ICML 2025 Papers

3,340 papers found • Page 1 of 67

$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation

Saúl Santos, António Farinhas, Daniel McNamee et al.

ICML 2025poster

$K^2$VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecasting

Xingjian Wu, Xiangfei Qiu, Hongfan Gao et al.

ICML 2025spotlight

$\mathcal{V}ista\mathcal{DPO}$: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

Haojian Huang, Haodong Chen, Shengqiong Wu et al.

ICML 2025oral

$S^2$FGL: Spatial Spectral Federated Graph Learning

Zihan Tan, Suyuan Huang, Guancheng Wan et al.

ICML 2025poster
1
citations

$\texttt{I$^2$MoE}$: Interpretable Multimodal Interaction-aware Mixture-of-Experts

Jiayi Xin, Sukwon Yun, Jie Peng et al.

ICML 2025poster

3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric Priors

Yujun Huang, Bin Chen, Niu Lian et al.

ICML 2025poster

3D Question Answering via only 2D Vision-Language Models

FENGYUN WANG, Sicheng Yu, Jiawei Wu et al.

ICML 2025poster

AAAR-1.0: Assessing AI’s Potential to Assist Research

Renze Lou, Hanzi Xu, Sijia Wang et al.

ICML 2025poster

A Bayesian Model Selection Criterion for Selecting Pretraining Checkpoints

Michael Munn, Susan Wei

ICML 2025poster

Ab Initio Nonparametric Variable Selection for Scalable Symbolic Regression with Large $p$

Shengbin Ye, Meng Li

ICML 2025poster
1
citations

ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via $\alpha$-$\beta$-Divergence

Guanghui Wang, Zhiyong Yang, Zitai Wang et al.

ICML 2025oral

ABNet: Adaptive explicit-Barrier Net for Safe and Scalable Robot Learning

Wei Xiao, Johnson Tsun-Hsuan Wang, Chuang Gan et al.

ICML 2025poster

A Bregman Proximal Viewpoint on Neural Operators

Abdel-Rahim Mezidi, Jordan Patracone, Saverio Salzo et al.

ICML 2025poster

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

Raanan Yehezkel Rohekar, Yaniv Gurwicz, Sungduk Yu et al.

ICML 2025poster

Accelerated Diffusion Models via Speculative Sampling

Valentin De Bortoli, Alexandre Galashov, Arthur Gretton et al.

ICML 2025poster

Accelerating Large Language Model Reasoning via Speculative Search

Zhihai Wang, Jie Wang, Jilai Pan et al.

ICML 2025poster
12
citations

Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity

Alessandro Pierro, Steven Abreu, Jonathan Timcheck et al.

ICML 2025poster

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies

Nadav Timor, Jonathan Mamou, Daniel Korat et al.

ICML 2025oral
9
citations

Accelerating PDE-Constrained Optimization by the Derivative of Neural Operators

Ze Cheng, Zhuoyu Li, Wang Xiaoqiang et al.

ICML 2025poster

Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach

Yang Xu, Vaneet Aggarwal

ICML 2025poster

Accelerating Spectral Clustering under Fairness Constraints

Francesco Tonin, Alex Lambert, Johan Suykens et al.

ICML 2025poster

Accelerating Unbiased LLM Evaluation via Synthetic Feedback

Zhaoyi Zhou, Yuda Song, Andrea Zanette

ICML 2025poster
3
citations

Accurate and Efficient World Modeling with Masked Latent Transformers

Maxime Burchi, Radu Timofte

ICML 2025poster

Accurate Identification of Communication Between Multiple Interacting Neural Populations

Belle Liu, Jacob I Sacks, Matthew Golub

ICML 2025poster

A Certified Unlearning Approach without Access to Source Data

Umit Basaran, Sk Miraj Ahmed, Amit Roy-Chowdhury et al.

ICML 2025poster

A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing

yu chen, Jing Lian, Zhaofei Yu et al.

ICML 2025oral

A Checks-and-Balances Framework for Context-Aware Ethical AI Alignment

Edward Chang

ICML 2025oral
3
citations

Achieving Linear Speedup and Near-Optimal Complexity for Decentralized Optimization over Row-stochastic Networks

Liyuan Liang, Xinyi Chen, Gan Luo et al.

ICML 2025spotlight

A Classification View on Meta Learning Bandits

Mirco Mutti, Jeongyeol Kwon, Shie Mannor et al.

ICML 2025poster

A Closer Look at Backdoor Attacks on CLIP

Shuo He, Zhifang Zhang, Feng Liu et al.

ICML 2025poster

A Closer Look at Generalized BH Algorithm for Out-of-Distribution Detection

Xinsong Ma, Jie Wu, Weiwei Liu

ICML 2025poster

A Closer Look at Multimodal Representation Collapse

Abhra Chaudhuri, Anjan Dutta, Tu Bui et al.

ICML 2025spotlight
8
citations

A Closer Look at Transformers for Time Series Forecasting: Understanding Why They Work and Where They Struggle

Yu Chen, Nathalia Céspedes, Payam Barnaghi

ICML 2025poster

A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks

Varshita Kolipaka, Akshit Sinha, Debangan Mishra et al.

ICML 2025poster

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD

Ruinan Jin, Xiao Li, Yaoliang Yu et al.

ICML 2025poster

A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs

Kihyuk Hong, Ambuj Tewari

ICML 2025poster

A Cross Modal Knowledge Distillation & Data Augmentation Recipe for Improving Transcriptomics Representations through Morphological Features

Ihab Bendidi, Yassir El Mesbahi, Alisandra Denton et al.

ICML 2025poster

Action-Constrained Imitation Learning

Chia-Han Yeh, Tse-Sheng Nan, Risto Vuorio et al.

ICML 2025poster

Action-Dependent Optimality-Preserving Reward Shaping

Grant Forbes, Jianxun Wang, Leonardo Villalobos-Arias et al.

ICML 2025poster
1
citations

Action Dubber: Timing Audible Actions via Inflectional Flow

Wenlong Wan, Weiying Zheng, Tianyi Xiang et al.

ICML 2025oral

Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional

Sanjeev Raja, Martin Šípka, Michael Psenka et al.

ICML 2025oral

ActionPiece: Contextually Tokenizing Action Sequences for Generative Recommendation

Yupeng Hou, Jianmo Ni, Zhankui He et al.

ICML 2025spotlight
14
citations

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

Sangyeon Park, Isaac Han, Seungwon Oh et al.

ICML 2025poster
5
citations

Activation Space Interventions Can Be Transferred Between Large Language Models

Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash et al.

ICML 2025poster
6
citations

Active Evaluation Acquisition for Efficient LLM Benchmarking

Yang Li, Jie Ma, Miguel Ballesteros et al.

ICML 2025poster
12
citations

Active feature acquisition via explainability-driven ranking

Osman Berke Guney, Ketan Saichandran, Karim Elzokm et al.

ICML 2025poster

Active Fine-Tuning of Multi-Task Policies

Marco Bagatella, Jonas Hübotter, Georg Martius et al.

ICML 2025oral
6
citations

Active Learning for Efficient Discovery of Optimal Combinatorial Perturbations

Jason Qin, Hans-Hermann Wessels, Carlos Fernandez-Granda et al.

ICML 2025poster

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes

Erica Zhang, Fangzhao Zhang, Mert Pilanci

ICML 2025poster
1
citations

Active Learning with Selective Time-Step Acquisition for PDEs

Yegon Kim, Hyunsu Kim, Gyeonghoon Ko et al.

ICML 2025poster
← PreviousNext →