ICML 2025 Papers

3,340 papers found • Page 7 of 67

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Zhengxuan Wu, Aryaman Arora, Atticus Geiger et al.

ICML 2025spotlight
100
citations

Backdoor Attacks in Token Selection of Attention Mechanism

Yunjuan Wang, Raman Arora

ICML 2025poster

BackSlash: Rate Constrained Optimized Training of Large Language Models

Jun Wu, jiangtao wen, Yuxing Han

ICML 2025poster

BalancEdit: Dynamically Balancing the Generality-Locality Trade-off in Multi-modal Model Editing

Dongliang Guo, Mengxuan Hu, Zihan Guan et al.

ICML 2025poster

Balanced Learning for Domain Adaptive Semantic Segmentation

Wangkai Li, Rui Sun, Bohao Liao et al.

ICML 2025poster

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Joshua Southern, Yam Eitan, Guy Bar Shalom et al.

ICML 2025poster

Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach

Jin Zhu, Jingyi Li, Hongyi Zhou et al.

ICML 2025poster

Balancing Model Efficiency and Performance: Adaptive Pruner for Long-tailed Data

Zhe Zhao, HaiBin Wen, Pengkun Wang et al.

ICML 2025poster

Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing

Zhuoying Li, Zhu Xu, Yuxin Peng et al.

ICML 2025poster

Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data

Corinna Cortes, Anqi Mao, Mehryar Mohri et al.

ICML 2025poster

BAME: Block-Aware Mask Evolution for Efficient N:M Sparse Training

Chenyi yang, Wenjie Nie, Yuxin Zhang et al.

ICML 2025poster

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

Yunlong Hou, Fengzhuo Zhang, Cunxiao Du et al.

ICML 2025poster

BAnG: Bidirectional Anchored Generation for Conditional RNA Design

Roman Klypa, Alberto Bietti, Sergei Grudinin

ICML 2025poster
2
citations

Banyan: Improved Representation Learning with Explicit Structure

Mattia Opper, Siddharth N

ICML 2025poster

BARK: A Fully Bayesian Tree Kernel for Black-box Optimization

Toby Boyne, Jose Pablo Folch, Robert Lee et al.

ICML 2025poster
3
citations

BARNN: A Bayesian Autoregressive and Recurrent Neural Network

Dario Coscia, Max Welling, Nicola Demo et al.

ICML 2025oral
3
citations

Batch List-Decodable Linear Regression via Higher Moments

Ilias Diakonikolas, Daniel Kane, Sushrut Karmalkar et al.

ICML 2025poster

BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation

Lian Liu, Xiandong Zhao, Guanchen Li et al.

ICML 2025poster

BaxBench: Can LLMs Generate Correct and Secure Backends?

Mark Vero, Niels Mündler, Viktor Chibotaru et al.

ICML 2025spotlight

Bayesian Active Learning for Bivariate Causal Discovery

Yuxuan Wang, Mingzhou Liu, Xinwei Sun et al.

ICML 2025poster

Bayesian Basis Function Approximation for Scalable Gaussian Process Priors in Deep Generative Models

Mehmet Yiğit Balık, Maksim Sinelnikov, Priscilla Ong et al.

ICML 2025poster

Bayesian Inference for Correlated Human Experts and Classifiers

Markelle Kelly, Alex Boyd, Samuel Showalter et al.

ICML 2025poster

Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks

Dongwoo Lee, Dong Bok Lee, Steven Adriaensen et al.

ICML 2025poster

Bayesian Optimization from Human Feedback: Near-Optimal Regret Bounds

Aya Kayal, Sattar Vakili, Laura Toni et al.

ICML 2025poster

Bayesian Weight Enhancement with Steady-State Adaptation for Test-time Adaptation in Dynamic Environments

Jae-Hong Lee

ICML 2025poster

BCE vs. CE in Deep Feature Learning

Qiufu Li, Huibin Xiao, Linlin Shen

ICML 2025poster

BDC-CLIP: Brownian Distance Covariance for Adapting CLIP to Action Recognition

Fei Long, Xiaoou Li, jiaming Lv et al.

