ICML

MARGE: Improving Math Reasoning for LLMs with Guided Exploration

Jingyue Gao, Runji Lin, Keming Lu, Bowen Yu, Junyang Lin, Jianyu Chen

机构 * Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China（清华大学交叉信息学院） ； Alibaba Group（阿里巴巴集团） ； Shanghai Qi Zhi Institute, Shanghai, China（上海启智研究院） 纠错

Comments To appear at ICML 2025

Efficient Optimization with Orthogonality Constraint: a Randomized Riemannian Submanifold Method

Andi Han, Pierre-Louis Poirion, Akiko Takeda

Comments Accepted to ICML 2025

Importance Sampling for Nonlinear Models

Prakash Palanivelu Rajmohan, Fred Roosta

Comments This work is accepted at ICML 2025

Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets

Ning Lu, Shengcai Liu, Jiahao Wu, Weiyu Chen, Zhirui Zhang, Yew-Soon Ong, Qi Wang, Ke Tang

机构 * Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of CSE, SUSTech（脑启发智能计算广东省重点实验室，计算机科学与工程系，华南理工大学） ； Department of CSE, HKUST（计算机科学与工程系，香港科技大学） ； Department of CSE, PolyU（计算机科学与工程系，PolyU） ； Department of CSE, SUSTech（计算机科学与工程系，华南理工大学） ； Huawei Technologies CO.（华为技术有限公司） ； College of Computing（计算学院） 纠错

Comments ICML 2025 Camera Ready

GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder

Shiming Chen, Dingjie Fu, Salman Khan, Fahad Shahbaz Khan

Comments Accepted to ICML'25

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

Rui Zhang, Yun Shen, Hongwei Li, Wenbo Jiang, Hanxiao Chen, Yuan Zhang, Guowen Xu, Yang Zhang

机构 * University of Electronic Science and Technology of China（电子科技大学） ； Flexera（Flexera公司） ； CISPA Helmholtz Center for Information Security（CISPA海德堡信息安全中心） 纠错

Comments Accepted by ICML 2025

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

Run He, Di Fang, Yicheng Xu, Yawen Cui, Ming Li, Cen Chen, Ziqian Zeng, Huiping Zhuang

Comments Accepted by ICML 2025; Camera ready version

Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective

Jiawei Huang, Bingcong Li, Christoph Dann, Niao He

Comments 36 Pages; ICML 2025

IntLoRA: Integral Low-rank Adaptation of Quantized Diffusion Models

Hang Guo, Yawei Li, Tao Dai, Shu-Tao Xia, Luca Benini

Comments ICML 2025

TCP-Diffusion: A Multi-modal Diffusion Model for Global Tropical Cyclone Precipitation Forecasting with Change Awareness

Cheng Huang, Pan Mu, Cong Bai, Peter AG Watson

Comments Camera-ready version. This paper has been accepted to ICML 2025

Benign Overfitting in Token Selection of Attention Mechanism

Keitaro Sakamoto, Issei Sato

机构 * Department of Computer Science, The University of Tokyo, Tokyo, Japan（东京大学计算机科学系） 纠错

Comments Accepted at ICML 2025. Code is available at https://github.com/keitaroskmt/benign-attention

Asymptotically-Optimal Gaussian Bandits with Side Observations

Alexia Atsidakou, Orestis Papadigenopoulos, Constantine Caramanis, Sujay Sanghavi, Sanjay Shakkottai

机构 * Department of Electrical and Computer Engineering University of Texas at Austin（电气与计算机工程系得克萨斯大学奥斯汀分校） 纠错

Comments International Conference on Machine Learning, ICML '22

From Pixels to Perception: Interpretable Predictions via Instance-wise Grouped Feature Selection

Moritz Vandenhirtz, Julia E. Vogt

Comments International Conference on Machine Learning

Autoencoder-Based Hybrid Replay for Class-Incremental Learning

Milad Khademi Nori, Il-Min Kim, Guanghui Wang

Comments Accepted ICML 2025

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

Shihao Zou, Qingfeng Li, Wei Ji, Jingjing Li, Yongkui Yang, Guoqi Li, Chao Dong

Comments Accepted by ICML 2025

Near Optimal Best Arm Identification for Clustered Bandits

Yash, Nikhil Karamchandani, Avishek Ghosh

Comments To be published in ICML 2025

TransPL: VQ-Code Transition Matrices for Pseudo-Labeling of Time Series Unsupervised Domain Adaptation

Jaeho Kim, Seulki Lee

Comments ICML 2025 Accept

Online Isolation Forest

Filippo Leveni, Guilherme Weigert Cassales, Bernhard Pfahringer, Albert Bifet, Giacomo Boracchi

Comments Accepted at International Conference on Machine Learning (ICML 2024)

Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy

Haoqi Wu, Wei Dai, Li Wang, Qiang Yan

Comments to be published in ICML 2025

Lightspeed Geometric Dataset Distance via Sliced Optimal Transport

Khai Nguyen, Hai Nguyen, Tuan Pham, Nhat Ho

Comments Accepted to ICML 2025, 16 pages, 13 figures

Commute Graph Neural Networks

Wei Zhuo, Han Yu, Guang Tan, Xiaoxiao Li

Comments Published in International Conference on Machine Learning (ICML), 2025

Learning Progress Driven Multi-Agent Curriculum

Wenshuai Zhao, Zhiyuan Li, Joni Pajarinen

Comments ICML 2025

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments

Yun Qu, Qi Cheems Wang, Yixiu Mao, Yiqin Lv, Xiangyang Ji

机构 * Yun Qu（未知） ； Qi (Cheems) Wang（未知） ； Yixiu Mao（未知） ； Yiqin Lv（未知） ； Xiangyang Ji（未知） 纠错

Comments ICML 2025

Position: Contextual Integrity is Inadequately Applied to Language Models

Yan Shvartzshnaider, Vasisht Duddu

Comments International Conference on Machine Learning (ICML), 2025

Doubly protected estimation for survival outcomes utilizing external controls for randomized clinical trials

Chenyin Gao, Shu Yang, Mingyang Shan, Wenyu Wendy Ye, Ilya Lipkovich, Douglas Faries

Comments accepted at ICML 2025

Fully Dynamic Euclidean Bi-Chromatic Matching in Sublinear Update Time

Gramoz Goranci, Peter Kiss, Neel Patel, Martin P. Seybold, Eva Szilagyi, Da Wei Zheng

Comments accepted at ICML 2025

GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration

Yuhang Li, Ruokai Yin, Donghyun Lee, Shiting Xiao, Priyadarshini Panda

机构 * Department of Electrical Engineering, Yale University（耶鲁大学电气工程系） 纠错

Comments ICML 2025

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

Chengqian Gao, Haonan Li, Liu Liu, Zeke Xie, Peilin Zhao, Zhiqiang Xu

Comments Accepted at ICML 2025

A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition

Nian Liu, Xiaoxin He, Thomas Laurent, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson

Comments This paper is accepted by ICML 2025

Preference Optimization for Combinatorial Optimization Problems

Mingjun Pan, Guanquan Lin, You-Wei Luo, Bin Zhu, Zhien Dai, Lijun Sun, Chun Yuan

Comments This paper has been accepted by ICML 2025