Language Models (LLMs) often generate incorrect or unsupported content, known as hallucinations. Existing detection methods rely on heuristics or simple models over isolated computational traces such as activations, or attention maps. We unify these signals by representing them as attributed graphs, where tokens are nodes, edges follow attentional flows, and both carry features from attention scores and activations. Our approach, CHARM, casts hallucination detection as a graph learning task and tackles it by applying GNNs over the above attributed graphs. We show that CHARM provably subsumes prior attention-based heuristics and, experimentally, it consistently outperforms other leading approaches across diverse benchmarks. Our results shed light on the relevant role played by the graph structure and on the benefits of combining computational traces, whilst showing CHARM exhibits promising zero-shot performance on cross-dataset transfer.
ICLR2026官方赛道 · Conference
Reasoning with Sampling: Your Base Model is Smarter Than You Think基于采样的推理：你的基础模型比想象中更聪明
Aayush Karan, Yilun Du
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型强化学习推理与规划
官方摘要 英文原文
Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilities can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models' own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.
ICLR2026官方赛道 · Conference
Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization引导式查询细化：采用测试时优化的多模态混合检索
Omri Uzan, Asaf Yehudai, Roi Pony, Eyal Shnarch, Ariel Gera
单位当前公开元数据未提供，暂不推断
推荐、检索与数据挖掘计算机视觉与视频多模态与视觉语言方法与模型视觉语言模型高效训练与压缩
官方摘要 英文原文
Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual tokens directly to image patches and achieving state-of-the-art performance on challenging benchmarks. Recent models relying on this paradigm have massively scaled the dimensionality of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited by modern vision-language models. In this work, we connect these challenges to the paradigm of hybrid retrieval, investigating whether a lightweight dense text retriever can enhance a stronger vision-centric model. Existing hybrid methods, which rely on coarse-grained fusion of ranks or scores, fail to exploit the rich interactions within each model’s representation space. To address this, we introduce Guided Query Refinement (GQR), a novel test-time optimization method that refines a primary retriever’s query embedding using guidance from a complementary retriever’s scores. Through extensive experiments on visual document retrieval benchmarks, we demonstrate that GQR allows ColPali-based models to match the performance of models with significantly larger representations, while being up to 14x faster and requiring 54x less memory. Our findings show that GQR effectively pushes the Pareto frontier for performance and efficiency in multimodal retrieval. We release our code at https://github.com/IBM/test-time-hybrid-retrieval
ICLR2026官方赛道 · Conference
VITA: Zero-Shot Value Functions via Test-Time Adaptation of Vision–Language ModelsVITA：通过视觉语言模型的测试时适应实现零样本价值函数
Christos Ziakas, Alessandra Russo
单位当前公开元数据未提供，暂不推断
计算机视觉与视频自然语言与大语言模型强化学习与智能体方法与模型强化学习推理与规划自监督与对比学习
官方摘要 英文原文
Vision–Language Models (VLMs) show promise as zero-shot goal-conditioned value functions, but their frozen pre-trained representations limit generalization and temporal reasoning. We introduce VITA, a zero-shot value function learning method that enhances both capabilities via test-time adaptation. At inference, a lightweight adaptation module is updated via a gradient step on a meta-learned self-supervised loss, such that each test-time update improves value estimation. By updating sequentially over a trajectory, VITA encodes history into its parameters, addressing the temporal reasoning limitations. To mitigate shortcut learning, we propose a dissimilarity-based sampling strategy that selects semantically diverse segments of the trajectory during training. In real-world robotic manipulation tasks, VITA generalizes from a single training environment to diverse out-of-distribution tasks, environments, and embodiments, outperforming the state-of-the-art zero-shot method using autoregressive VLMs. Furthermore, we demonstrate that VITA’s zero-shot value estimates can be utilized for reward shaping in offline reinforcement learning, resulting in multi-task policies on the Meta-World benchmark that exceed the performance of those trained with the simulation’s fuzzy-logic dense rewards. Project website: https://chziakas.github.io/vita/.
ICLR2026官方赛道 · Conference
PRISON: Unmasking the Criminal Potential of Large Language ModelsPRISON：揭示大语言模型的犯罪潜能
Xinyi Wu, Geng Hong, Pei Chen, Yueyue Chen, Xudong Pan, Min Yang
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型Transformer与大模型对齐、安全与隐私
官方摘要 英文原文
As large language models (LLMs) advance, concerns about their misconduct in complex social contexts intensify. Existing research has overlooked the systematic assessment of LLMs’ criminal potential in realistic interactions, where criminal potential is defined as the risk of producing harmful behaviors such as deception and blame-shifting under adversarial settings that could facilitate unlawful activities. Therefore, we propose a unified framework PRISON, to quantify LLMs' criminal potential across five traits: False Statements, Frame-Up, Psychological Manipulation, Emotional Disguise, and Moral Disengagement. Using structured crime scenarios grounded in reality, we evaluate both criminal potential and anti-crime ability of LLMs. Results show that state-of-the-art LLMs frequently exhibit emergent criminal tendencies, such as proposing misleading statements or evasion tactics, even without explicit instructions. Moreover, when placed in a detective role, models recognize deceptive behavior with only 44\% accuracy on average, revealing a striking mismatch between expressing and detecting criminal traits. These findings underscore the urgent need for adversarial robustness, behavioral alignment, and safety mechanisms before broader LLM deployment.
ICLR2026官方赛道 · Conference
Asynchronous Matching with Dynamic Sampling for Multimodal Dataset Distillation面向多模态数据集蒸馏的动态采样异步匹配
Ding Qi, Jian Li, Shuguang Dou, Zifan Song, Junyao Gao, Yabiao Wang, Chengjie Wang, Cai Zhao
单位当前公开元数据未提供，暂不推断
多模态与视觉语言计算机视觉与视频自然语言与大语言模型方法与模型数据集与基准视觉语言模型高效训练与压缩
官方摘要 英文原文
Multimodal Dataset Distillation (MDD) has emerged as a vital paradigm for enabling efficient training of vision-language models (VLMs) in the era of multimodal data proliferation. Unlike traditional dataset distillation methods that focus on single-modal tasks, MDD presents distinct challenges: (i) the effective distillation of heterogeneous multimodal knowledge, complicated by feature space misalignment and asynchronous optimization dynamics; and (ii) the lack of discrete class guidance, which hinders the distribution coverage and representativeness of synthetic data due to the vastness and continuity of the semantic space. To address these challenges, this paper proposes an Asynchronous Matching with Dynamic sampling (AMD) framework. AMD enables asynchronous trajectory matching by decoupling the selection of starting points for image and text trajectories. Additionally, a Semantics-Aware Prototype Mining module is introduced, which replaces random initialization by leveraging feature-space clustering to identify representative prototypes, enhancing the coverage and representativeness of the distilled samples. Extensive experiments demonstrate that AMD achieves superior distillation performance on Flickr30k and COCO (e.g., IR@1, IR@5, and IR@10 \textbf{gains of 4.5\%, 9.6\%, and 10.9\%}, respectively, on Flickr30k 200 pairs.) with negligible computational overhead.
ICLR2026官方赛道 · Conference
The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives对齐审计器：用于验证与细化大语言模型目标的贝叶斯框架
Matthieu Bou, Nyal Patel, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo
单位当前公开元数据未提供，暂不推断
强化学习与智能体自然语言与大语言模型机器学习基础与理论方法与模型理论与分析Transformer与大模型强化学习对齐、安全与隐私
官方摘要 英文原文
The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from behaviour, existing approaches either produce a single, overconfident reward estimate or fail to address the fundamental ambiguity of the task (non-identifiability). This paper introduces a principled auditing framework that re-frames reward inference from a simple estimation task to a comprehensive process for verification. Our framework leverages Bayesian IRL to not only recover a distribution over objectives but to enable three critical audit capabilities: (i) Quantifying and systematically reducing non-identifiability by demonstrating posterior contraction over sequential rounds of evidence; (ii) Providing actionable, uncertainty-aware diagnostics that expose spurious shortcuts and identify out-of-distribution prompts where the inferred objective cannot be trusted; and (iii) Validating policy-level utility by showing that the refined, low-uncertainty reward can be used directly in RLHF to achieve training dynamics and toxicity reductions comparable to the ground-truth alignment process. Empirically, our framework successfully audits a detoxified LLM and generalizes beyond detoxification to a helpfulness preference setting, yielding a well-calibrated and interpretable objective that strengthens alignment guarantees. Overall, this work provides a practical toolkit for auditors, safety teams, and regulators to verify what LLMs are truly trying to achieve, moving us toward more trustworthy and accountable AI.
ICLR2026官方赛道 · Conference
PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and AlignmentPromptHub：通过局部性感知融合、聚合与对齐增强多提示视觉上下文学习
Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia
单位当前公开元数据未提供，暂不推断
计算机视觉与视频自然语言与大语言模型方法与模型对齐、安全与隐私
官方摘要 英文原文
Visual In-Context Learning (VICL) aims to complete vision tasks by imitating pixel demonstrations. Recent work Condenser pioneered prompt fusion that combines the advantages of various demonstrations, which shows a promising way to extend VICL. Unfortunately, the patch-wise fusion framework and model-agnostic supervision hinder the exploitation of informative cues, thereby limiting performance gains. To overcome this deficiency, we introduce PromptHub, a framework that holistically strengthens multi-prompting through locality-aware fusion, concentration and alignment. PromptHub exploits spatial priors to capture richer contextual information, employs complementary concentration, alignment, and prediction objectives to mutually guide training, and incorporates data augmentation to further reinforce supervision. Extensive experiments on three fundamental vision tasks demonstrate the superiority of PromptHub. Moreover, we validate its universality, transferability, and robustness across out-of-distribution settings, and various retrieval scenarios. This work establishes a reliable locality-aware paradigm for prompt fusion, moving beyond prior patch-wise approaches. Code is available at https://github.com/luotc-why/ICLR26-PromptHub.
ICLR2026官方赛道 · Conference
AP-OOD: Attention Pooling for Out-of- Distribution DetectionAP-OOD：用于分布外检测的注意力池化
Claus Hofmann, Christian Huber, Bernhard Lehner, Daniel Klotz, Sepp Hochreiter, Werner Zellinger
单位Institute for Machine Learning , JKU LIT SAL IWS Lab , Johannes Kepler University , Linz , Austria · Silicon Austria Labs , JKU LIT SAL IWS Lab , Linz , Austria · Interdisciplinary Transformation University Austria , Linz , Austria · ELLIS Unit , LIT AI Lab , Institute for Machine Learning , JKU Linz , AustriaOpenAlex 论文记录 ↗
计算机视觉与视频自然语言与大语言模型方法与模型
官方摘要 英文原文
Out-of-distribution (OOD) detection, which maps high-dimensional data into a scalar OOD score, is critical for the reliable deployment of machine learning models. A key challenge in recent research is how to effectively leverage and aggregate token embeddings from language models to obtain the OOD score. In this work, we propose AP-OOD, a novel OOD detection method for natural language that goes beyond simple average-based aggregation by exploiting token-level information. AP-OOD is a semi-supervised approach that flexibly interpolates between unsupervised and supervised settings, enabling the use of limited auxiliary outlier data. Empirically, AP-OOD sets a new state of the art in OOD detection for text: in the unsupervised setting, it reduces the FPR95 (false positive rate at 95% true positives) from 27.77% to 5.91% on XSUM summarization, and from 75.19% to 68.13% on WMT15 En–Fr translation.
ICLR2026官方赛道 · Conference
Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective强化学习用于语言模型规划的优势与隐患：理论视角
Siwei Wang, Yifei Shen, Haoran Sun, Shi Feng, Shang-Hua Teng, Li Dong, Yaru Hao, Wei Chen
单位当前公开元数据未提供，暂不推断
强化学习与智能体机器学习基础与理论自然语言与大语言模型方法与模型理论与分析综述与观点强化学习推理与规划
官方摘要 英文原文
Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits and limitations through a tractable graph-based abstraction, focusing on policy gradient (PG) and Q-learning methods. Our theoretical analyses reveal that supervised fine-tuning (SFT) may introduce co-occurrence-based spurious solutions, whereas RL achieves correct planning primarily through exploration, underscoring exploration’s role in enabling better generalization. However, we also show that PG suffers from diversity collapse, where output diversity decreases during training and persists even after perfect accuracy is attained. By contrast, Q-learning provides two key advantages: off-policy learning and diversity preservation at convergence. We further demonstrate that careful reward design is necessary to prevent Q-value bias in Q-learning. Finally, applying our framework to the real-world planning benchmark Blocksworld, we confirm that these behaviors manifest in practice.
