arXivSub Start free trial

ICML 2025 Papers with Code — Page 8

International Conference on Machine Learning · 722 papers

Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

Liang CHEN, Kam-Fai Wong (Chinese University of Hong Kong)

CodeOptimizationData-Centric LearningSupervised Fine-TuningText

🎯 What it does: A data-forgetfulness-based alignment method VAA is proposed, which balances forgettable and memorable samples through group learning to enhance robustness against harmful fine-tuning.

Wasserstein Policy Optimization

David Pfau (Google DeepMind), Hado van Hasselt (Google DeepMind)

CodeOptimizationReinforcement LearningPhysics Related

🎯 What it does: A Wasserstein gradient flow-based actor-critic algorithm, WPO, is proposed for policy optimization in continuous action spaces.

Watch Out Your Album! On the Inadvertent Privacy Memorization in Multi-Modal Large Language Models

Tianjie Ju (Shanghai Jiao Tong University), Gongshen Liu (Shanghai Jiao Tong University)

CodeSafty and PrivacyTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelMultimodality

🎯 What it does: This study investigates whether multimodal large models unintentionally memorize privacy content unrelated to tasks during the fine-tuning process and proposes a detection method based on gradient similarity and hierarchical probing.

Weakly-Supervised Contrastive Learning for Imprecise Class Labels

Zi-Hao Zhou (Southeast University), Min-Ling Zhang (Southeast University)

CodeClassificationRepresentation LearningGraph Neural NetworkContrastive LearningImage

🎯 What it does: A weakly supervised contrastive learning framework is proposed, which constructs continuous positive and negative samples through semantic similarity, effectively utilizing imprecise labels.

Weight matrices compression based on PDB model in deep neural networks

Xiaoling Wu (Southern University of Science and Technology), Zeng Li (Southern University of Science and Technology)

CodeCompressionImageText

🎯 What it does: This paper proposes the Population Double Bulk (PDB) model and the corresponding weight matrix compression algorithm, which can automatically determine the boundary between noise and information and compress the network without introducing hyperparameters.

Weisfeiler and Leman Go Gambling: Why Expressive Lottery Tickets Win

Lorenz Kummer (University of Vienna), Nils Morten Kriege

CodeDrug DiscoveryProtein Structure PredictionGraph Neural NetworkGraph

🎯 What it does: This paper studies the Lottery Ticket Hypothesis (LTH) in sparse initialized Graph Neural Networks (GNNs), proving that it is still possible to find trainable sparse sub-networks while maintaining sufficient expressive power (i.e., comparable to 1-WL);

What Makes In-context Learning Effective for Mathematical Reasoning

Jiayu Liu (University of Science and Technology of China), Enhong Chen (University of Science and Technology of China)

CodeTransformerLarge Language ModelText

🎯 What it does: This paper quantifies the impact of examples on the mathematical reasoning performance of large language models in context learning through theoretical analysis and proposes an example selection method called LMS3 based on semantic similarity and reasoning stability.

When can in-context learning generalize out of task distribution?

Chase Goddard (Princeton University), David J. Schwab (Graduate Center CUNY)

CodeTransformerLarge Language ModelTabular

🎯 What it does: This paper studies whether the Transformer can generalize to out-of-distribution tasks when the diversity of pre-training task distributions changes. By sampling linear regression tasks on high-dimensional spherical sections at different angles ϕ and training a GPT-2 style Transformer for in-context learning (ICL), a transition from 'specialized' solutions to 'general' solutions was observed; this transition was further validated in classification and nonlinear regression tasks.

When Maximum Entropy Misleads Policy Optimization

Ruipeng Zhang (University of California San Diego), Sicun Gao (University of California San Diego)

CodeAutonomous DrivingOptimizationRobotic IntelligenceReinforcement LearningSequential

🎯 What it does: This paper studies the reasons why Maximum Entropy Reinforcement Learning (MaxEnt RL) may lead to misleading policy optimization in complex control tasks, and proposes the 'Entropy Bifurcation Extension' method to demonstrate the existence of this misleading effect. It further experimentally verifies the reasons for the poor performance of Soft Actor-Critic (SAC) in real control environments (such as high-speed vehicles, quadcopters, and quadruped robots) and explores the mitigating effects of adaptive entropy regulation.

When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

Min-Yeong Park (Kyung Hee University), Gyeong-Moon Park (Korea University)

CodeAnomaly DetectionTransformerTime Series

🎯 What it does: A time series anomaly prediction framework A2P is proposed, which can locate anomaly points in future signals.

