ICLR

Robust Feature Learning for Multi-Index Models in High Dimensions

Alireza Mousavi-Hosseini, Adel Javanmard, Murat A. Erdogdu

Comments 41 pages, 1 figure. To appear in the International Conference on Learning Representations (ICLR), 2025

Gaussian Splatting Lucas-Kanade

Liuyue Xie, Joel Julin, Koichiro Niinuma, Laszlo A. Jeni

Comments International Conference on Learning Representations

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Samuel Marks, Can Rager, Eric J. Michaud, Yonatan Belinkov, David Bau, Aaron Mueller

Comments Code and data at https://github.com/saprmarks/feature-circuits. Demonstration at https://feature-circuits.xyz

Journal ref International Conference on Learning Representations, 2025

Partial Gromov-Wasserstein Metric

Yikun Bai, Rocio Diaz Martin, Abihith Kothapalli, Hengrong Du, Xinran Liu, Soheil Kolouri

Comments Published at ICLR 2025

Low Stein Discrepancy via Message-Passing Monte Carlo

Nathan Kirk, T. Konstantin Rusch, Jakob Zech, Daniela Rus

Comments 8 pages, 2 figures, Accepted at the ICLR 2025 Workshop on Frontiers in Probabilistic Inference

Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics

Alireza Mousavi-Hosseini, Denny Wu, Murat A. Erdogdu

Comments 36 pages, 2 figures. To appear in the International Conference on Learning Representations (ICLR), 2025

Benchmarking and optimizing organism wide single-cell RNA alignment methods

Juan Javier Diaz-Mejia, Elias Williams, Octavian Focsa, Dylan Mendonca, Swechha Singh, Brendan Innes, Sam Cooper

Comments Accepted to ICLR 2025 LMRL workshop (International Conference on Learning Representations, Learning Meaningful Representations of Life Workshop)

Learning Straight Flows by Learning Curved Interpolants

Shiv Shankar, Tomas Geffner

Comments Delta workshop at ICLR 2025

Assessing SAM for Tree Crown Instance Segmentation from Drone Imagery

Mélisande Teng, Arthur Ouaknine, Etienne Laliberté, Yoshua Bengio, David Rolnick, Hugo Larochelle

Comments ICLR 2025 ML4RS workshop

Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Models Using Implicit Feedback from Pre-training Demonstrations

Ran Tian, Kratarth Goel

Comments ICLR 2025 Spotlight

MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations

Hongyu Ke, Jack Morris, Kentaro Oguchi, Xiaofei Cao, Yongkang Liu, Haoxin Wang, Yi Ding

Journal ref ICLR 2025

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights

Fenglu Hong, Ravi Raju, Jonathan Lingjie Li, Bo Li, Urmish Thakker, Avinash Ravichandran, Swayambhoo Jain, Changran Hu

Comments Published as a workshop paper at SCOPE - ICLR 2025

AIMS.au: A Dataset for the Analysis of Modern Slavery Countermeasures in Corporate Statements

Adriana Eufrosina Bora, Pierre-Luc St-Charles, Mirko Bronzi, Arsène Fansi Tchango, Bruno Rousseau, Kerrie Mengersen

Comments Camera ready. ICLR 2025

Contractive Dynamical Imitation Policies for Efficient Out-of-Sample Recovery

Amin Abyaneh, Mahrokh G. Boroujeni, Hsiu-Chin Lin, Giancarlo Ferrari-Trecate

Comments International Conference on Learning Representations

Long-Sequence Recommendation Models Need Decoupled Embeddings

Ningya Feng, Junwei Pan, Jialong Wu, Baixu Chen, Ximei Wang, Qian Li, Xian Hu, Jie Jiang, Mingsheng Long

Comments ICLR 2025. First three authors contributed equally. Code is available at https://github.com/thuml/DARE

Mixture of Robust Experts (MoRE):A Robust Denoising Method towards multiple perturbations