ICLR2026官方赛道 · Conference
Fast Data Mixture Optimization via Gradient Descent基于梯度下降的快速数据混合优化
Haoru Tan, Sitong Wu, Yanfeng Chen, Jun Xia, Ruobing Xie, Bin Xia, Samm Sun, XIAOJUAN QI
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型
ICLR2026官方赛道 · Conference
LogiConBench: Benchmarking Logical Consistencies of LLMsLogiConBench：大语言模型逻辑一致性基准评测
Zheng Chen, Chuan Zhou, Fengxiang Cheng, Tin Po Yip, Fenrong Liu, Yisen Wang, Jiajun Chai, Xiaohan Wang, Guojun Yin, Wei Lin, Bo Li, Haoxuan Li, Zhouchen Lin
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型数据集与基准Transformer与大模型推理与规划
官方摘要 英文原文
Logical consistency, the requirement that statements remain non-contradictory under logical rules, is fundamental for trustworthy reasoning, yet current LLMs often fail to maintain it even on simple inference tasks. Existing benchmarks for LLM logical consistency are not scalable, not diverse, and not challenging, with state-of-the-art models already surpassing 95\% accuracy. LogiConBench is the first benchmark that (1) generates unlimited logical rule combinations with precise labels, (2) provides controllable-depth graphs with explicit reasoning paths, and (3) remains challenging for state-of-the-art LLMs. To achieve this, LogiConBench automatically generates logical graphs where nodes represent symbolic propositions and edges denote reasoning relations. From these graphs, it samples lists of propositions, extracts reasoning paths, determines all consistent label lists, and translates them into diverse natural language expressions. While we release a 280K-sample corpus in this work, the framework can be scaled to generate unlimited data. To strengthen its evaluative significance, we evaluate 14 frontier LLMs on three tasks with varying difficulty levels, and find that the Enumerative task remains extremely challenging, with the best exact accuracy as only 34\%. Our code and data are available at https://github.com/Bellafc/LogiConBench.git.
ICLR2026官方赛道 · Conference
Flow2GAN: Hybrid Flow Matching and GAN with Multi-Resolution Network for Few-step High-Fidelity Audio GenerationFlow2GAN：采用多分辨率网络融合流匹配与 GAN 的少步高保真音频生成
Zengwei Yao, Wei Kang, Han Zhu, Liyong Guo, Lingxuan Ye, Fangjun Kuang, Weiji Zhuang, Zhaoqing Li, Zhifeng Han, Long Lin, Daniel Povey
单位当前公开元数据未提供，暂不推断
生成式人工智能方法与模型理论与分析扩散与流模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step inference that introduces considerable computational overhead. In this work, we introduce Flow2GAN, a two-stage framework that combines Flow Matching training for learning generative capabilities with GAN fine-tuning for efficient few-step inference. Specifically, given audio's unique properties, we first improve Flow Matching for audio modeling through: 1) reformulating the objective as endpoint estimation, avoiding velocity estimation difficulties when involving empty regions; 2) applying spectral energy-based loss scaling to emphasize perceptually salient quieter regions. Building on these Flow Matching adaptations, we demonstrate that a further stage of lightweight GAN fine-tuning enables us to obtain few-step (e.g., 1/2/4 steps) generators that produce high-quality audio. In addition, we develop a multi-branch network architecture that processes Fourier coefficients at different time-frequency resolutions, which improves the modeling capabilities compared to prior single-resolution designs. Experimental results indicate that our Flow2GAN delivers high-fidelity audio generation from Mel-spectrograms or discrete audio tokens, achieving highly favorable quality-efficiency trade-offs compared to existing state-of-the-art GAN-based and Flow Matching-based methods. Online demo samples are available at \url{https://flow2gan.github.io}, and the source code is released at \url{https://github.com/k2-fsa/Flow2GAN}.
ICLR2026官方赛道 · Conference
Incorporating Expert Priors into Bayesian Optimization via Dynamic Mean Decay通过动态均值衰减将专家先验融入贝叶斯优化
Chongqi Qu, Meiqin Liu, Jian Lan, Shanling Dong, Zhunga Liu
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型理论与分析对齐、安全与隐私
官方摘要 英文原文
Bayesian optimization (BO) is a powerful approach for black-box optimization, and in many real-world problems, domain experts possess valuable prior knowledge about promising regions of the search space. However, existing prior-informed BO methods are often overly complex, tied to specific acquisition functions, or highly sensitive to inaccurate priors. We propose DynMeanBO, a simple and general framework that incorporates expert priors into the Gaussian process mean function with a dynamic decay mechanism. This design allows BO to exploit expert knowledge in the early stages while gradually reverting to standard BO behavior, ensuring robustness against misleading priors while retaining the exploratory behavior of standard BO. DynMeanBO is broadly compatible with acquisition functions, introduces negligible computational cost, and comes with convergence guarantees under Expected Improvement and Upper Confidence Bound. Experiments on synthetic benchmarks and hyperparameter optimization tasks show that DynMeanBO accelerates convergence with informative priors and remains robust under biased ones.
NeurIPS2025官方赛道 · Main Conference Track
NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow ModelsNeuralPLexer3：基于流模型的高精度生物分子复合物结构预测
Jarren Zhuoran Qiao, Feizhi Ding, Thomas Dresselhaus, Mia Rosenfeld, Xiaotian Han, Owen Howell, Aniketh Iyengar, Stephen Opalenski, Anders Christensen, Sai Krishna Sirumalla, Fred Manby, Thomas K. Miller, Matthew Welborn
单位当前公开元数据未提供，暂不推断
AI for Science与医疗方法与模型扩散与流模型高效训练与压缩
官方摘要 英文原文
Biomolecular structure determination is essential to a mechanistic understanding of diseases and the development of novel therapeutics. Machine-learning-based structure prediction methods have made significant advancements by computationally predicting protein and bioassembly structures from sequences and molecular topology alone. Despite substantial progress in the field, challenges remain to deliver structure prediction models to real-world drug discovery. Here, we present NeuralPLexer3 -- a physics-inspired flow-based generative model that achieves state-of-the-art prediction accuracy on key biomolecular interaction types and improves training and sampling efficiency compared to its predecessors and alternative methodologies. Examined through existing and new benchmarks, NeuralPLexer3 excels in areas crucial to structure-based drug design, including blind docking, physical validity, and ligand-induced protein conformational changes.
NeurIPS2025官方赛道 · Main Conference Track
The Primacy of Magnitude in Low-Rank Adaptation低秩适应中幅值的首要作用
Zicheng Zhang, Haoran Li, Yifeng Zhang, Guoqiang Gong, Jiaxing Wang, Junxing Hu, Pengzhang Liu, Qixia Jiang
单位JD.com · University of the Chinese Academy of Sciences University of Illinois Urbana-Champaign · JD.COM · jd.comOpenAlex 论文记录 ↗
其他机器学习研究理论与分析高效训练与压缩
官方摘要 英文原文
Low-Rank Adaptation (LoRA) offers a parameter-efficient paradigm for tuning large models. While recent spectral initialization methods improve convergence and performance over the naive “Noise & Zeros” scheme, their extra computational and storage overhead undermines efficiency. In this paper, we establish update magnitude as the fundamental driver of LoRA performance and propose LoRAM, a magnitude-driven “Basis & Basis” initialization scheme that matches spectral methods without their inefficiencies. Our key contributions are threefold: (i) Magnitude of weight updates determines convergence. We prove low-rank structures intrinsically bound update magnitudes, unifying hyperparameter tuning in learning rate, scaling factor, and initialization as mechanisms to optimize magnitude regulation. (ii) Spectral initialization succeeds via magnitude amplification. We demystify that the presumed knowledge-driven benefit of spectral component essentially arises from the boost in the weight update magnitude. (iii) A novel and compact initialization strategy, LoRAM, scales deterministic orthogonal bases using pretrained weight magnitudes to simulate spectral gains. Extensive experiments show that LoRAM serves as a strong baseline, retaining the full efficiency of LoRA while matching or outperforming spectral initialization across benchmarks.
NeurIPS2025官方赛道 · Datasets and Benchmarks Track
EngiBench: A Framework for Data-Driven Engineering Design ResearchEngiBench：面向数据驱动工程设计研究的框架
Florian Felten, Gabriel Apaza, Gerhard Bräunlich, Cashen Diniz, Xuliang Dong, Arthur Drake, Milad Habibi, Nathaniel Hoffman, Matthew Keeler, Soheyl Massoudi, Francis VanGessel, Mark Fuge
单位ETH Zürich · University of Maryland, College Park · ETHZ - ETH ZurichOpenAlex 论文记录 ↗
生成式人工智能机器学习基础与理论方法与模型
官方摘要 英文原文
Engineering design optimization seeks to automatically determine the shapes, topologies, or parameters of components that maximize performance under given conditions. This process often depends on physics-based simulations, which are difficult to install, computationally expensive, and require domain-specific expertise. To mitigate these challenges, we introduce EngiBench, the first open‐source library and datasets spanning diverse domains for data‐driven engineering design. EngiBench provides a unified API and a curated set of benchmarks---covering aeronautics, heat conduction, photonics, and more---that enable fair, reproducible comparisons of optimization and machine learning algorithms, such as generative or surrogate models. We also release EngiOpt, a companion library offering a collection of such algorithms compatible with the EngiBench interface. Both libraries are modular, letting users plug in novel algorithms or problems, automate end-to-end experiment workflows, and leverage built-in utilities for visualization, dataset generation, feasibility checks, and performance analysis. We demonstrate their versatility through experiments comparing state-of-the-art techniques across multiple engineering design problems, an undertaking that was previously prohibitively time-consuming to perform. Finally, we show that these problems pose significant challenges for standard machine learning methods due to highly sensitive and constrained design manifolds.
NeurIPS2025官方赛道 · Main Conference Track
COME: Adding Scene-Centric Forecasting Control to Occupancy World ModelCOME：为占用世界模型引入以场景为中心的预测控制
Yining Shi, Kun Jiang, Qiang Meng, Ke Wang, JiaBao Wang, Wenchao Sun, Tuopu Wen, mengmeng yang, diange yang
单位Tsinghua University, Tsinghua University · Tsinghua University · University of Washington, Seattle · The Chinese University of Hong Kong · Nankai University · Horizon RoboticsOpenAlex 论文记录 ↗
计算机视觉与视频方法与模型
官方摘要 英文原文
World models are critical for autonomous driving to simulate environmental dynamics and generate synthetic data. Existing methods struggle to disentangle ego-vehicle motion (perspective shifts) from scene evolvement (agent interactions), leading to suboptimal predictions. Instead, we propose to separate environmental changes from ego-motion by leveraging the scene-centric coordinate systems. In this paper, we introduce COME: a framework that integrates scene-centric forecasting Control into the Occupancy world ModEl. Specifically, COME first generates ego-irrelevant, spatially consistent future features through a scene-centric prediction branch, which are then converted into scene condition using a tailored ControlNet. These condition features are subsequently injected into the occupancy world model, enabling more accurate and controllable future occupancy predictions. Experimental results on the nuScenes-Occ3D dataset show that COME achieves consistent and significant improvements over state-of-the-art (SOTA) methods across diverse configurations, including different input sources (ground-truth, camera-based, fusion-based occupancy) and prediction horizons (3s and 8s). For example, under the same settings, COME achieves 26.3% better mIoU metric than DOME and 23.7% better mIoU metric than UniScene. These results highlight the efficacy of disentangled representation learning in enhancing spatio-temporal prediction fidelity for world models. Code is available at https://github.com/synsin0/COME.