ICML 2025oral

Be a Goldfish: Forgetting Bad Conditioning in Sparse Linear Regression via Variational Autoencoders

Kuheli Pratihar, Debdeep Mukhopadhyay

ICML 2025poster

BECAME: Bayesian Continual Learning with Adaptive Model Merging

Mei Li, Yuxiang Lu, Qinyan Dai et al.

ICML 2025poster

Be Confident: Uncovering Overfitting in MLLM Multi-Task Tuning

Wenke Huang, Jian Liang, Guancheng Wan et al.

ICML 2025oral

Behavior-agnostic Task Inference for Robust Offline In-context Reinforcement Learning

Long Ma, Fangwei Zhong, Yizhou Wang

ICML 2025poster

Behavioral Exploration: Learning to Explore via In-Context Adaptation

Andrew Wagenmaker, Zhiyuan Zhou, Sergey Levine

ICML 2025oral
1
citations

Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning

Chen-Xiao Gao, Chenyang Wu, Mingjun Cao et al.

ICML 2025poster

Bellman Unbiasedness: Toward Provably Efficient Distributional Reinforcement Learning with General Value Function Approximation

Taehyun Cho, Seungyub Han, Seokhun Ju et al.

ICML 2025poster

Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective

Qingchuan Ma, Yuhang Wu, Xiawu Zheng et al.

ICML 2025poster

Benchmarking Quantum Reinforcement Learning

Nico Meyer, Christian Ufrecht, George Yammine et al.

ICML 2025poster

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

Jingfeng Wu, Peter Bartlett, Matus Telgarsky et al.

ICML 2025poster

Benign Overfitting in Token Selection of Attention Mechanism

Keitaro Sakamoto, Issei Sato

ICML 2025poster

Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety

Zihan Guan, Mengxuan Hu, Ronghang Zhu et al.

ICML 2025spotlight
11
citations

Best of Both Worlds: Advantages of Hybrid Graph Sequence Models

Ali Behrouz, Ali Parviz, Mahdi Karami et al.

ICML 2025poster
4
citations

Best of Both Worlds: Regret Minimization versus Minimax Play

Adrian Müller, Jon Schneider, EFSTRATIOS PANTELEIMON SKOULAKIS et al.

ICML 2025poster

BEST-Route: Adaptive LLM Routing with Test-Time Optimal Compute

Dujian Ding, Ankur Mallick, Shaokun Zhang et al.

ICML 2025poster
16
citations

Best Subset Selection: Optimal Pursuit for Feature Selection and Elimination

Zhihan Zhu, Yanhao Zhang, Yong Xia

ICML 2025poster

Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance

Fan Li, Xuan Wang, Min Qi et al.

ICML 2025spotlight

Beyond Atoms: Enhancing Molecular Pretrained Representations with 3D Space Modeling

Shuqi Lu, Xiaohong Ji, Bohang Zhang et al.

ICML 2025poster

Beyond Bradley-Terry Models: A General Preference Model for Language Model Alignment

Yifan Zhang, Ge Zhang, Yue Wu et al.

ICML 2025poster
9
citations

Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning

Ze'ev Zukerman, Bassel Hamoud, Kfir Levy

ICML 2025poster

Beyond Confidence: Exploiting Homogeneous Pattern for Semi-Supervised Semantic Segmentation

Rui Sun, Huayu Mai, Wangkai Li et al.

ICML 2025poster

Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts

Li gengluo, Huawen Shen, Yu ZHOU

ICML 2025poster

Beyond CVaR: Leveraging Static Spectral Risk Measures for Enhanced Decision-Making in Distributional Reinforcement Learning

Mehrdad Moghimi, Hyejin Ku

ICML 2025poster
3
citations