ICLR

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, Song Han

机构 * MIT（麻省理工学院） ； NVIDIA（NVIDIA公司） ； CMU（卡内基梅隆大学） ； Princeton（普林斯顿大学） ； UC Berkeley（加州大学伯克利分校） ； SJTU（上海交通大学） ； Pika Labs（Pika实验室） 纠错

Comments ICLR 2025 Spotlight Quantization Library: https://github.com/mit-han-lab/deepcompressor Inference Engine: https://github.com/mit-han-lab/nunchaku Website: https://hanlab.mit.edu/projects/svdquant Demo: https://demo.nunchaku.tech/ Blog: https://hanlab.mit.edu/blog/svdquant

Multi-Scale Fusion for Object Representation

Rongzhen Zhao, Vivienne Wang, Juho Kannala, Joni Pajarinen

机构 * Department of Electrical Engineering and Automation, Aalto University, Finland（艾尔沃斯大学电子工程与自动化系） ； Department of Computer Science, Aalto University, Finland（艾尔沃斯大学计算机科学系） ； Center for Machine Vision and Signal Analysis, University of Oulu, Finland（奥卢大学机器视觉与信号分析中心） 纠错

Comments Accepted to ICLR 2025

Linear combinations of latents in generative models: subspaces and beyond

Erik Bodin, Alexandru Stere, Dragos D. Margineantu, Carl Henrik Ek, Henry Moss

Comments Published at International Conference on Learning Representations (ICLR) 2025

Conformal Prediction Adaptive to Unknown Subpopulation Shifts

Nien-Shao Wang, Duygu Nur Yaldiz, Yavuz Faruk Bakman, Sai Praneeth Karimireddy

机构 * University of Southern California（南加州大学） 纠错

Comments 21 pages, 7 figures, 5 tables, submitted to ICLR 2026

On Scaling Up 3D Gaussian Splatting Training

Hexu Zhao, Haoyang Weng, Daohan Lu, Ang Li, Jinyang Li, Aurojit Panda, Saining Xie

机构 * New York University（纽约大学） ； Pacific Northwest National Laboratory（太平洋西北国家实验室） 纠错

Comments ICLR 2025 Oral; Homepage: https://daohanlu.github.io/scaling-up-3dgs/

CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding

Jiquan Wang, Sha Zhao, Zhiling Luo, Yangxuan Zhou, Haiteng Jiang, Shijian Li, Tao Li, Gang Pan

机构 * State Key Laboratory of Brain-machine Intelligence（脑机智能国家重点实验室） ； College of Computer Science and Technology（计算机科学与技术学院） ； Alibaba Group（阿里巴巴集团） ； Department of Neurobiology, Affiliated Mental Health Center & Hangzhou Seventh People’s Hospital, Zhejiang University School of Medicine（神经生物学系、附属心理健康中心及杭州第七人民医院，浙江大学医学院） ； MOE Frontier Science Center for Brain Science and Brain-machine Integration（教育部脑科学与脑机集成前沿科学中心） 纠错

Comments Accepted by The Thirteenth International Conference on Learning Representations (ICLR 2025)

Enhancing Efficiency in Multidevice Federated Learning through Data Selection

Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee, Fahim Kawsar, Akhil Mathur

机构 * Imperial College London（帝国理工学院伦敦分校） ； Nokia Bell Labs（诺基亚贝尔实验室） ； University of Glasgow（格拉斯哥大学） 纠错

Comments To be presented in the 10th ACM/IEEE Symposium on Edge Computing (SEC2025) [an early version (v3) has been presented at ICLR 2023 Workshop on Machine Learning for IoT: Datasets, Perception, and Understanding]

Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions

Emi Soroka, Tanmay Chopra, Krish Desai, Sanjay Lall

机构 * Department of Electrical Engineering Stanford University（电气工程系 斯坦福大学） ； Emissary Technologies 纠错

Comments Under review at ICLR 2026

Improving Uncertainty Estimation through Semantically Diverse Language Generation