NeurIPS2025官方赛道 · Main Conference Track
Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models通过嵌入扭曲缓解文本条件扩散模型的性内容生成
Jaesin Ahn, Heechul Jung
单位当前公开元数据未提供，暂不推断
生成式人工智能自然语言与大语言模型计算机视觉与视频方法与模型扩散与流模型对齐、安全与隐私
官方摘要 英文原文
Diffusion models show remarkable image generation performance following text prompts, but risk generating sexual contents. Existing approaches, such as prompt filtering, concept removal, and even sexual contents mitigation methods, struggle to defend against adversarial attacks while maintaining benign image quality. In this paper, we propose a novel approach called Distorting Embedding Space (DES), a text encoder-based defense mechanism that effectively tackles these issues through innovative embedding space control. DES transforms unsafe embeddings, extracted from a text encoder using unsafe prompts, toward carefully calculated safe embedding regions to prevent unsafe contents generation, while reproducing the original safe embeddings. DES also neutralizes the ``nudity'' embedding, by aligning it with neutral embedding to enhance robustness against adversarial attacks. As a result, extensive experiments on explicit content mitigation and adaptive attack defense show that DES achieves state-of-the-art (SOTA) defense, with attack success rate (ASR) of 9.47\% on FLUX.1, a recent popular model, and 0.52\% on the widely adopted Stable Diffusion v1.5. These correspond to ASR reductions of 76.5\% and 63.9\% compared to previous SOTA methods, EraseAnything and AdvUnlearn, respectively. Furthermore, DES maintains benign image quality, achieving Frechet Inception Distance and CLIP score comparable to those of the original FLUX.1 and Stable Diffusion v1.5.
NeurIPS2025官方赛道 · Main Conference Track
Stochastic Forward-Forward Learning through Representational Dimensionality Compression通过表征维度压缩实现随机前向—前向学习
Zhichao Zhu, YANG QI, Hengyuan Ma, Wenlian Lu, Jianfeng Feng
单位Fudan UniversityOpenAlex 论文记录 ↗
机器学习基础与理论方法与模型高效训练与压缩自监督与对比学习
官方摘要 英文原文
The Forward-Forward (FF) learning algorithm provides a bottom-up alternative to backpropagation (BP) for training neural networks, relying on a layer-wise "goodness" function with well-designed negative samples for contrastive learning. Existing goodness functions are typically defined as the sum of squared postsynaptic activations, neglecting correlated variability between neurons. In this work, we propose a novel goodness function termed dimensionality compression that uses the effective dimensionality (ED) of fluctuating neural responses to incorporate second-order statistical structure. Our objective minimizes ED for noisy copies of individual inputs while maximizing it across the sample distribution, promoting structured representations without the need to prepare negative samples. We demonstrate that this formulation achieves competitive performance compared to other non-BP methods. Moreover, we show that noise plays a constructive role that can enhance generalization and improve inference when predictions are derived from the mean of squared output, which is equivalent to making predictions based on an energy term. Our findings contribute to the development of more biologically plausible learning algorithms and suggest a natural fit for neuromorphic computing, where stochasticity is a computational resource rather than a nuisance. The code is available at https://github.com/ZhichaoZhu/StochasticForwardForward.
NeurIPS2025官方赛道 · Main Conference Track
Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting面向高斯泼溅文本驱动三维编辑的扩散特征场
Eunseo Koh, Sangeek Hyun, MinKyu Lee, Jiwoo Chung, Kangmin Seo, Jae-Pil Heo
单位Sung Kyun Kwan University · Sungkyunkwan UniversityOpenAlex 论文记录 ↗
计算机视觉与视频生成式人工智能自然语言与大语言模型方法与模型扩散与流模型对齐、安全与隐私
官方摘要 英文原文
Recent advances in text-based image editing have motivated the extension of these techniques into the 3D domain. However, existing methods typically apply 2D diffusion models independently to multiple viewpoints, resulting in significant artifacts, most notably the Janus problem, due to inconsistencies across edited views. To address this, we propose a novel approach termed DFFSplat, which integrates a 3D-consistent diffusion feature field into the editing pipeline. By rendering and injecting these 3D-consistent structural features into intermediate layers of a 2D diffusion model, our method effectively enforces geometric alignment and semantic coherence across views. However, averaging 3D features during the feature field learning process can lead to the loss of fine texture details. To overcome this, we introduce a dual-encoder architecture to disentangle view-independent structural information from view-dependent appearance details. By encoding only the disentangled structure into the 3D field and injecting it during 2D editing, our method produces semantically and multi-view coherent edited images while maintaining high text fidelity. Additionally, we employ a time-invariance objective to ensure consistency across diffusion timesteps, enhancing the stability of learned representations. Experimental results demonstrate that our method achieves state-of-the-art performance in terms of text-fidelity, and better preserves structural and semantic consistency compared to existing approaches.
NeurIPS2025官方赛道 · Main Conference Track
Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs从上下文聚焦到线索：面向多图像多模态大语言模型的分层偏好优化
Xudong Li, Mengdan Zhang, Peixian Chen, Xiawu Zheng, Yan Zhang, Jingyuan Zheng, Yunhang Shen, Ke Li, Chaoyou Fu, Xing Sun, Rongrong Ji
单位当前公开元数据未提供，暂不推断
计算机视觉与视频机器学习基础与理论多模态与视觉语言方法与模型
官方摘要 英文原文
Multi-modal Large Language Models (MLLMs) excel at single-image tasks but struggle with multi-image understanding due to cross-modal misalignment, leading to hallucinations (context omission, conflation, and misinterpretation). Existing methods using Direct Preference Optimization (DPO) constrain optimization to a solitary image reference within the input sequence, neglecting holistic context modeling. To address this, we propose Context-to-Cue Direct Preference Optimization (CcDPO), a multi-level preference optimization framework that enhances per-image perception in multi-image settings by zooming into visual clues—from sequential context to local details. Our approach features two sequentially dependent components: (i) Context-Level Optimization: By introducing low-cost sequence preference pairs, we optimize the model to distinguish between complete and disrupted multi-image contexts, thereby correcting cognitive biases in MLLMs’ multi-image understanding. (ii) Needle-Level Optimization: By integrating region-specific visual prompts with multimodal preference supervision, we direct the model’s attention to critical visual details, effectively suppressing perceptual biases toward fine-grained visual information. To support scalable optimization, we also construct MultiScope-42k, an automatically generated multi-image dataset with hierarchical preference pairs. Experiments show that CcDPO significantly reduces hallucinations and yields consistent performance gains across general single- and multi-image tasks. Codes are available at https://github.com/LXDxmu/CcDPO.
NeurIPS2025官方赛道 · Main Conference Track
Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design将类 AlphaFold3 蛋白质折叠模型重新用于抗体序列—结构协同设计
Nianzu Yang, Songlin Jiang, Jian Ma, Huaijin Wu, Shuangjia Zheng, Wengong Jin, Junchi Yan
单位Shanghai Jiao Tong University · Shanghai Jiaotong University · Northeastern UniversityOpenAlex 论文记录 ↗
生成式人工智能AI for Science与医疗方法与模型扩散与流模型
官方摘要 英文原文
Diffusion models hold great potential for accelerating antibody design, but their performance is so far limited by the number of antibody-antigen complexes used for model training. Meanwhile, AlphaFold3-like protein folding models, pre-trained on a large corpus of crystal structures, have acquired a broad understanding of biomolecular interaction. Based on this insight, we develop a new antigen-conditioned antibody design model by adapting the diffusion module of AlphaFold3-like models for sequence-structure co-diffusion. Specifically, we extend their structure diffusion module with a sequence diffusion head and fine-tune the entire protein folding model for antibody sequence-structure co-design. Our benchmark results show that sequence-structure co-diffusion models not only surpass state-of-the-art antibody design methods in performance but also maintain structure prediction accuracy comparable to the original folding model. Notably, in the antibody co-design task, our method achieves a CDR-H3 recovery rate of 65% for typical antibodies, outperforming the baselines by 87%, and attains a remarkable 63% recovery rate for nanobodies.
NeurIPS2025官方赛道 · Main Conference Track
Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving采用块对角 LoRA 消除张量并行 LoRA 服务中的通信开销
Xinyu Wang, Jonas Kübler, Kailash Budhathoki, Yida Wang, Matthäus Kleindessner
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型Transformer与大模型高效训练与压缩
官方摘要 英文原文
When serving a single base LLM with several different LoRA adapters simultaneously, the adapters cannot simply be merged with the base model’s weights as the adapter swapping would create overhead and requests using different adapters could not be batched. Rather, the LoRA computations have to be separated from the base LLM computations, and in a multi-device setup the LoRA adapters can be sharded in a way that is well aligned with the base model’s tensor parallel execution, as proposed in S-LoRA. However, the S-LoRA sharding strategy encounters some communication overhead, which may be small in theory, but can be large in practice. In this paper, we propose to constrain certain LoRA factors to be block-diagonal, which allows for an alternative way of sharding LoRA adapters that does not require any additional communication for the LoRA computations. We demonstrate in extensive experiments that our block-diagonal LoRA approach is similarly parameter efficient as standard LoRA (i.e., for a similar number of parameters it achieves similar downstream performance) and that it leads to significant end-to-end speed-up over S-LoRA. For example, when serving on eight A100 GPUs, we observe up to 1.79x (1.23x) end-to-end speed-up with 0.87x (1.74x) the number of adapter parameters for Llama-3.1-70B, and up to 1.63x (1.3x) end-to-end speed-up with 0.86x (1.73x) the number of adapter parameters for Llama-3.1-8B.
NeurIPS2025官方赛道 · Main Conference Track
Vulnerable Data-Aware Adversarial Training脆弱数据感知对抗训练
Yuqi Feng, Jiahao Fan, Yanan Sun
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Fast adversarial training (FAT) has been considered as one of the most effective alternatives to the computationally-intensive adversarial training. Generally, FAT methods pay equal attention to each sample of the target task. However, the distance between each sample and the decision boundary is different, learning samples which are far from the decision boundary (i.e., less important to adversarial robustness) brings additional training cost and leads to sub-optimal results. To tackle this issue, we present vulnerable data-aware adversarial training (VDAT) in this study. Specifically, we first propose a margin-based vulnerability calculation method to measure the vulnerability of data samples. Moreover, we propose a vulnerability-aware data filtering method to reduce the training data for adversarial training thus improve the training efficiency. The experiments are conducted in terms of adversarial training and robust neural architecture search on CIFAR-10, CIFAR-100, and ImageNet-1K. The results demonstrate that VDAT is up to 76% more efficient than state-of-the-art FAT methods, while achieving improvements regarding the natural accuracy and adversarial accuracy in both scenarios. Furthermore, the visualizations and ablation studies show the effectiveness of both core components designed in VDAT.
NeurIPS2025官方赛道 · Main Conference Track
Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers在二次—线性混合 Transformer 中融合互补记忆系统
Kazuki Irie, Morris Yau, Samuel J Gershman
单位Harvard University · Massachusetts Institute of TechnologyOpenAlex 论文记录 ↗
推荐、检索与数据挖掘方法与模型强化学习
官方摘要 英文原文
We develop hybrid memory architectures for general-purpose sequence processing neural networks, that combine key-value memory using softmax attention (KV-memory) with fast weight memory through dynamic synaptic modulation (FW-memory)---the core principles of quadratic and linear transformers, respectively. These two memory systems have complementary but individually limited properties: KV-memory offers precise retrieval but is constrained by quadratic complexity in sequence length, while FW-memory supports arbitrarily long sequences and enables more expressive computation but sacrifices precise recall. We propose and compare three methods to blend these two systems into a single memory system, differing in how and when input information is delivered to each system, to leverage the strengths of both. We conduct experiments on general language modeling and retrieval tasks by training 340M- and 1.3B-parameter models from scratch, as well as on synthetic algorithmic tasks designed to precisely illustrate the benefits of certain hybrid methods over others. We also evaluate our hybrid memory systems on reinforcement learning in partially observable environments. Overall, we demonstrate how a well-designed hybrid can overcome the limitations of its individual components, offering new insights into the design principle of neural memory systems.