Hao Cheng, Kaidi Xu, Chenan Wang, Bhavya Kailkhura, Xue Lin, Ryan Goldhahn

Comments This paper is accepted by ICLR 2021 Robust and reliable machine learning in the real world Workshop

Analytic DAG Constraints for Differentiable DAG Learning

Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Mingming Gong, Biwei Huang, Kun Zhang, Anton van den Hengel, Javen Qinfeng Shi

Comments Accepted to ICLR 2025

Journal ref ICLR 2025

Neuromorphic Principles for Efficient Large Language Models on Intel Loihi 2

Steven Abreu, Sumit Bam Shrestha, Rui-Jie Zhu, Jason Eshraghian

Comments Accepted to International Conference on Learning Representations (ICLR) Workshop on Scalable Optimization for Efficient and Adaptive Foundation Models (SCOPE)

Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

Nguyen Do, Truc Nguyen, Malik Hassanaly, Raed Alharbi, Jung Taek Seo, My T. Thai

Journal ref In The Thirteenth International Conference on Learning Representations, 2025

Towards Understanding Distilled Reasoning Models: A Representational Approach

David D. Baek, Max Tegmark

Comments 13 pages, 9 figures

Journal ref ICLR 2025 Workshop on Building Trust in Language Models and Applications

Improved Training Technique for Latent Consistency Models

Quan Dao, Khanh Doan, Di Liu, Trung Le, Dimitris Metaxas

Comments Accepted at ICLR 2025

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

Sravanti Addepalli, Yerram Varun, Arun Suggala, Karthikeyan Shanmugam, Prateek Jain

Comments Accepted in ICLR 2025

Journal ref Addepalli, S., Varun, Y., Suggala, A., Shanmugam, K., & Jain, P. (2025). Does safety training of LLMs generalize to semantically related natural prompts? In The Thirteenth International Conference on Learning Representations 2025

h4rm3l: A language for Composable Jailbreak Attack Synthesis

Moussa Koulako Bala Doumbouya, Ananjan Nandi, Gabriel Poesia, Davide Ghilardi, Anna Goldie, Federico Bianchi, Dan Jurafsky, Christopher D. Manning

Comments Accepted to the Thirteenth International Conference on Learning Representations (ICLR 2025)

TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models

Leigang Qu, Haochuan Li, Tan Wang, Wenjie Wang, Yongqi Li, Liqiang Nie, Tat-Seng Chua

Comments ICLR 2025 Camera-ready

PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis

Satoki Ishikawa, Makoto Yamada, Han Bao, Yuki Takezawa

Comments ICLR 2025

MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers

Ao Li, Wei Fang, Hongbo Zhao, Le Lu, Ge Yang, Minfeng Xu

Comments Accepted by ICLR 2025

Interleaved Scene Graphs for Interleaved Text-and-Image Generation Assessment

Dongping Chen, Ruoxi Chen, Shu Pu, Zhaoyi Liu, Yanru Wu, Caixi Chen, Benlin Liu, Yue Huang, Yao Wan, Pan Zhou, Ranjay Krishna

Comments Accepted by ICLR 2025 as Spotlight. Project homepage: https://interleave-eval.github.io/

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks

Qiang Liu, Mengyu Chu, Nils Thuerey

Comments Accepted by ICLR2025 as spotlight paper; Project homepage: https://tum-pbs.github.io/ConFIG/

Journal ref The Thirteenth International Conference on Learning Representations, 2025

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

Dongping Chen, Yue Huang, Siyuan Wu, Jingyu Tang, Liuyi Chen, Yilin Bai, Zhigang He, Chenlong Wang, Huichi Zhou, Yiqiang Li, Tianshuo Zhou, Yue Yu, Chujie Gao, Qihui Zhang, Yi Gui, Zhen Li, Yao Wan, Pan Zhou, Jianfeng Gao, Lichao Sun

Comments Accepted by ICLR 2025

Mitigating Reward Over-Optimization in RLHF via Behavior-Supported Regularization

Juntao Dai, Taiye Chen, Yaodong Yang, Qian Zheng, Gang Pan

Comments Published as a conference paper at ICLR 2025