Lukas Aichberger, Kajetan Schweighofer, Mykyta Ielanskyi, Sepp Hochreiter

机构 * ELLIS Unit Linz and LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz（林茨ELLIS单元和LIT AI实验室，机器学习研究所，林茨约瑟夫·胡纳克大学） ； NXAI GmbH（NXAI公司） 纠错

Comments ICLR 2025

Bayesian Coreset Optimization for Personalized Federated Learning

Prateek Chanda, Shrey Modi, Ganesh Ramakrishnan

机构 * Department of Computer Science（计算机科学系） ； Indian Institute of Technology Bombay（印度理工学院班加罗尔） 纠错

Comments 9 pages, 5 figures, ICLR 2024

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time

Daniel Tan, Anders Woodruff, Niels Warncke, Arun Jose, Maxime Riché, David Demitri Africa, Mia Taylor

机构 * University College London（伦敦大学学院） ； Center on Long-Term Risk（长期风险中心） ； McGill University（麦吉尔大学） ； UK AI Security Institute（英国人工智能安全研究所） 纠错

Comments 40 pages, 22 figures. Under review at ICLR 2026

What's the next frontier for Data-centric AI? Data Savvy Agents

Nabeel Seedat, Jiashuo Liu, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） ； Tsinghua University（清华大学） 纠错

Comments Presented at ICLR 2025 Data-FM. Seedat & Liu contributed equally

Trustworthy AI Must Account for Interactions

Jesse C. Cresswell

机构 * Jesse C. Cresswell（独立研究者） 纠错

Comments Presented at the ICLR 2025 Workshop on Bidirectional Human-AI Alignment

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

Boyang Zheng, Chumeng Liang, Xiaoyu Wu

机构 * Shanghai Jiao Tong University（上海交通大学） ； University of Southern California（南加州大学） 纠错

Comments ICLR 2025 (Spotlight)

Functional embeddings enable Aggregation of multi-area SEEG recordings over subjects and sessions

Sina Javadzadeh, Rahil Soroushmojdehi, S. Alireza Seyyed Mousavi, Mehrnaz Asadi, Sumiko Abe, Terence D. Sanger

机构 * Department of Biomedical Engineering, University of California Irvine（生物医学工程系，加州大学尔湾分校） ； Department of Electrical Engineering, University of California Irvine（电气工程系，加州大学尔湾分校） ； Department of Neurology, Rady Children’s Health（神经病学系，Rady儿童健康中心） 纠错

Comments Submitted to ICLR 2026

W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Models

Shang Wang

机构 * ShanghaiTech University（上海科技大学） 纠错

Comments ICLR 2025

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?

Mingyu Sung, Seungjae Ham, Kangwoo Kim, Yeokyoung Yoon, Sangseok Yun, Il-Min Kim, Jae-Mo Kang

机构 * Department of Artificial Intelligence（人工智能系） ； Kyungpook National University（庆尚国立大学） ； Department of Electrical and Computer Engineering（电气电子工程系） ； Queen’s University（皇后大学） ； Department of Information and Communications Engineering（信息与通信工程系） ； Pukyong National University（浦项国立大学） 纠错

Comments 11 pages, 6 figures. Includes supplementary material. Under review as a conference paper at ICLR 2026

Disentangling Shared and Private Neural Dynamics with SPIRE: A Latent Modeling Framework for Deep Brain Stimulation

Rahil Soroushmojdehi, Sina Javadzadeh, Mehrnaz Asadi, Terence D. Sanger

机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系） ； Department of Biomedical Engineering（生物医学工程系） ； Department of Neurology（神经病学系） 纠错

Comments 25 pages total. Main paper (including references): 13 pages with 7 figures. Appendix: 12 pages with 5 figures and 4 tables. Submitted to ICLR 2026

Expand and Compress: Exploring Tuning Principles for Continual Spatio-Temporal Graph Forecasting

Wei Chen, Yuxuan Liang

机构 * INTR \& DSA Thrust, The Hong Kong University of Science 纠错

Comments Accepted by ICLR 2025

Mechanism and Emergence of Stacked Attention Heads in Multi-Layer Transformers

Tiberiu Musat

机构 * ETH Zürich（苏黎世联邦理工学院） 纠错

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

Enhancing Pre-trained Representation Classifiability can Boost its Interpretability