NeurIPS2025官方赛道 · Main Conference Track
SALS: Sparse Attention in Latent Space for KV Cache CompressionSALS：用于 KV 缓存压缩的潜在空间稀疏注意力
Junlin Mu, Hantao Huang, Jihang Zhang, Minghui Yu, Tao Wang, Yidong Li
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型高效训练与压缩
官方摘要 英文原文
Large Language Models (LLMs) capable of handling extended contexts are in high demand, yet their inference remains challenging due to substantial Key-Value (KV) cache size and high memory bandwidth requirements. Previous research has demonstrated that KV cache exhibits low-rank characteristics within the hidden dimension, suggesting the potential for effective compression. However, due to the widely adopted Rotary Position Embedding (RoPE) mechanism in modern LLMs, naive low‑-rank compression suffers severe accuracy degradation or creates a new speed bottleneck, as the low-rank cache must first be reconstructed in order to apply RoPE. In this paper, we introduce two key insights: first, the application of RoPE to the key vectors increases their variance, which in turn results in a higher rank; second, after the key vectors are transformed into the latent space, they largely maintain their representation across most layers. Based on these insights, we propose the Sparse Attention in Latent Space (SALS) framework. SALS projects the KV cache into a compact latent space via low-rank projection, and performs sparse token selection using RoPE-free query--key interactions in this space. By reconstructing only a small subset of important tokens, it avoids the overhead of full KV cache reconstruction. We comprehensively evaluate SALS on various tasks using two large-scale models: LLaMA2-7b-chat and Mistral-7b, and additionally verify its scalability on the RULER-128k benchmark with LLaMA3.1-8B-Instruct. Experimental results demonstrate that SALS achieves SOTA performance by maintaining competitive accuracy. Under different settings, SALS achieves 6.4-fold KV cache compression and 5.7-fold speed-up in the attention operator compared to FlashAttention2 on the 4K sequence. For the end-to-end throughput performance, we achieves 1.4-fold and 4.5-fold improvement compared to GPT-fast on 4k and 32K sequences, respectively. The source code will be publicly available in the future.
NeurIPS2025官方赛道 · Main Conference Track
Wan-Move: Motion-controllable Video Generation via Latent Trajectory GuidanceWan-Move：通过潜在轨迹引导实现运动可控视频生成
Ruihang Chu, Yefei He, Zhekai Chen, Shiwei Zhang, Xiaogang Xu, bin xia, Dingdong WANG, Hongwei Yi, Xihui Liu, Hengshuang Zhao, Yu Liu, Yingya Zhang, Yujiu Yang
单位当前公开元数据未提供，暂不推断
计算机视觉与视频生成式人工智能方法与模型
官方摘要 英文原文
We present Wan-Move, a simple and scalable framework that brings motion control to video generative models. Existing motion-controllable methods typically suffer from coarse control granularity and limited scalability, leaving their outputs insufficient for practical use. We narrow this gap by achieving precise and high-quality motion control. Our core idea is to directly make the original condition features motion-aware for guiding video synthesis. To this end, we first represent object motions with dense point trajectories, allowing fine-grained control over the scene. We then project these trajectories into latent space and propagate the first frame's features along each trajectory, producing an aligned spatiotemporal feature map that tells how each scene element should move. This feature map serves as the updated latent condition, which is naturally integrated into the off-the-shelf image-to-video model, e.g., Wan-I2V-14B, as motion guidance without any architecture change. It removes the need for auxiliary motion encoders and makes fine-tuning base models easily scalable. Through scaled training, Wan-Move generates 5-second, 480p videos whose motion controllability rivals Kling 1.5 Pro's commercial Motion Brush, as indicated by user studies. To support comprehensive evaluation, we further design MoveBench, a rigorously curated benchmark featuring diverse content categories and hybrid-verified annotations. It is distinguished by larger data volume, longer video durations, and high-quality motion annotations. Extensive experiments on MoveBench and the public dataset consistently show Wan-Move's superior motion quality. Code, models, and benchmark data are made available.
NeurIPS2025官方赛道 · Main Conference Track
Can Diffusion Models Disentangle? A Theoretical Perspective扩散模型能否实现解耦？理论视角
Liming Wang, Muhammad Jehanzeb Mirza, Yishu Gong, Yuan Gong, Jiaqi Zhang, Brian Tracey, Katerina Placek, Marco Vilela, Jim Glass
单位当前公开元数据未提供，暂不推断
生成式人工智能机器学习基础与理论方法与模型理论与分析综述与观点扩散与流模型
官方摘要 英文原文
This paper presents a novel theoretical framework for understanding how diffusion models can learn disentangled representations with commonly used weak supervision such as partial labels and multiple views. Within this framework, we establish identifiability conditions for diffusion models to disentangle latent variable models with \emph{stochastic}, \emph{non-invertible} mixing processes. We also prove \emph{finite-sample global convergence} for diffusion models to disentangle independent subspace models. To validate our theory, we conduct extensive disentanglement experiments on subspace recovery in latent subspace Gaussian mixture models, image colorization, denoising, and voice conversion for speech classification. Our experiments show that training strategies inspired by our theory, such as style guidance regularization, consistently enhance disentanglement performance.
NeurIPS2025官方赛道 · Datasets and Benchmarks Track
Struct-Bench: A Benchmark for Differentially Private Structured Text GenerationStruct-Bench：差分隐私结构化文本生成基准
Shuaiqi Wang, Vikas Raunak, Arturs Backurs, Victor Reis, Pei Zhou, Sihao Chen, Longqi Yang, Zinan Lin, Sergey Yekhanin, Giulia Fanti
单位CMU, Carnegie Mellon University · Google DeepMind · TTIC · Microsoft · University of Hong Kong · Microsoft Research · CMUOpenAlex 论文记录 ↗
自然语言与大语言模型生成式人工智能方法与模型数据集与基准对齐、安全与隐私
官方摘要 英文原文
Differentially private (DP) synthetic data generation is a promising technique for utilizing private datasets that otherwise cannot be exposed for model training or other analytics. While much research literature has focused on generating private unstructured text and image data, in enterprise settings, structured data (e.g., tabular) is more common, often including natural language fields or components. Existing synthetic data evaluation techniques (e.g., FID) struggle to capture the structural properties and correlations of such datasets. In this work, we propose Struct-Bench, a framework and benchmark for evaluating synthetic datasets derived from structured datasets that contain natural language data. The Struct-Bench framework requires users to provide a representation of their dataset structure as a Context-Free Grammar (CFG). Our benchmark comprises 5 real-world and 2 synthetically generated datasets. We show that these datasets demonstrably present a great challenge even for state-of-the-art DP synthetic data generation methods. Struct-Bench provides reference implementations of different metrics and a leaderboard, offering a standardized platform to benchmark and investigate privacy-preserving synthetic data methods. We also present a case study showing how Struct-Bench improves the synthetic data quality of Private Evolution (PE) on structured data. The benchmark and the leaderboard have been publicly made available at https://struct-bench.github.io.
NeurIPS2025官方赛道 · Main Conference Track
DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image EditingDCI：用于增强扩散式图像编辑的双条件反演
Zixiang Li, Haoyu Wang, Wei Wang, Chuangchuang Tan, Yunchao Wei, Yao Zhao
单位Beijing Jiaotong University · Tianjin University · UCLAOpenAlex 论文记录 ↗
计算机视觉与视频生成式人工智能方法与模型扩散与流模型对齐、安全与隐私
官方摘要 英文原文
Diffusion models have achieved remarkable success in image generation and editing tasks. Inversion within these models aims to recover the latent noise representation for a real or generated image, enabling reconstruction, editing, and other downstream tasks. However, to date, most inversion approaches suffer from an intrinsic trade-off between reconstruction accuracy and editing flexibility. This limitation arises from the difficulty of maintaining both semantic alignment and structural consistency during the inversion process. In this work, we introduce Dual-Conditional Inversion (DCI) , a novel framework that jointly conditions on the source prompt and reference image to guide the inversion process. Specifically, DCI formulates the inversion process as a dual-condition fixed-point optimization problem, minimizing both the latent noise gap and the reconstruction error under the joint guidance. This design anchors the inversion trajectory in both semantic and visual space, leading to more accurate and editable latent representations. Our novel setup brings new understanding to the inversion process. Extensive experiments demonstrate that DCI achieves state-of-the-art performance across multiple editing tasks, significantly improving both reconstruction quality and editing precision. Furthermore, we also demonstrate that our method achieves strong results in reconstruction tasks, implying a degree of robustness and generalizability approaching the ultimate goal of the inversion process. Our codes are available at: https://github.com/Lzxhh/Dual-Conditional-Inversion
NeurIPS2025官方赛道 · Main Conference Track
Post Hoc Regression Refinement via Pairwise Rankings基于成对排序的事后回归优化
Kevin Tirta Wijaya, Michael Sun, Minghao Guo, Hans-peter Seidel, Wojciech Matusik, Vahid Babaei
单位Max Planck Institute for Informatics · Computer Science and Artificial Intelligence Laboratory, Electrical Engineering & Computer Science · MIT · Max-Planck Institute · Rheinische Friedrich-Wilhelms Universität BonnOpenAlex 论文记录 ↗
自然语言与大语言模型AI for Science与医疗方法与模型Transformer与大模型
官方摘要 英文原文
Accurate prediction of continuous properties is essential to many scientific and engineering tasks. Although deep-learning regressors excel with abundant labels, their accuracy deteriorates in data-scarce regimes. We introduce RankRefine, a model-agnostic, plug-and-play post-hoc refinement technique that injects expert knowledge through pairwise rankings. Given a query item and a small reference set with known properties, RankRefine combines the base regressor’s output with a rank-based estimate via inverse-variance weighting, requiring no retraining. In molecular property prediction task, RankRefine achieves up to 10\% relative reduction in mean absolute error using only 20 pairwise comparisons obtained through a general-purpose large language model (LLM) with no finetuning. As rankings provided by human experts or general-purpose LLMs are sufficient for improving regression across diverse domains, RankRefine offers practicality and broad applicability, especially in low-data settings.
NeurIPS2025官方赛道 · Main Conference Track
FreeControl: Efficient, Training-Free Structural Control via One-Step Attention ExtractionFreeControl：通过单步注意力提取实现高效免训练结构控制
Jiang Lin, Xinyu Chen, Song Wu, Zhiqiu Zhang, Jizhi Zhang, Ye Wang, Qiang Tang, Qian Wang, Jian Yang, Zili Yi
单位当前公开元数据未提供，暂不推断
生成式人工智能方法与模型扩散与流模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Controlling the spatial and semantic structure of diffusion-generated images remains a challenge. Existing methods like ControlNet rely on handcrafted condition maps and retraining, limiting flexibility and generalization. Inversion-based approaches offer stronger alignment but incur high inference cost due to dual-path denoising. We present \textbf{FreeControl}, a training-free framework for semantic structural control in diffusion models. Unlike prior methods that extract attention across multiple timesteps, FreeControl performs \textit{one-step attention extraction} from a single, optimally chosen timestep and reuses it throughout denoising. This enables efficient structural guidance without inversion or retraining. To further improve quality and stability, we introduce \textit{Latent-Condition Decoupling (LCD)}: a principled separation of the timestep condition and the noised latent used in attention extraction. LCD provides finer control over attention quality and eliminates structural artifacts. FreeControl also supports compositional control via reference images assembled from multiple sources, enabling intuitive scene layout design and stronger prompt alignment. FreeControl introduces a new paradigm for test-time control—enabling structurally and semantically aligned, visually coherent generation directly from raw images, with the flexibility for intuitive compositional design and compatibility with modern diffusion models at ~5\% additional cost.
