ICML Spotlight Papers

406 papers found • Page 3 of 9

Learning with Exact Invariances in Polynomial Time

Ashkan Soleymani, Behrooz Tahmasebi, Stefanie Jegelka et al.

ICML 2025spotlightarXiv:2502.19758

Leveraging Diffusion Model as Pseudo-Anomalous Graph Generator for Graph-Level Anomaly Detection

Jinyu Cai, Yunhe Zhang, Fusheng Liu et al.

ICML 2025spotlight

Lightweight Protocols for Distributed Private Quantile Estimation

Anders Aamand, Fabrizio Boninsegna, Abigail Gentle et al.

ICML 2025spotlightarXiv:2502.02990

Linearization Turns Neural Operators into Function-Valued Gaussian Processes

Emilia Magnani, Marvin Pförtner, Tobias Weber et al.

ICML 2025spotlightarXiv:2406.05072

LipsNet++: Unifying Filter and Controller into a Policy Network

Xujie Song, Liangfa Chen, Tong Liu et al.

ICML 2025spotlight
3
citations

Local Identifying Causal Relations in the Presence of Latent Variables

Zheng Li, Zeyu Liu, Feng Xie et al.

ICML 2025spotlight

LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Paul McVay, Sergio Arnaud, Ada Martin et al.

ICML 2025spotlightarXiv:2504.14151

Log-Sum-Exponential Estimator for Off-Policy Evaluation and Learning

Armin Behnamnia, Gholamali Aminian, Alireza Aghaei et al.

ICML 2025spotlightarXiv:2506.06873
4
citations

LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression

Haotian Wu, Gongpu Chen, Pier Luigi Dragotti et al.

ICML 2025spotlightarXiv:2507.01204
6
citations

MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

Mahir Labib Dihan, Tanvir Hassan, Md Tanvir Parvez et al.

ICML 2025spotlightarXiv:2501.00316

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

Hao Chen, Yujin Han, Fangyi Chen et al.

ICML 2025spotlightarXiv:2502.03444

Mastering Board Games by External and Internal Planning with Language Models

John Schultz, Jakub Adamek, Matej Jusup et al.

ICML 2025spotlightarXiv:2412.12119
21
citations

MCU: An Evaluation Framework for Open-Ended Game Agents

Xinyue Zheng, Haowei Lin, Kaichen He et al.

ICML 2025spotlightarXiv:2310.08367

Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization

Phillip Guo, Aaquib Syed, Abhay Sheshadri et al.

ICML 2025spotlightarXiv:2410.12949

Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

Linxi Zhao, Yihe Deng, Weitong Zhang et al.

ICML 2025spotlightarXiv:2402.08680

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Zhicheng Zhang, Wuyou Xia, Chenxi Zhao et al.

ICML 2025spotlightarXiv:2507.04635
4
citations

Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws

Xiyuan Wei, Ming Lin, Fanjiang Ye et al.

ICML 2025spotlightarXiv:2505.06699

Monte Carlo Tree Diffusion for System 2 Planning

Jaesik Yoon, Hyeonseo Cho, Doojin Baek et al.

ICML 2025spotlightarXiv:2502.07202
17
citations

Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport

Tuan Dam, Pascal Stenger, Lukas Schneider et al.

ICML 2025spotlightarXiv:2309.10737
2
citations

Multi-Turn Code Generation Through Single-Step Rewards

Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen et al.

ICML 2025spotlightarXiv:2502.20380

Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime

Diyuan Wu, Marco Mondelli

ICML 2025spotlightarXiv:2501.19104

New Bounds for Sparse Variational Gaussian Processes

Michalis Titsias

ICML 2025spotlightarXiv:2502.08730

Nonparametric Teaching for Graph Property Learners

Chen Zhang, Weixin Bu, Zeyi Ren et al.

ICML 2025spotlightarXiv:2505.14170
2
citations

Non-stationary Diffusion For Probabilistic Time Series Forecasting

Weiwei Ye, Zhuopeng Xu, Ning Gui

ICML 2025spotlightarXiv:2505.04278

No Soundness in the Real World: On the Challenges of the Verification of Deployed Neural Networks

Attila Szász, Balázs Bánhelyi, Mark Jelasity

ICML 2025spotlightarXiv:2506.01054

Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks

Lukas Braun, Erin Grant, Andrew Saxe

ICML 2025spotlight
8
citations

Not All Wrong is Bad: Using Adversarial Examples for Unlearning

Ali Ebrahimpour-Boroojeny, Hari Sundaram, Varun Chandrasekaran

ICML 2025spotlight

Novelty Detection in Reinforcement Learning with World Models

Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch et al.