Where is the Truth? The Risk of Getting Confounded in a Continual World

Florian Peter Busch (TU Darmstadt), Martin Mundt (University of Bremen)

CodeClassificationRecognitionConvolutional Neural NetworkImage

🎯 What it does: The study investigates the impact of confounding factors on model performance in continuous learning scenarios, proposing the ConCon dataset and evaluating various CL methods.

Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Shaokun Zhang (Pennsylvania State University), Qingyun Wu (AG2AI, Inc.)

CodeTransformerLarge Language ModelPrompt EngineeringText

🎯 What it does: Research on automation failure attribution, identifying agents and steps that lead to task failures in multi-agent systems.

WikiBigEdit: Understanding the Limits of Lifelong Knowledge Editing in LLMs

Lukas Thede (University of Tübingen), Thomas Hartvigsen (University of Virginia)

CodeTransformerTextBenchmarkRetrieval-Augmented Generation

🎯 What it does: Proposes the WikiBigEdit benchmark, providing over 500,000 real-time knowledge editing question-answer data based on Wikidata, supporting large-scale lifelong knowledge editing research.

Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale

Rogerio Bonatti (Microsoft), Zheng Hui

CodeTransformerLarge Language ModelAgentic AITextMultimodalityBenchmarkChain-of-Thought

🎯 What it does: Introducing Windows Agent Arena, a scalable multimodal agent benchmark built on a real Windows 11 environment, containing 154 tasks across 11 categories including office, browsing, system, programming, and media.

Winner-takes-all for Multivariate Probabilistic Time Series Forecasting

Adrien Cortes (Institut Polytechnique de Paris), Victor Letzelter (Valeo)

CodeRecurrent Neural NetworkTime SeriesFinance Related

🎯 What it does: The TimeMCL method is proposed, which utilizes multi-head neural networks and Winner-Takes-All (WTA) loss to generate multiple feasible future prediction paths with a single forward pass.

Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning

Sunwoo Lee (Ulsan National Institute of Science and Technology), Seungyul Han (Ulsan National Institute of Science and Technology)

CodeAdversarial AttackTransformerReinforcement LearningTabular

🎯 What it does: This paper proposes the Wolfpack adversarial attack strategy and its corresponding WALL robust training framework to enhance the reliability of multi-agent reinforcement learning in the face of coordinated attacks.

WOMD-Reasoning: A Large-Scale Dataset for Interaction Reasoning in Driving

Yiheng Li (University of California Berkeley), Wei Zhan

CodeAutonomous DrivingTransformerLarge Language ModelSupervised Fine-TuningVision Language ModelVideoTextMultimodalityChain-of-Thought

🎯 What it does: A large-scale interactive reasoning dataset, WOMD-Reasoning, has been constructed, and Motion-LLaVA has been fine-tuned based on it to enhance the understanding and prediction of traffic rules and human intention-driven interactions.

WyckoffDiff -- A Generative Diffusion Model for Crystal Symmetry

Filip Ekström Kelvinius (Linköping University), Fredrik Lindsten (Linköping University)

CodeGenerationData SynthesisGraph Neural NetworkDiffusion modelGraph

🎯 What it does: This paper proposes a discrete diffusion model based on Wyckoff positions, called WyckoffDiff, which can generate prototype structures that satisfy crystal symmetry constraints.

X-Hacking: The Threat of Misguided AutoML

Rahul Sharma (Deutsches Forschungszentrum für Künstliche Intelligenz GmbH), David Antony Selby (Deutsches Forschungszentrum für Künstliche Intelligenz GmbH)

CodeOptimizationExplainability and InterpretabilityAuto EncoderTabular

🎯 What it does: This study proposes the concept of 'X-hacking' and explores how to use AutoML to find models that maintain predictive performance while providing pre-defined explanations (such as SHAP values) within model diversity (Rashomon phenomenon), which can intentionally or unintentionally mislead model interpretations.

XAttention: Block Sparse Attention with Antidiagonal Scoring

Ruyi Xu (Tsinghua University), Song Han (Massachusetts Institute of Technology)

CodeTransformerVideoTextBenchmark

🎯 What it does: A pluggable block sparse attention framework called XAttention is proposed to accelerate long-context Transformer inference.

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

Maximilian Beck (NXAI GmbH), Sepp Hochreiter (Johannes Kepler University)

CodeRecurrent Neural NetworkLarge Language ModelText

🎯 What it does: Developed and trained a 7B parameter xLSTM language model, focusing on efficient inference.

You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption

Weihang Ran (University of Tokyo), Yinqiang Zheng (University of Tokyo)

CodeRecognitionData SynthesisOptimizationConvolutional Neural NetworkNeural Radiance FieldImage

🎯 What it does: Using multi-view 3D reconstruction to obtain voxel representation, robust texture optimization is applied to the color channel, significantly improving model recognition accuracy under various image degradation conditions.