NeurIPS2025官方赛道 · Main Conference Track
UFO-RL: Uncertainty-Focused Optimization for Efficient Reinforcement Learning Data SelectionUFO-RL：面向高效强化学习数据选择的不确定性聚焦优化
Yang Zhao, Kai Xiong, Xiao Ding, Li Du, Yangou Ouyang, Zhouhao Sun, Jiannan Guan, Wenbin Zhang, Bin Liu, Dong Hu, Bing Qin, Ting Liu
单位当前公开元数据未提供，暂不推断
强化学习与智能体机器学习基础与理论方法与模型强化学习高效训练与压缩
NeurIPS2025官方赛道 · Main Conference Track
OSKAR: Omnimodal Self-supervised Knowledge Abstraction and RepresentationOSKAR：全模态自监督知识抽象与表征
Mohamed Abdelfattah, Kaouther Messaoud, Alexandre Alahi
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型计算机视觉与视频多模态与视觉语言方法与模型Transformer与大模型高效训练与压缩自监督与对比学习
官方摘要 英文原文
We present OSKAR, the first multimodal foundation model based on bootstrapped latent feature prediction. Unlike generative or contrastive methods, it avoids memorizing unnecessary details (e.g., pixels), and does not require negative pairs, large memory banks, or hand-crafted augmentations. We propose a novel pretraining strategy: given masked tokens from multiple modalities, predict a subset of missing tokens per modality, supervised by momentum-updated uni-modal target encoders. This design efficiently utilizes the model capacity in learning high-level representations while retaining modality-specific information. Further, we propose a scalable design which decouples the compute cost from the number of modalities using a fixed representative token budget—in both input and target tokens—and introduces a parameter-efficient cross-attention predictor that grounds each prediction in the full multimodal context. We instantiate OSKAR on video, skeleton, and text modalities. Extensive experimental results show that OSKAR's unified pretrained encoder outperforms models with specialized architectures of similar size in action recognition (rgb, skeleton, frozen, low-shot) and localization, video-text retrieval, and video question answering. Project website: https://multimodal-oskar.github.io
NeurIPS2025官方赛道 · Main Conference Track
LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert SpaceLocDiff：通过希尔伯特空间扩散识别地球位置
Zhangyu Wang, Zeping Liu, Jielu Zhang, Zhongliang Zhou, Qian Cao, Nemin Wu, Lan Mu, Yang Song, Yiqun Xie, Ni Lao, Gengchen Mai
单位University of Maine · University of Texas at Austin · University of Georgia · MERCK & CO., INC · OpenAI · University of Maryland, College Park · Google · University of Texas at Austin; Google ResearchOpenAlex 论文记录 ↗
计算机视觉与视频生成式人工智能推荐、检索与数据挖掘方法与模型扩散与流模型
官方摘要 英文原文
Image geolocalization is a fundamental yet challenging task, aiming at inferring the geolocation on Earth where an image is taken. State-of-the-art methods employ either grid-based classification or gallery-based image-location retrieval, whose spatial generalizability significantly suffers if the spatial distribution of test images does not align with the choices of grids and galleries. Recently emerging generative approaches, while getting rid of grids and galleries, use raw geographical coordinates and suffer quality losses due to their lack of multi-scale information. To address these limitations, we propose a multi-scale latent diffusion model called LocDiff for image geolocalization. We developed a novel positional encoding-decoding framework called Spherical Harmonics Dirac Delta (SHDD) Representations, which encodes points on a spherical surface (e.g., geolocations on Earth) into a Hilbert space of Spherical Harmonics coefficients and decodes points (geolocations) by mode-seeking on spherical probability distributions. We also propose a novel SirenNet-based architecture (CS-UNet) to learn an image-based conditional backward process in the latent SHDD space by minimizing a latent KL-divergence loss. To the best of our knowledge, LocDiff is the first image geolocalization model that performs latent diffusion in a multi-scale location encoding space and generates geolocations under the guidance of images. Experimental results show that LocDiff can outperform all state-of-the-art grid-based, retrieval-based, and diffusion-based baselines across 5 challenging global-scale image geolocalization datasets, and demonstrates significantly stronger generalizability to unseen geolocations.
NeurIPS2025官方赛道 · Main Conference Track
Robust and Computation-Aware Gaussian Processes稳健且计算感知的高斯过程
Marshal Sinaga, Julien Martinelli, Samuel Kaski
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Gaussian processes (GPs) are widely used for regression and optimization tasks such as Bayesian optimization (BO) due to their expressiveness and principled uncertainty estimates. However, in settings with large datasets corrupted by outliers, standard GPs and their sparse approximations struggle with computational tractability and robustness. We introduce Robust Computation-aware Gaussian Process (RCaGP), a novel GP model that jointly addresses these challenges by combining a principled treatment of approximation-induced uncertainty with robust generalized Bayesian updating. The key insight is that robustness and approximation-awareness are not orthogonal but intertwined: approximations can exacerbate the impact of outliers, and mitigating one without the other is insufficient. Unlike previous work that focuses narrowly on either robustness or approximation quality, RCaGP combines both in a principled and scalable framework, thus effectively managing both outliers and computational uncertainties introduced by approximations such as low-rank matrix multiplications. Our model ensures more conservative and reliable uncertainty estimates, a property we rigorously demonstrate. Additionally, we establish a robustness property and show that the mean function is key to preserving it, motivating a tailored model selection scheme for robust mean functions. Empirical results confirm that solving these challenges jointly leads to superior performance across both clean and outlier-contaminated settings, both on regression and high-throughput Bayesian optimization benchmarks.
NeurIPS2025官方赛道 · Main Conference Track
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models通过调整初始噪声缓解文本到图像扩散模型的记忆化
Hyeonggeun Han, Sehwan Kim, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee
单位Seoul National University · Konkuk UniversityOpenAlex 论文记录 ↗
生成式人工智能计算机视觉与视频自然语言与大语言模型方法与模型扩散与流模型对齐、安全与隐私
官方摘要 英文原文
Despite their impressive generative capabilities, text-to-image diffusion models often memorize and replicate training data, prompting serious concerns over privacy and copyright. Recent work has attributed this memorization to an attraction basin—a region where applying classifier-free guidance (CFG) steers the denoising trajectory toward memorized outputs—and has proposed deferring CFG application until the denoising trajectory escapes this basin. However, such delays often result in non-memorized images that are poorly aligned with the input prompts, highlighting the need to promote earlier escape so that CFG can be applied sooner in the denoising process. In this work, we show that the initial noise sample plays a crucial role in determining when this escape occurs. We empirically observe that different initial samples lead to varying escape times. Building on this insight, we propose two mitigation strategies that adjust the initial noise—either collectively or individually—to find and utilize initial samples that encourage earlier basin escape. These approaches significantly reduce memorization while preserving image-text alignment.
NeurIPS2025官方赛道 · Datasets and Benchmarks Track
RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation ModelsRoFt-Mol：分子图基础模型稳健微调基准评测
Shikun Liu, Deyu Zou, Nima Shoghi, Victor Fung, Kai Liu, Pan Li
单位Georgia Institute of Technology · The Chinese University of Hong Kong · Shanghai Jiaotong UniversityOpenAlex 论文记录 ↗
AI for Science与医疗方法与模型自监督与对比学习
官方摘要 英文原文
In the era of foundation models, fine-tuning pre-trained models for specific downstream tasks has become crucial. This drives the need for robust fine-tuning methods to address challenges such as model overfitting and sparse labeling. Moleculargraph foundation models (MGFMs) face unique difficulties that complicate fine-tuning. These models are limited by smaller pre-training datasets and more severedata scarcity for downstream tasks, both of which require enhanced model generalization. Moreover, MGFMs must accommodate diverse objectives, including bothregression and classification tasks. To better understand and improve fine-tuningtechniques under these conditions, we classify eight fine-tuning methods into threemechanisms: weight-based, representation-based, and partial fine-tuning. Webenchmark these methods on downstream regression and classification tasks acrosssupervised and self-supervised pre-trained models in diverse labeling settings. Thisextensive evaluation provides valuable insights and informs the design of a refinedrobust fine-tuning method, ROFT-MOL. This approach combines the strengths ofsimple post-hoc weight interpolation with more complex weight ensemble fine-tuning methods, delivering improved performance across both task types whilemaintaining the ease of use inherent in post-hoc weight interpolation.
NeurIPS2025官方赛道 · Main Conference Track
CAT: Content-Adaptive Image TokenizationCAT：内容自适应图像标记化
Junhong Shen, Kushal Tirumala, Michihiro Yasunaga, Ishan Misra, Luke Zettlemoyer, LILI YU, Chunting Zhou
单位当前公开元数据未提供，暂不推断
计算机视觉与视频自然语言与大语言模型方法与模型高效训练与压缩
官方摘要 英文原文
Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity and introducing unnecessary computate overhead for simpler images. To address this, we propose Content-Adaptive Tokenizer (CAT), which dynamically adjusts representation capacity based on the image content and encodes simpler images into fewer tokens. We design (1) a caption-based evaluation system that leverages LLMs to predict content complexity and determine the optimal compression ratio for an image, and (2) a novel nested VAE architecture that performs variable-rate compression in a single model. Trained on images with varying complexity, CAT achieves an average of 15% reduction in rFID across seven detail-rich datasets containing text, humans, and complex textures. On natural image datasets like ImageNet and COCO, it reduces token usage by 18% while maintaining high-fidelity reconstructions. We further evaluate CAT on two downstream tasks. For image classification, CAT consistently improves top-1 accuracy across five datasets spanning diverse domains. For image generation, it boosts training throughput by 23% on ImageNet, leading to more efficient learning and improved FIDs over fixed-token baselines.
NeurIPS2025官方赛道 · Main Conference Track
Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2随机化 MLP 正则化提升 DINOv2 的领域适应与可解释性
Joel Valdivia Ortega, Lorenz Lamm, Franziska Eckardt, Benedikt Schworm, Marion Jasnin, Tingying Peng
单位当前公开元数据未提供，暂不推断
计算机视觉与视频AI for Science与医疗方法与模型自监督与对比学习
官方摘要 英文原文
Vision Transformers (ViTs), such as DINOv2, achieve strong performance across domains but often repurpose low-informative patch tokens in ways that reduce the interpretability of attention and feature maps. This challenge is especially evident in medical imaging, where domain shifts can degrade both performance and transparency. In this paper, we introduce Randomized-MLP (RMLP) regularization, a contrastive learning-based method that encourages more semantically aligned representations. We apply RMLP when fine-tuning DINOv2 to both medical and natural image modalities, showing that it improves or maintains downstream performance while producing more interpretable attention maps. We also provide a mathematical analysis of RMLPs, offering insights into its role in enhancing ViT-based models and advancing our understanding of contrastive learning in this context.
NeurIPS2025官方赛道 · Datasets and Benchmarks Track
CogPhys: Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological SensingCogPhys：基于多模态远程与接触式生理感知的认知负荷评估
Anirudh Bindiganavale Harish, Peikun Guo, Bhargav Ghanekar, Diya Gupta, Akilesh Rajavenkatanarayan, MANOJ SHARMA, Maureen August, Akane Sano, Ashok Veeraraghavan
单位当前公开元数据未提供，暂不推断
多模态与视觉语言方法与模型
NeurIPS2025官方赛道 · Main Conference Track
3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion基于三维高斯泼溅并融合单向与双向特征的场景无关重定位
Junyi Wang, Yuze Wang, Wantong Duan, Meng Wang, Yue Qi
单位当前公开元数据未提供，暂不推断
计算机视觉与视频方法与模型
官方摘要 英文原文
Visual localization is a critical component across various domains. The recent emergence of novel scene representations, such as 3D Gaussian Splatting (3D GS), introduces new opportunities for advancing localization pipelines. In this paper, we propose a novel 3D GS-based framework for RGB based, scene-independent camera relocalization, with three main contributions. First, we design a two-stage pipeline with fully exploiting 3D GS. The pipeline consists of an initial stage, which utilizes 2D-3D correspondences between image pixels and 3D Gaussians, followed by pose refinement using the rendered image by 3D GS. Second, we introduce a 3D GS based Relocalization Network, termed GS-RelocNet, to establish correspondences for initial camera pose estimation. Additionally, we present a refinement network that further optimizes the camera pose. Third, we propose a unidirectional 2D-3D feature fusion module and a bidirectional image feature fusion module, integrated into GS-RelocNet and the refinement network, respectively, to enhance feature sharing across the two stages. Experimental results on public 7 Scenes, Cambridge Landmarks, TUM RGB-D and Bonn demonstrate state-of-the-art performance. Furthermore, the beneficial effects of the two feature fusion modules and pose refinement are also highlighted. In summary, we believe that the proposed framework can be a novel universal localization pipeline for further research.
