ICLR

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competition

Priya Kasimbeg, Frank Schneider, Runa Eschenhagen, Juhan Bae, Chandramouli Shama Sastry, Mark Saroufim, Boyuan Feng, Less Wright, Edward Z. Yang, Zachary Nado, Sourabh Medapati, Philipp Hennig, Michael Rabbat, George E. Dahl

Comments ICLR 2025; 23 pages, 5 figures, 8 tables

High-Dynamic Radar Sequence Prediction for Weather Nowcasting Using Spatiotemporal Coherent Gaussian Representation

Ziye Wang, Yiran Qin, Lin Zeng, Ruimao Zhang

Comments Accepted as an Oral paper at ICLR 2025. Project page: https://ziyeeee.github.io/stcgs.github.io

VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation

Wei Zhao, Pengxiang Ding, Min Zhang, Zhefei Gong, Shuanghao Bai, Han Zhao, Donglin Wang

Comments Accepted as a conference paper at ICLR 2025

Do Large Language Models Truly Understand Geometric Structures?

Xiaofeng Wang, Yiming Wang, Wenhong Zhu, Rui Wang

Comments Accepted to ICLR 2025

Ask, and it shall be given: On the Turing completeness of prompting

Ruizhong Qiu, Zhe Xu, Wenxuan Bao, Hanghang Tong

Comments ICLR 2025

KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

Jaron Maene, Vincent Derkinderen, Pedro Zuidberg Dos Martires

Comments Accepted to ICLR 2025

MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection

Xi Jiang, Jian Li, Hanqiu Deng, Yong Liu, Bin-Bin Gao, Yifeng Zhou, Jialin Li, Chengjie Wang, Feng Zheng

Comments Accepted by ICLR 2025. The code and data are available at https://github.com/jam-cc/MMAD

Vision-LSTM: xLSTM as Generic Vision Backbone

Benedikt Alkin, Maximilian Beck, Korbinian Pöppel, Sepp Hochreiter, Johannes Brandstetter

Comments Published as a conference paper at ICLR 2025, Github: https://github.com/NX-AI/vision-lstm

Chain-of-Action: Faithful and Multimodal Question Answering through Large Language Models

Zhenyu Pan, Haozheng Luo, Manling Li, Han Liu

Comments International Conference on Learning Representations (ICLR) 2025

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations

Benedikt Alkin, Lukas Miklautz, Sepp Hochreiter, Johannes Brandstetter

Comments Published as a conference paper at ICLR 2025. Github: https://github.com/ml-jku/MIM-Refiner

Towards Robust Probabilistic Modeling on SO(3) via Rotation Laplace Distribution

Yingda Yin, Jiangran Lyu, Yang Wang, Haoran Liu, He Wang, Baoquan Chen

Comments TPAMI 2025. ICLR 2023 spotlight. arXiv admin note: substantial text overlap with arXiv:2303.01743

Fast and Accurate Blind Flexible Docking

Zizhuo Zhang, Lijun Wu, Kaiyuan Gao, Jiangchao Yao, Tao Qin, Bo Han

Comments 25 pages, Accepted by ICLR 2025

Narrowing Information Bottleneck Theory for Multimodal Image-Text Representations Interpretability

Zhiyu Zhu, Zhibo Jin, Jiayu Zhang, Nan Yang, Jiahao Huang, Jianlong Zhou, Fang Chen

Comments Accepted by ICLR 2025

Dynamic Low-Rank Sparse Adaptation for Large Language Models

Weizhong Huang, Yuxin Zhang, Xiawu Zheng, Yang Liu, Jing Lin, Yiwu Yao, Rongrong Ji

Comments Accepted to ICLR 2025

PEARL: Towards Permutation-Resilient LLMs

Liang Chen, Li Shen, Yang Deng, Xiaoyan Zhao, Bin Liang, Kam-Fai Wong

Comments ICLR 2025

Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining

Wonhyeok Choi, Kyumin Hwang, Wei Peng, Minwoo Choi, Sunghoon Im

Comments Accepted at ICLR 2025

Factor Graph-based Interpretable Neural Networks

Yicong Li, Kuanjiu Zhou, Shuo Yu, Qiang Zhang, Renqiang Luo, Xiaodong Li, Feng Xia

Comments The Thirteenth International Conference on Learning Representations

Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective

Ruichen Shao, Bei Li, Gangao Liu, Yang Chen, Xiang Zhou, Jingang Wang, Xunliang Cai, Peng Li

Comments Accepted by ICLR 2025

Rethinking Spiking Neural Networks from an Ensemble Learning Perspective

Yongqi Ding, Lin Zuo, Mengmeng Jing, Pei He, Hanpu Deng

Comments Published as a conference paper at ICLR 2025

Accurate Forgetting for Heterogeneous Federated Continual Learning

Abudukelimu Wuerkaixi, Sen Cui, Jingfeng Zhang, Kunda Yan, Bo Han, Gang Niu, Lei Fang, Changshui Zhang, Masashi Sugiyama

Comments published in ICLR 2024

On-the-fly Preference Alignment via Principle-Guided Decoding

Mingye Zhu, Yi Liu, Lei Zhang, Junbo Guo, Zhendong Mao

Comments Accepted to ICLR 2025

Efficient Inverse Multiagent Learning

Denizalp Goktas, Amy Greenwald, Sadie Zhao, Alec Koppel, Sumitra Ganesh

Comments Paper was submitted to the International Conference on Learning Representations (2024) under the title of "Generative Adversarial Inverse Multiagent Learning", and renamed for the camera-ready submission as "Efficient Inverse Multiagent Learning"

Learning from End User Data with Shuffled Differential Privacy over Kernel Densities

Tal Wagner

Comments ICLR 2025

SimPER: A Minimalist Approach to Preference Alignment without Hyperparameters

Teng Xiao, Yige Yuan, Zhengyu Chen, Mingxiao Li, Shangsong Liang, Zhaochun Ren, Vasant G Honavar

Comments ICLR 2025

Certified Robustness Under Bounded Levenshtein Distance

Elias Abad Rocamora, Grigorios G. Chrysos, Volkan Cevher

Comments Accepted in ICLR 2025

Towards counterfactual fairness through auxiliary variables

Bowei Tian, Ziyao Wang, Shwai He, Wanghao Ye, Guoheng Sun, Yucong Dai, Yongkai Wu, Ang Li

Comments arXiv admin note: text overlap with arXiv:2307.08232 by other authors

Journal ref The International Conference on Learning Representations (ICLR 2025)

ParetoFlow: Guided Flows in Multi-Objective Optimization

Ye Yuan, Can Chen, Christopher Pal, Xue Liu

Comments Accepted by ICLR 2025

Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training

Zhanpeng Zhou, Mingze Wang, Yuchen Mao, Bingrui Li, Junchi Yan

Comments 32 pages, 16 figures, ICLR 2025 Spotlight

Revisiting In-context Learning Inference Circuit in Large Language Models

Hakaze Cho, Mariko Kato, Yoshihiro Sakai, Naoya Inoue

Comments 37 pages, 41 figures, 8 tables. ICLR 2025 Accepted. Camera-ready Version

PFDiff: Training-Free Acceleration of Diffusion Models Combining Past and Future Scores

Guangyi Wang, Yuren Cai, Lijiang Li, Wei Peng, Songzhi Su

Comments Accepted at ICLR 2025