ICML 2025spotlightarXiv:2310.08731

On Learning Parallel Pancakes with Mostly Uniform Weights

Ilias Diakonikolas, Daniel Kane, Sushrut Karmalkar et al.

ICML 2025spotlightarXiv:2504.15251

On the Benefits of Active Data Collection in Operator Learning

Unique Subedi, Ambuj Tewari

ICML 2025spotlightarXiv:2410.19725

On the Guidance of Flow Matching

Ruiqi Feng, Chenglei Yu, Wenhao Deng et al.

ICML 2025spotlightarXiv:2502.02150
17
citations

On the Power of Context-Enhanced Learning in LLMs

Xingyu Zhu, Abhishek Panigrahi, Sanjeev Arora

ICML 2025spotlightarXiv:2503.01821

On the Tension between Byzantine Robustness and No-Attack Accuracy in Distributed Learning

Yi-Rui Yang, Chang-Wei Shi, Wu-Jun Li

ICML 2025spotlight

Optimizing Adaptive Attacks against Watermarks for Language Models

Abdulrahman Diaa, Toluwani Aremu, Nils Lukas

ICML 2025spotlightarXiv:2410.02440

Overcoming Multi-step Complexity in Multimodal Theory-of-Mind Reasoning: A Scalable Bayesian Planner

Chunhui Zhang, Zhongyu Ouyang, Kwonjoon Lee et al.

ICML 2025spotlightarXiv:2506.01301
3
citations

P(all-atom) Is Unlocking New Path For Protein Design

Wei Qu, Jiawei Guan, Rui Ma et al.

ICML 2025spotlight
20
citations

PANDAS: Improving Many-shot Jailbreaking via Positive Affirmation, Negative Demonstration, and Adaptive Sampling

Avery Ma, Yangchen Pan, Amir-massoud Farahmand

ICML 2025spotlightarXiv:2502.01925
4
citations

Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models

Huanjian Zhou, Masashi Sugiyama

ICML 2025spotlightarXiv:2412.07435

PASS: Private Attributes Protection with Stochastic Data Substitution

Yizhuo Chen, Chun-Fu (Richard) Chen, Hsiang Hsu et al.

ICML 2025spotlightarXiv:2506.07308

PCEvolve: Private Contrastive Evolution for Synthetic Dataset Generation via Few-Shot Private Data and Generative APIs

Jianqing Zhang, Yang Liu, Jie Fu et al.

ICML 2025spotlightarXiv:2506.05407

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

Jeonghye Kim, Yongjae Shin, Whiyoung Jung et al.

ICML 2025spotlightarXiv:2507.08761

Peri-LN: Revisiting Normalization Layer in the Transformer Architecture

Jeonghoon Kim, Byeongchan Lee, Cheonbok Park et al.

ICML 2025spotlightarXiv:2502.02732

PhySpec: Physically Consistent Spectral Reconstruction via Orthogonal Subspace Decomposition and Self-Supervised Meta-Auxiliary Learning

Xingxing Yang, Jie Chen, Zaifeng Yang

ICML 2025spotlight

PokéChamp: an Expert-level Minimax Language Agent

Seth Karten, Andy Nguyen, Chi Jin

ICML 2025spotlightarXiv:2503.04094

Policy-labeled Preference Learning: Is Preference Enough for RLHF?

Taehyun Cho, Seokhun Ju, Seungyub Han et al.

ICML 2025spotlightarXiv:2505.06273

Policy Regularization on Globally Accessible States in Cross-Dynamics Reinforcement Learning

Zhenghai Xue, Lang Feng, Jiacheng Xu et al.

ICML 2025spotlightarXiv:2503.06893

Position: Algebra Unveils Deep Learning - An Invitation to Neuroalgebraic Geometry

Giovanni Luca Marchetti, Vahid Shahverdi, Stefano Mereta et al.

ICML 2025spotlight

Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption

Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite et al.

ICML 2025spotlightarXiv:2508.08883

Position: Deep Learning is Not So Mysterious or Different

Andrew Wilson

ICML 2025spotlight

Position: Don't Use the CLT in LLM Evals With Fewer Than a Few Hundred Datapoints

Sam Bowyer, Laurence Aitchison, Desi Ivanova

ICML 2025spotlightarXiv:2503.01747
14
citations