NeurIPS2025官方赛道 · Main Conference Track
An Ellipsoid Algorithm for Online Convex Optimization一种用于在线凸优化的椭球算法
Zakaria Mhammedi
单位Research, GoogleOpenAlex 论文记录 ↗
机器学习基础与理论方法与模型
ICML2025
Aggregation of Dependent Expert Distributions in Multimodal Variational Autoencoders多模态变分自编码器中相依专家分布的聚合
Rogelio A. Mancisidor, Robert Jenssen, Shujian Yu, Michael Kampffmeyer
单位当前公开元数据未提供，暂不推断
多模态与视觉语言生成式人工智能方法与模型
官方摘要 英文原文
Multimodal learning with variational autoencoders (VAEs) requires estimating joint distributions to evaluate the evidence lower bound (ELBO). Current methods, the product and mixture of experts, aggregate single-modality distributions assuming independence for simplicity, which is an overoptimistic assumption. This research introduces a novel methodology for aggregating single-modality distributions by exploiting the principle of consensus of dependent experts (CoDE), which circumvents the aforementioned assumption. Utilizing the CoDE method, we propose a novel ELBO that approximates the joint likelihood of the multimodal data by learning the contribution of each subset of modalities. The resulting CoDE-VAE model demonstrates better performance in terms of balancing the trade-off between generative coherence and generative quality, as well as generating more precise log-likelihood estimations. CoDE-VAE further minimizes the generative quality gap as the number of modalities increases. In certain cases, it reaches a generative quality similar to that of unimodal VAEs, which is a desirable property that is lacking in most current methods. Finally, the classification accuracy achieved by CoDE-VAE is comparable to that of state-of-the-art multimodal VAE models.
ICML2025
Lightweight Protocols for Distributed Private Quantile Estimation分布式隐私分位数估计的轻量级协议
Anders Aamand, Fabrizio Boninsegna, Abigail Gentle, Jacob Imola, Rasmus Pagh
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型对齐、安全与隐私
官方摘要 英文原文
Distributed data analysis is a large and growing field driven by a massive proliferation of user devices, and by privacy concerns surrounding the centralised storage of data. We consider two adaptive algorithms for estimating one quantile (e.g. the median) when each user holds a single data point lying in a domain $[B]$ that can be queried once through a private mechanism; one under local differential privacy (LDP) and another for shuffle differential privacy (shuffle-DP). In the adaptive setting we present an $\varepsilon$-LDP algorithm which can estimate any quantile within error $\alpha$ only requiring $O(\frac{\log B}{\varepsilon^2\alpha^2})$ users, and an $(\varepsilon,\delta)$-shuffle DP algorithm requiring only $\widetilde{O}((\frac{1}{\varepsilon^2}+\frac{1}{\alpha^2})\log B)$ users. Prior (nonadaptive) algorithms require more users by several logarithmic factors in $B$. We further provide a matching lower bound for adaptive protocols, showing that our LDP algorithm is optimal in the low-$\varepsilon$ regime. Additionally, we establish lower bounds against non-adaptive protocols which paired with our understanding of the adaptive case, proves a fundamental separation between these models.
ICML2025
Breaking the $n^1.5$ Additive Error Barrier for Private and Efficient Graph Sparsification via Private Expander Decomposition通过隐私扩展图分解突破隐私高效图稀疏化的 $n^{1.5}$ 加性误差壁垒
Anders Aamand, Justin Y. Chen, Mina Dalirrooyfard, Slobodan Mitrović, Yuriy Nevmyvaka, Sandeep Silwal, Yinzhan Xu
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
We study differentially private algorithms for graph cut sparsification, a fundamental problem in algorithms, privacy, and machine learning. While significant progress has been made, the best-known private and efficient cut sparsifiers on $n$-node graphs approximate each cut within $\widetilde{O}(n^{1.5})$ additive error and $1+\gamma$ multiplicative error for any $\gamma > 0$ [Gupta, Roth, Ullman TCC’12]. In contrast, inefficient algorithms, i.e., those requiring exponential time, can achieve an $\widetilde{O}(n)$ additive error and $1+\gamma$ multiplicative error [Eliáš, Kapralov, Kulkarni, Lee SODA’20]. In this work, we break the $n^{1.5}$ additive error barrier for private and efficient cut sparsification. We present an $(\varepsilon,\delta)$-DP polynomial time algorithm that, given a non-negative weighted graph, outputs a private synthetic graph approximating all cuts with multiplicative error $1+\gamma$ and additive error $n^{1.25 + o(1)}$ (ignoring dependencies on $\varepsilon, \delta, \gamma$). At the heart of our approach lies a private algorithm for expander decomposition, a popular and powerful technique in (non-private) graph algorithms.
ICML2025
Improved Approximations for Hard Graph Problems using Predictions利用预测改进困难图问题的近似算法
Anders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao Wu
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型
官方摘要 英文原文
We design improved approximation algorithms for NP-hard graph problems by incorporating predictions (e.g., learned from past data). Our prediction model builds upon and extends the $\varepsilon$-prediction framework by Cohen-Addad, d’Orsi, Gupta, Lee, and Panigrahi (NeurIPS 2024). We consider an edge-based version of this model, where each edge provides two bits of information, corresponding to predictions about whether each of its endpoints belong to an optimal solution. Even with weak predictions where each bit is only $\varepsilon$-correlated with the true solution, this information allows us to break approximation barriers in the standard setting. We develop algorithms with improved approximation ratios for MaxCut, Vertex Cover, Set Cover, and Maximum Independent Set problems (among others). Across these problems, our algorithms share a unifying theme, where we separately satisfy constraints related to high degree vertices (using predictions) and low-degree vertices (without using predictions) and carefully combine the answers.
ICML2025
Graph Neural Network Generalization With Gaussian Mixture Model Based Augmentation基于高斯混合模型增强的图神经网络泛化
Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine M. Aboussalah, Michalis Vazirgiannis
单位当前公开元数据未提供，暂不推断
机器学习基础与理论图学习与结构化数据方法与模型理论与分析图神经网络高效训练与压缩
官方摘要 英文原文
Graph Neural Networks (GNNs) have shown great promise in tasks like node and graph classification, but they often struggle to generalize, particularly to unseen or out-of-distribution (OOD) data. These challenges are exacerbated when training data is limited in size or diversity. To address these issues, we introduce a theoretical framework using Rademacher complexity to compute a regret bound on the generalization error and then characterize the effect of data augmentation. This framework informs the design of GRATIN, an efficient graph data augmentation algorithm leveraging the capability of Gaussian Mixture Models (GMMs) to approximate any distribution. Our approach not only outperforms existing augmentation techniques in terms of generalization but also offers improved time complexity, making it highly suitable for real-world applications.
ICML2025
LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language ModelsLMRL Gym：语言模型多轮强化学习基准
Marwa Abdulhai, Isadora White, Charlie Victor Snell, Charles Sun, Joey Hong, Yuexiang Zhai, Kelvin Xu, Sergey Levine
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型强化学习与智能体生成式人工智能方法与模型强化学习
官方摘要 英文原文
Large language models (LLMs) provide excellent text-generation capabilities, but standard prompting and generation methods generally do not lead to intentional or goal-directed agents and might necessitate considerable prompt tuning. Even the best current LLMs rarely ask clarifying questions, engage in explicit information gathering, or take actions that lead to better decisions after multiple turns. Reinforcement learning has the potential to leverage the powerful modeling capabilities of LLMs, as well as their internal representation of textual interactions, to create capable goal-directed language agents. This can enable intentional and temporally extended interactions, such as with humans, the emergence of complex skills such as persuasion, and long-horizon strategic behavior, such as in the context of games. Enabling this requires the community to develop reliable reinforcement learning algorithms for training LLMs. Developing such algorithms requires tasks that can gauge progress on algorithm design, provide accessible and reproducible evaluations for multi-turn interactions, and cover a range of task properties and challenges in improving reinforcement learning algorithms. Our paper introduces the LMRL-Gym benchmark for evaluating multi-turn RL for LLMs, together with an open-source research framework for getting started on multi-turn RL with offline value-based and online policy-based RL methods. Our benchmark consists of 3 Interactive Dialogue tasks and 5 RL Capability tests for a total of 8 tasks, which require multiple rounds of language interaction and cover a range of tasks in open-ended dialogue and text games.
ICML2025
Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?基于自回归组合结构的任务泛化：从 $D$ 个任务学习能否泛化至 $D^T$ 个任务？
Amirhesam Abedsoltan, Huaqing Zhang, Kaiyue Wen, Hongzhou Lin, Jingzhao Zhang, Mikhail Belkin
单位当前公开元数据未提供，暂不推断
机器学习基础与理论自然语言与大语言模型评测与实证研究推理与规划
官方摘要 英文原文
Large language models (LLMs) exhibit remarkable task generalization, solving tasks they were never explicitly trained on with only a few demonstrations. This raises a fundamental question: When can learning from a small set of tasks generalize to a large task family? In this paper, we investigate task generalization through the lens of autoregressive compositional structure, where each task is a composition of T operations, and each operation is among a finite family of D subtasks. This yields a total class of size D^T. We first show that generalization to all D^T tasks is theoretically achievable by training on only Õ(D) tasks. Empirically, we demonstrate that Transformers achieve such exponential task generalization on sparse parity functions via In-context Learning (ICL) and chain-of-thought (CoT) reasoning. We further demonstrate this exponential generalization in arithmetic and language translation, extending beyond parity functions.
ICML2025
Consensus Is All You Get: The Role of Attention in Transformers你所能得到的只有共识：注意力在 Transformer 中的作用
Álvaro Rodrı́guez Abella, João Pedro Silvestre, Paulo Tabuada
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型理论与分析Transformer与大模型
官方摘要 英文原文
A key component of transformers is the attention mechanism orchestrating how each token influences the propagation of every other token along the layers of a transformer. In this paper we provide a rigorous, mathematical analysis of the asymptotic properties of attention in transformers. Although we present several results based on different assumptions, all of them point to the same conclusion, all tokens asymptotically converge to each other, a phenomenon that has been empirically reported in the literature. Our findings are carefully compared with existing theoretical results and illustrated by simulations and experimental studies using the GPT-2 model.
ICML2025
Soup-of-Experts: Pretraining Specialist Models via Parameters AveragingSoup-of-Experts：通过参数平均预训练专家模型
Pierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型
官方摘要 英文原文
Machine learning models are routinely trained on a mixture of different data domains. Different domain weights yield very different downstream performances. We propose the Soup-of-Experts, a novel architecture that can instantiate a model at test time for any domain weights with minimal computational cost and without re-training the model. Our architecture consists of a bank of expert parameters, which are linearly combined to instantiate one model. We learn the linear combination coefficients as a function of the input domain weights. To train this architecture, we sample random domain weights, instantiate the corresponding model, and backprop through one batch of data sampled with these domain weights. We demonstrate how our approach obtains small specialized models on several language modeling tasks quickly. Soup-of-Experts are particularly appealing when one needs to ship many different specialist models quickly under a size constraint.
ICML2025
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models参数量与浮点运算量：混合专家语言模型最优稀疏度的缩放定律
Samira Abnar, Harshay Shah, Dan Busbridge, Alaaeldin El-Nouby, Joshua M. Susskind, Vimal Thilak
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型高效训练与压缩
官方摘要 英文原文
Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the compute per example. While scaling typically involves increasing both, the precise interplay between these factors and their combined contribution to overall capacity remains not fully understood. We explore this relationship in the context of sparse Mixture-of-Expert models (MoEs), which allow scaling the number of parameters without proportionally increasing the FLOPs per example. We investigate how varying the sparsity level, i.e., the ratio of non-active to total parameters, affects model performance in terms of both pretraining and downstream performance. We find that under different constraints (e.g. parameter size and total training compute), there is an optimal level of sparsity that improves both training efficiency and model performance.These results provide a better understanding of the impact of sparsity in scaling laws for MoEs and complement existing works in this area, offering insights for designing more efficient architectures.
ICML2025
Grokking in the Wild: Data Augmentation for Real-World Multi-Hop Reasoning with Transformers真实环境中的顿悟学习：面向 Transformer 现实多跳推理的数据增强
Roman Abramov, Felix Steinbauer, Gjergji Kasneci
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型推理与规划
官方摘要 英文原文
Transformers have achieved great success in numerous NLP tasks but continue to exhibit notable gaps in multi-step factual reasoning, especially when real-world knowledge is sparse. Recent advances in grokking have demonstrated that neural networks can transition from memorizing to perfectly generalizing once they detect underlying logical patterns – yet these studies have primarily used small, synthetic tasks. In this paper, for the first time, we extend grokking to real-world factual data and address the challenge of dataset sparsity by augmenting existing knowledge graphs with carefully designed synthetic data to raise the ratio $\phi_r$ of inferred facts to atomic facts above the threshold required for grokking. Surprisingly, we find that even factually incorrect synthetic data can strengthen emergent reasoning circuits rather than degrade accuracy, as it forces the model to rely on relational structure rather than memorization. When evaluated on multi-hop reasoning benchmarks, our approach achieves up to 95–100% accuracy on 2WikiMultiHopQA – substantially improving over strong baselines and matching or exceeding current state-of-the-art results. We further provide an in-depth analysis of how increasing $\phi_r$ drives the formation of generalizing circuits inside Transformers. Our findings suggest that grokking-based data augmentation can unlock implicit multi-hop reasoning capabilities, opening the door to more robust and interpretable factual reasoning in large-scale language models.
