三大顶会，
从论文直接进入。

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

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

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

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

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

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

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

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

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

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 ↗

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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 ↗

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

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

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

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

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

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

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 ↗

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 ↗

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 ↗

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

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 ↗

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 ↗

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

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 ↗

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