Shufan Shen, Zhaobo Qi, Junshu Sun, Qingming Huang, Qi Tian, Shuhui Wang

机构 * Key Lab of Intell. Info. Process., Inst. of Comput. Tech., CAS（智能信息处理重点实验室，计算技术研究所，中国科学院） ； University of Chinese Academy of Sciences（中国科学院大学） ； Harbin Institute of Technology, Weihai（哈尔滨工业大学威海学院） ； Peng Cheng Laboratory（鹏城实验室） ； Huawei Inc.（华为公司） 纠错

Comments ICLR 2025 (Spotlight)

RS-ORT: A Reduced-Space Branch-and-Bound Algorithm for Optimal Regression Trees

Cristobal Heredia, Pedro Chumpitaz-Flores, Kaixun Hua

机构 * Department of Industrial and Management Systems Engineering（工业与管理系统工程系） ； University of South Florida（佛罗里达州立大学） 纠错

Comments 20 pages, 1 figure, uses ICLR 2026 LaTeX style. Submitted to arXiv as a preprint version

LASER: A Neuro-Symbolic Framework for Learning Spatial-Temporal Scene Graphs with Weak Supervision

Jiani Huang, Ziyang Li, Mayur Naik, Ser-Nam Lim

机构 * University of Pennsylvania（宾夕法尼亚大学） ； University of Central Florida（中央佛罗里达大学） 纠错

Comments Accepted at International Conference on Learning Representations (ICLR) 2025

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, Dongzhan Zhou

机构 * Nanyang Technological University（南洋理工大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） ； University of Science and Technology of China（中国科学技术大学） ； Wuhan University（武汉大学） ； University of New South Wales（新南威尔士大学） ； GreenDynamics ； Singapore University of Technology and Design（新加坡科技设计大学） 纠错

Comments Accepted by ICLR 2025

Charting the Design Space of Neural Graph Representations for Subgraph Matching

Vaibhav Raj, Indradyumna Roy, Ashwin Ramachandran, Soumen Chakrabarti, Abir De

机构 * Department of Computer Science and Engineering, IIT Bombay（计算机科学与工程系，印度理工学院班加罗尔） 纠错

Comments ICLR 2025

Deep Learning on Real-World Graphs

Emanuele Rossi

Comments The thesis was submitted for the degree of Doctor of Philosophy in Computing at Imperial College London (February 2024), under the supervision of Prof. Michael M. Bronstein. It includes work published at ICML, ICLR, NeurIPS, and the Learning on Graphs Conference

Rolling Ball Optimizer: Learning by ironing out loss landscape wrinkles

Mohammed Djameleddine Belgoumri, Mohamed Reda Bouadjenek, Hakim Hacid, Imran Razzak, Sunil Aryal

机构 * Deakin University（德肯大学） ； Technology Innovation Institute（技术创新研究所） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

Comments Submitted for review to ICLR 2026

TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees

Weibin Liao, Xu Chu, Yasha Wang

机构 * School of Computer Science, Peking University（北京大学计算机科学系） ； Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心） ； National Research and Engineering Center of Software Engineering, Peking University（北京大学软件工程研究中心） 纠错

Comments Accepted by ICLR 2025

Neural Variational Dropout Processes

Insu Jeon, Youngjin Park, Gunhee Kim

机构 * Seoul National University（首尔国立大学） 纠错

Comments Accepted as a Poster at International Conference on Learning Representations (ICLR) 2022 (Apr 25-29, 2022)

Understanding Reasoning in Thinking Language Models via Steering Vectors

Constantin Venhoff, Iván Arcuschin, Philip Torr, Arthur Conmy, Neel Nanda

机构 * University of Oxford（牛津大学） ； University of Buenos Aires（布宜诺斯艾利斯大学） 纠错

Comments Accepted to the Workshop on Reasoning and Planning for Large Language Models at ICLR 2025