ICML2025
EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security VulnerabilitiesEnIGMA：交互式工具显著帮助语言模型智能体发现安全漏洞
Talor Abramovich, Meet Udeshi, Minghao Shao, Kilian Lieret, Haoran Xi, Kimberly Milner, Sofija Jancheska, John Yang, Carlos E Jimenez, Farshad Khorrami, Prashanth Krishnamurthy, Brendan Dolan-Gavitt, Muhammad Shafique, Karthik R Narasimhan, Ramesh Karri, Ofir Press
单位当前公开元数据未提供，暂不推断
强化学习与智能体方法与模型
官方摘要 英文原文
Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present EnIGMA , an LM agent for autonomously solving Capture The Flag (CTF) challenges. We introduce new tools and interfaces to improve the agent’s ability to find and exploit security vulnerabilities, focusing on interactive terminal programs. These novel Interactive Agent Tools enable LM agents, for the first time, to run interactive utilities, such as a debugger and a server connection tool, which are essential for solving these challenges. Empirical analysis on 390 CTF challenges across four benchmarks demonstrate that these new tools and interfaces substantially improve our agent’s performance, achieving state-of-the-art results on NYU CTF, Intercode-CTF, and CyBench. Finally, we analyze data leakage, developing new methods to quantify it and identifying a new phenomenon we term soliloquizing , where the model self-generates hallucinated observations without interacting with the environment.
ICML2025
Star Attention: Efficient LLM Inference over Long Sequences星形注意力：面向长序列的高效大语言模型推理
Shantanu Acharya, Fei Jia, Boris Ginsburg
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型Transformer与大模型高效训练与压缩
官方摘要 英文原文
Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation that improves computational efficiency by sharding attention across multiple hosts while minimizing communication overhead. In the first phase, the context is processed using blockwise-local attention across hosts, in parallel. In the second phase, query and response tokens attend to all prior cached tokens through sequence-global attention. Star Attention integrates seamlessly with most Transformer-based LLMs trained with global attention, reducing memory requirements and inference time by up to 11x while preserving 97-100% of accuracy.
ICML2025
Geometric Median (GM) Matching for Robust k-Subset Selection from Noisy Data用于从噪声数据中稳健选择 k 元子集的几何中位数匹配
Anish Acharya, Sujay Sanghavi, Alex Dimakis, Inderjit S Dhillon
单位当前公开元数据未提供，暂不推断
计算机视觉与视频理论与分析对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Data pruning – the combinatorial task of selecting a small and representative subset from a large dataset, is crucial for mitigating the enormous computational costs associated with training data-hungry modern deep learning models at scale. Since large-scale data collections are invariably noisy, developing data pruning strategies that remain robust even in the presence of corruption is critical in practice. Existing data pruning methods often fail under high corruption rates due to their reliance on empirical mean estimation, which is highly sensitive to outliers. In response, this work proposes Geometric Median (GM) Matching, a novel k-subset selection strategy that leverages the Geometric Median (GM) , a robust estimator with an optimal breakdown point of 1/2; to enhance resilience against noisy data. Our method iteratively selects a $k$-subset such that the mean of the subset approximates the GM of the (potentially) noisy dataset, ensuring robustness even under arbitrary corruption. We provide theoretical guarantees, showing that GM Matching enjoys an improved $\mathcal{O}(1/k)$ convergence rate, outperforming $\mathcal{O}(1/\sqrt{k})$ scaling of uniform sampling, even under arbitrary corruption. Extensive experiments across image classification and image generation tasks demonstrate that GM Matching consistently outperforms existing pruning approaches, particularly in high-corruption settings; making it a strong baseline for robust data pruning.
ICML2025
Inverse Problem Sampling in Latent Space Using Sequential Monte Carlo基于序贯蒙特卡洛的潜在空间逆问题采样
Idan Achituve, Hai Victor Habi, Amir Rosenfeld, Arnon Netzer, Idit Diamant, Ethan Fetaya
单位当前公开元数据未提供，暂不推断
生成式人工智能计算机视觉与视频评测与实证研究扩散与流模型
官方摘要 英文原文
In image processing, solving inverse problems is the task of finding plausible reconstructions of an image that was corrupted by some (usually known) degradation operator. Commonly, this process is done using a generative image model that can guide the reconstruction towards solutions that appear natural. The success of diffusion models over the last few years has made them a leading candidate for this task. However, the sequential nature of diffusion models makes this conditional sampling process challenging. Furthermore, since diffusion models are often defined in the latent space of an autoencoder, the encoder-decoder transformations introduce additional difficulties. To address these challenges, we suggest a novel sampling method based on sequential Monte Carlo (SMC) in the latent space of diffusion models. We name our method LD-SMC. We define a generative model for the data using additional auxiliary observations and perform posterior inference with SMC sampling based on a backward diffusion process. Empirical evaluations on ImageNet and FFHQ show the benefits of LD-SMC over competing methods in various inverse problem tasks and especially in challenging inpainting tasks.
ICML2025
An in depth look at the Procrustes-Wasserstein distance: properties and barycenters深入解析 Procrustes–Wasserstein 距离：性质与重心
Davide Adamo, Marco Corneli, Manon Vuillien, Emmanuelle Vila
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型对齐、安全与隐私
官方摘要 英文原文
Due to its invariance to rigid transformations such as rotations and reflections, Procrustes-Wasserstein (PW) was introduced in the literature as an optimal transport (OT) distance, alternative to Wasserstein and more suited to tasks such as the alignment and comparison of point clouds. Having that application in mind, we carefully build a space of discrete probability measures and show that over that space PW actually is a distance. Algorithms to solve the PW problems already exist, however we extend the PW framework by discussing and testing several initialization strategies. We then introduce the notion of PW barycenter and detail an algorithm to estimate it from the data. The result is a new method to compute representative shapes from a collection of point clouds. We benchmark our method against existing OT approaches, demonstrating superior performance in scenarios requiring precise alignment and shape preservation. We finally show the usefulness of the PW barycenters in an archaeological context. Our results highlight the potential of PW in advancing 2D and 3D point cloud analysis for machine learning and computational geometry applications.
ICML2025
From Mechanistic Interpretability to Mechanistic Biology: Training, Evaluating, and Interpreting Sparse Autoencoders on Protein Language Models从机制可解释性到机制生物学：蛋白质语言模型稀疏自编码器的训练、评估与解释
Etowah Adams, Liam Bai, Minji Lee, Yiyang Yu, Mohammed Alquraishi
单位Department of Systems Biology, Columbia University · Ginkgo Bioworks, Boston · Ginkgo BioworksOpenAlex 论文记录 ↗
AI for Science与医疗自然语言与大语言模型评测与实证研究
官方摘要 英文原文
Protein language models (pLMs) are powerful predictors of protein structure and function, learning through unsupervised training on millions of protein sequences. pLMs are thought to capture common motifs in protein sequences, but the specifics of pLM features are not well understood. Identifying these features would not only shed light on how pLMs work, but potentially uncover novel protein biologystudying the model to study the biology. Motivated by this, we train sparse autoencoders (SAEs) on the residual stream of a pLM, ESM-2. By characterizing SAE features, we determine that pLMs use a combination of generic features and family-specific features to represent a protein. In addition, we demonstrate how known sequence determinants of properties such as thermostability and subcellular localization can be identified by linear probing of SAE features. For predictive features without known functional associations, we hypothesize their role in unknown mechanisms and provide visualization tools to aid their interpretation. Our study gives a better understanding of the limitations of pLMs, and demonstrates how SAE features can be used to help generate hypotheses for biological mechanisms. We release our code, model weights, and feature visualizer.
ICML2025
Sparse Training from Random Initialization: Aligning Lottery Ticket Masks using Weight Symmetry从随机初始化开始的稀疏训练：利用权重对称性对齐彩票掩码
Mohammed Adnan, Rohan Jain, Ekansh Sharma, Rahul Krishnan, Yani Ioannou
单位当前公开元数据未提供，暂不推断
机器学习基础与理论方法与模型
官方摘要 英文原文
The Lottery Ticket Hypothesis (LTH) suggests there exists a sparse LTH mask and weights that achieve the same generalization performance as the dense model while using significantly fewer parameters. However, finding a LTH solution is computationally expensive, and a LTH sparsity mask does not generalize to other random weight initializations. Recent work has suggested that neural networks trained from random initialization find solutions within the same basin modulo permutation, and proposes a method to align trained models within the same loss basin. We hypothesize that misalignment of basins is the reason why LTH masks do not generalize to new random initializations and propose permuting the LTH mask to align with the new optimization basin when performing sparse training from a different random init. We empirically show a significant increase in generalization when sparse training from random initialization with the permuted mask as compared to using the non-permuted LTH mask, on multiple datasets (CIFAR-10/100 & ImageNet) and models (VGG11 & ResNet20/50).
ICML2025
Design Considerations in Offline Preference-based RL离线偏好强化学习中的设计考量
Alekh Agarwal, Christoph Dann, Teodor Vanislavov Marinov
单位当前公开元数据未提供，暂不推断
强化学习与智能体机器学习基础与理论理论与分析强化学习
官方摘要 英文原文
Offline algorithms for Reinforcement Learning from Human Preferences (RLHF), which use only a fixed dataset of sampled responses given an input, and preference feedback among these responses, have gained increasing prominence in the literature on aligning language models. In this paper, we study how the different design choices made in methods such as DPO, IPO, SLiC and many variants influence the quality of the learned policy, from a theoretical perspective. Our treatment yields insights into the choices of loss function, the policy which is used to normalize log-likelihoods, and also the role of the data sampling policy. Notably, our results do not rely on the standard reparameterization-style arguments used to motivate some of the algorithms in this family, which allows us to give a unified treatment to a broad class of methods. We also conduct a small empirical study to verify some of the theoretical findings on a standard summarization benchmark.
ICML2025
Optimal Fair Learning Robust to Adversarial Distribution Shift对对抗性分布偏移稳健的最优公平学习
Sushant Agarwal, Amit Deshpande, Rajmohan Rajaraman, Ravi Sundaram
单位当前公开元数据未提供，暂不推断
其他机器学习研究评测与实证研究对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Previous work in fair machine learning has characterised the Fair Bayes Optimal Classifier (BOC) on a given distribution for both deterministic and randomized classifiers. We study the robustness of the Fair BOC to adversarial noise in the data distribution. Kearns & Li (1988) implies that the accuracy of the deterministic BOC without any fairness constraints is robust (Lipschitz) to malicious noise in the data distribution. We demonstrate that their robustness guarantee breaks down when we add fairness constraints. Hence, we consider the randomized Fair BOC, and our central result is that its accuracy is robust to malicious noise in the data distribution. Our robustness result applies to various fairness constraints—Demographic Parity, Equal Opportunity, Predictive Equality. Beyond robustness, we demonstrate that randomization leads to better accuracy and efficiency. We show that the randomized Fair BOC is nearly-deterministic, and gives randomized predictions on at most one data point, hence availing numerous benefits of randomness, while using very little of it.
ICML2025
FedECADO: A Dynamical System Model of Federated LearningFedECADO：联邦学习的动力系统模型
Aayushya Agarwal, Gauri Joshi, Lawrence Pileggi
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型系统与工具
官方摘要 英文原文
Federated learning harnesses the power of distributed optimization to train a unified machine learning model across separate clients. However, heterogeneous data distributions and computational workloads can lead to inconsistent updates and limit model performance. This work tackles these challenges by proposing FedECADO, a new algorithm inspired by a dynamical system representation of the federated learning process. FedECADO addresses non-IID data distribution through an aggregate sensitivity model that reflects the amount of data processed by each client. To tackle heterogeneous computing, we design a multi-rate integration method with adaptive step-size selections that synchronizes active client updates in continuous time. Compared to prominent techniques, including FedProx, FedExp, and FedNova, FedECADO achieves higher classification accuracies in numerous heterogeneous scenarios.
