ICLR

Conformal Prediction Sets Can Cause Disparate Impact

Jesse C. Cresswell, Bhargava Kumar, Yi Sui, Mouloud Belbahri

Comments ICLR 2025 Spotlight, https://openreview.net/forum?id=fZK6AQXlUU. Code and experimental data are available at https://github.com/layer6ai-labs/conformal-prediction-fairness

Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation

Chenyu Zhang, Xu Chen, Xuan Di

Comments Published as a conference paper at ICLR 2025

Linear Mode Connectivity in Differentiable Tree Ensembles

Ryuichi Kanoh, Mahito Sugiyama

Comments Accepted to ICLR 2025

AgentStudio: A Toolkit for Building General Virtual Agents

Longtao Zheng, Zhiyuan Huang, Zhenghai Xue, Xinrun Wang, Bo An, Shuicheng Yan

Comments ICLR 2025. Project page: https://ltzheng.github.io/agent-studio

Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos

Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

Comments Accepted at ICLR 2025 (camera-ready version). Update: added language modeling experiments

LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

Jing Wen, Alexander G. Schwing, Shenlong Wang

Comments ICLR 2025; Project page: https://wenj.github.io/LIFe-GoM/

DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References

Xueyi Liu, Jianibieke Adalibieke, Qianwei Han, Yuzhe Qin, Li Yi

Comments Accepted to ICLR 2025. Website: https://meowuu7.github.io/DexTrack/ Code: https://github.com/Meowuu7/DexTrack/ Video: https://youtu.be/zru1Z-DaiWE

Latent Radiance Fields with 3D-aware 2D Representations

Chaoyi Zhou, Xi Liu, Feng Luo, Siyu Huang

Comments Accepted to ICLR 2025; Project page: https://latent-radiance-field.github.io/LRF

Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs

Siyan Zhao, Mingyi Hong, Yang Liu, Devamanyu Hazarika, Kaixiang Lin

Comments Accepted at ICLR 2025 as oral presentation. Code and data at: https://prefeval.github.io/

OGBench: Benchmarking Offline Goal-Conditioned RL

Seohong Park, Kevin Frans, Benjamin Eysenbach, Sergey Levine

Comments ICLR 2025

Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes

Jianqi Chen, Panwen Hu, Xiaojun Chang, Zhenwei Shi, Michael Kampffmeyer, Xiaodan Liang

Comments Accepted by ICLR 2025. Project Page: https://windvchen.github.io/Sitcom-Crafter

Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection

Hongru Yan, Yu Zheng, Yueqi Duan

Comments Accepted to ICLR 2025

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

Simon Heilig, Alessio Gravina, Alessandro Trenta, Claudio Gallicchio, Davide Bacciu

Comments Accepted at ICLR 2025 (https://openreview.net/forum?id=03EkqSCKuO)

Transformers Learn Low Sensitivity Functions: Investigations and Implications

Bhavya Vasudeva, Deqing Fu, Tianyi Zhou, Elliott Kau, Youqi Huang, Vatsal Sharan

Comments ICLR 2025. 24 pages, 19 figures, 3 tables

A Deep Inverse-Mapping Model for a Flapping Robotic Wing

Hadar Sharvit, Raz Karl, Tsevi Beatus

Comments Accepted to ICLR 2025. 10 Pages 5 figures + 2 figures in appendix

Bridging Jensen Gap for Max-Min Group Fairness Optimization in Recommendation

Chen Xu, Yuxin Li, Wenjie Wang, Liang Pang, Jun Xu, Tat-Seng Chua

Comments Accepted in ICLR 2025

Improving Deep Regression with Tightness

Shihao Zhang, Yuguang Yan, Angela Yao

Comments ICLR 2025, Code: https://github.com/needylove/Regression_tightness

What exactly has TabPFN learned to do?

Calvin McCarter

Comments Originally published in Blogposts Track at ICLR 2024. Appendix contains re-analysis on TabPFN-v2 [Hollmann et al., 2025]

Biologically Plausible Brain Graph Transformer

Ciyuan Peng, Yuelong Huang, Qichao Dong, Shuo Yu, Feng Xia, Chengqi Zhang, Yaochu Jin

Comments 27pages, 16figures, published as a conference paper at ICLR 2025

Continuous Autoregressive Modeling with Stochastic Monotonic Alignment for Speech Synthesis

Weiwei Lin, Chenghan He

Comments ICLR 2025

Journal ref ICLR 2025

An Engorgio Prompt Makes Large Language Model Babble on

Jianshuo Dong, Ziyuan Zhang, Qingjie Zhang, Tianwei Zhang, Hao Wang, Hewu Li, Qi Li, Chao Zhang, Ke Xu, Han Qiu

Comments ICLR 2025

COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training

Haocheng Xi, Han Cai, Ligeng Zhu, Yao Lu, Kurt Keutzer, Jianfei Chen, Song Han

Comments Accepted by ICLR 2025. 22 pages. 9 Figures. 13 Tables

ImDy: Human Inverse Dynamics from Imitated Observations

Xinpeng Liu, Junxuan Liang, Zili Lin, Haowen Hou, Yong-Lu Li, Cewu Lu

Comments To appear in ICLR 2025. Yong-Lu Li and Cewu Lu are the corresponding authors

An Evolved Universal Transformer Memory

Edoardo Cetin, Qi Sun, Tianyu Zhao, Yujin Tang

Comments Published at ICLR 2025. Source code available at https://github.com/SakanaAI/evo-memory

MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation

Trung X. Pham, Tri Ton, Chang D. Yoo

Comments ICLR 2025

OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation

Kepan Nan, Rui Xie, Penghao Zhou, Tiehan Fan, Zhenheng Yang, Zhijie Chen, Xiang Li, Jian Yang, Ying Tai

Comments 20 pages, 15 figures, Published as a conference paper at ICLR 2025

Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation

Mohamed El Amine Boudjoghra, Angela Dai, Jean Lahoud, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Fahad Shahbaz Khan

Comments ICLR 2025 (Oral)

For Better or For Worse? Learning Minimum Variance Features With Label Augmentation

Muthu Chidambaram, Rong Ge

Comments ICLR 2025, 25 pages, 8 figures

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding

Xinyu Yang, Tianqi Chen, Beidi Chen

Comments ICLR 2025

Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation

Anish Abhijit Diwan, Julen Urain, Jens Kober, Jan Peters

Comments Accepted as a conference paper at the International Conference on Learning Representations (ICLR) 2025. Revised to include review feedback