ICML2025
The Missing Alignment Link of In-context Learning on Sequences序列上下文学习中缺失的对齐环节
Harshvardhan Agarwal, Sunita Sarawagi
单位当前公开元数据未提供，暂不推断
自然语言与大语言模型方法与模型Transformer与大模型对齐、安全与隐私高效训练与压缩
官方摘要 英文原文
Large language models (LLMs) have demonstrated the capability to perform in-context learning (ICL) for completely unseen tasks in classification or language completion. Sequence to sequence (seq2seq) is another popular task category with several applications seeking quick adaptation with ICL. We present a systematic analysis of the ICL capability of LLMs on Seq2Seq tasks using a formal structured language-pair. Our study reveals a critical limitation: except for very short input sequences, ICL fails to achieve consistent learning across all output positions. This exposes a fundamental weakness of modern LLMs — their inability to effectively uncover the alignment between input and output sequences. Consequently, this limitation results in incomplete induction heads, which are essential for in-context learning of new discrete mappings. To address these limitations, we propose ICA-Tune, a method for focused fine-tuning of an LLM using in-context examples. We present a mechanistic evaluation with two accuracy probes to show how input-output alignment emerges in middle layers of an LLM without direct supervision. This alignment leads to an abrupt jump in the completeness of the induction heads in higher layers. We show that, compared to standard fine-tuning, ICA-Tune enables more sample efficient learning and better generalization to OOD instances.
ICML2025
Proto Successor Measure: Representing the Behavior Space of an RL Agent原型后继测度：表征强化学习智能体的行为空间
Siddhant Agarwal, Harshit Sikchi, Peter Stone, Amy Zhang
单位当前公开元数据未提供，暂不推断
强化学习与智能体方法与模型强化学习
官方摘要 英文原文
Having explored an environment, intelligent agents should be able to transfer their knowledge to most downstream tasks within that environment without additional interactions. Referred to as "zero-shot learning", this ability remains elusive for general-purpose reinforcement learning algorithms. While recent works have attempted to produce zero-shot RL agents, they make assumptions about the nature of the tasks or the structure of the MDP. We present Proto Successor Measure : the basis set for all possible behaviors of a Reinforcement Learning Agent in a dynamical system. We prove that any possible behavior (represented using visitation distributions) can be represented using an affine combination of these policy-independent basis functions. Given a reward function at test time, we simply need to find the right set of linear weights to combine these bases corresponding to the optimal policy. We derive a practical algorithm to learn these basis functions using reward-free interaction data from the environment and show that our approach can produce the near-optimal policy at test time for any given reward function without additional environmental interactions. Project page: agarwalsiddhant10.github.io/projects/psm.html.
ICML2025
AlphaVerus: Bootstrapping Formally Verified Code Generation through Self-Improving Translation and TreefinementAlphaVerus：通过自改进翻译与 Treefinement 自举生成形式化验证代码
Pranjal Aggarwal, Bryan Parno, Sean Welleck
单位当前公开元数据未提供，暂不推断
生成式人工智能自然语言与大语言模型方法与模型
官方摘要 英文原文
Automated code generation with large language models has gained significant traction, but there remains no guarantee of the correctness of generated code. We aim to use formal verification to provide mathematical guarantees that the generated code is correct. However, generating formally verified code with LLMs is hindered by the scarcity of training data and the complexity of formal proofs. To tackle this challenge, we introduce AlphaVerus, a self-improving framework that bootstraps formally verified code generation by iteratively translating programs from a higher-resource language and leveraging feedback from a verifier. AlphaVerus operates in three phases: exploration of candidate translations, Treefinement – a novel tree search algorithm for program refinement using verifier feedback, and filtering misaligned specifications and programs to prevent reward hacking. Through this iterative process, AlphaVerus enables the LLaMA-3.1-70B model to generate verified code without human intervention or model finetuning. AlphaVerus shows an ability to generate formally verified solutions for HumanEval and MBPP, laying the groundwork for truly trustworthy code-generation agents.
ICML2025
NextCoder: Robust Adaptation of Code LMs to Diverse Code EditsNextCoder：代码语言模型对多样化代码编辑的稳健适应
Tushar Aggarwal, Swayam Singh, Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan
单位当前公开元数据未提供，暂不推断
生成式人工智能自然语言与大语言模型方法与模型对齐、安全与隐私
官方摘要 英文原文
Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this shortcoming through (1) a novel synthetic data generation pipeline and (2) a robust model adaptation algorithm. Starting with seed code examples and diverse editing criteria, our pipeline generates high-quality samples comprising original and modified code, along with natural language instructions in different styles and verbosity. Today’s code LMs come bundled with strong abilities, such as code generation and instruction following, which should not be lost due to fine-tuning. To ensure this, we propose a novel adaptation algorithm, SeleKT, that (a) leverages a dense gradient-based step to identify the weights that are most important for code editing, and (b) does a sparse projection onto the base model to avoid overfitting. Using our approach, we obtain a new series of models NextCoder (adapted from QwenCoder-2.5) that achieves strong results on five code-editing benchmarks, outperforming comparable size models and even several larger ones. We show the generality of our approach on two model families DeepSeekCoder and QwenCoder), compare against other fine-tuning approaches, and demonstrate robustness by showing retention of code generation and general problem-solving abilities post adaptation. We opensource the models, synthetic dataset, and implementation at https://aka.ms/nextcoder.
ICML2025
FunBO: Discovering Acquisition Functions for Bayesian Optimization with FunSearchFunBO：利用 FunSearch 发现贝叶斯优化的采集函数
Virginia Aglietti, Ira Ktena, Jessica Schrouff, Eleni Sgouritsa, Francisco Ruiz, Alan Malek, Alexis Bellot, Silvia Chiappa
单位当前公开元数据未提供，暂不推断
机器学习基础与理论自然语言与大语言模型方法与模型Transformer与大模型高效训练与压缩
官方摘要 英文原文
The sample efficiency of Bayesian optimization algorithms depends on carefully crafted acquisition functions (AFs) guiding the sequential collection of function evaluations. The best-performing AFs can vary significantly across optimization problems, often requiring ad-hoc and problem-specific choices. This work tackles the challenge of designing novel AFs that perform well across a variety of experimental settings. Based on FunSearch, a recent work using Large Language Models (LLMs) for discovery in mathematical sciences, we propose FunBO, an LLM-based method that can be used to learn new AFs written in computer code by leveraging access to a number of evaluations for a limited set of objective functions. We provide the analytic expression of all discovered AFs and evaluate them on various global optimization benchmarks and hyperparameter optimization tasks. We show how FunBO identifies AFs that generalize well both in and out of the training distribution of functions, thus outperforming established general-purpose AFs and achieving competitive performance against AFs that are customized to specific function types and are learned via transfer-learning algorithms.
ICML2025
Understanding the difficulties of posterior predictive estimation理解后验预测估计的难点
Abhinav Agrawal, Justin Domke
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型理论与分析
官方摘要 英文原文
Predictive posterior densities (PPDs) are essential in approximate inference for quantifying predictive uncertainty and comparing inference methods. Typically, PPDs are estimated by simple Monte Carlo (MC) averages. In this paper, we expose a critical under-recognized issue: the signal-to-noise ratio (SNR) of the simple MC estimator can sometimes be extremely low, leading to unreliable estimates. Our main contribution is a theoretical analysis demonstrating that even with exact inference, SNR can decay rapidly with an increase in (a) the mismatch between training and test data, (b) the dimensionality of the latent space, or (c) the size of test data relative to training data. Through several examples, we empirically verify these claims and show that these factors indeed lead to poor SNR and unreliable PPD estimates (sometimes, estimates are off by hundreds of nats even with a million samples). While not the primary focus, we also explore an adaptive importance sampling approach as an illustrative way to mitigate the problem, where we learn the proposal distribution by maximizing a variational proxy to the SNR. Taken together, our findings highlight an important challenge and provide essential insights for reliable estimation.
ICML2025
Optimal Sensor Scheduling and Selection for Continuous-Discrete Kalman Filtering with Auxiliary Dynamics具有辅助动力学的连续—离散卡尔曼滤波最优传感器调度与选择
Mohamad Al Ahdab, John Leth, Zheng-Hua Tan
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型高效训练与压缩
官方摘要 英文原文
We study the Continuous-Discrete Kalman Filter (CD-KF) for State-Space Models (SSMs) where continuous-time dynamics are observed via multiple sensors with discrete, irregularly timed measurements. Our focus extends to scenarios in which the measurement process is coupled with the states of an auxiliary SSM. For instance, higher measurement rates may increase energy consumption or heat generation, while a sensor’s accuracy can depend on its own spatial trajectory or that of the measured target. Each sensor thus carries distinct costs and constraints associated with its measurement rate and additional constraints and costs on the auxiliary state. We model measurement occurrences as independent Poisson processes with sensor-specific rates and derive an upper bound on the mean posterior covariance matrix of the CD-KF along the mean auxiliary state. The bound is continuously differentiable with respect to the measurement rates, which enables efficient gradient-based optimization. Exploiting this bound, we propose a finite-horizon optimal control framework to optimize measurement rates and auxiliary-state dynamics jointly. We further introduce a deterministic method for scheduling measurement times from the optimized rates. Empirical results in state-space filtering and dynamic temporal Gaussian process regression demonstrate that our approach achieves improved trade-offs between resource usage and estimation accuracy.
ICML2025
Online Laplacian-Based Representation Learning in Reinforcement Learning强化学习中的在线拉普拉斯表征学习
Maheed H. Ahmed, Jayanth Bhargav, Mahsa Ghasemi
单位当前公开元数据未提供，暂不推断
机器学习基础与理论强化学习与智能体方法与模型理论与分析强化学习高效训练与压缩
官方摘要 英文原文
Representation learning plays a crucial role in reinforcement learning, especially in complex environments with high-dimensional and unstructured states. Effective representations can enhance the efficiency of learning algorithms by improving sample efficiency and generalization across tasks. This paper considers the Laplacian-based framework for representation learning, where the eigenvectors of the Laplacian matrix of the underlying transition graph are leveraged to encode meaningful features from raw sensory observations of the states. Despite the promising algorithmic advances in this framework, it remains an open question whether the Laplacian-based representations can be learned online and with theoretical guarantees along with policy learning. We address this by formulating an online optimization approach using the Asymmetric Graph Drawing Objective (AGDO) and analyzing its convergence via online projected gradient descent under mild assumptions. Our extensive simulation studies empirically validate the convergence guarantees to the true Laplacian representation. Furthermore, we provide insights into the compatibility of different reinforcement learning algorithms with online representation learning.
ICML2025
Otter: Generating Tests from Issues to Validate SWE PatchesOtter：从问题单生成测试以验证软件工程补丁
Toufique Ahmed, Jatin Ganhotra, Rangeet Pan, Avraham Shinnar, Saurabh Sinha, Martin Hirzel
单位当前公开元数据未提供，暂不推断
其他机器学习研究方法与模型Transformer与大模型
官方摘要 英文原文
While there has been plenty of work on generating tests from existing code, there has been limited work on generating tests from issues. A correct test must validate the code patch that resolves the issue. This paper focuses on the scenario where that code patch does not yet exist. Doing so supports two major use-cases. First, it supports TDD (test-driven development), the discipline of "test first, write code later" that has well-documented benefits for human software engineers. Second, it also validates SWE (software engineering) agents, which generate code patches for resolving issues. This paper introduces TDD-Bench-Verified, a benchmark for generating tests from issues, and Otter, an LLM-based solution for this task. Otter augments LLMs with rule-based analysis to check and repair their outputs, and introduces a novel self-reflective action planner. Experiments show Otter outperforming state-of-the-art systems for generating tests from issues, in addition to enhancing systems that generate patches from issues. We hope that Otter helps make developers more productive at resolving issues and leads to more robust, well-tested code.
这个页面做什么，也不做什么。
本站保存公开元数据和链接，不复制、不二次分发论文文件。
PDF 与摘要来自官方论文页；单位和辅助标签显示各自来源与边界。
首批 90 篇是功能试点，不代表最佳论文、影响力或推荐次序。当前确认 31 条正式代码入口。