ICLR 2025 Conference Submissions

UNComp: Uncertainty-Aware Long-context Compressor for Efficient Large Language Model Inference
Jing Xiong, Jianghan Shen, Fanghua Ye, Chaofan Tao, Zhongwei Wan, Jianqiao Lu, Xun Wu, Chuanyang Zheng, Zhijiang Guo, Lingpeng Kong, Ngai Wong
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Price of Freedom: Exploring Tradeoffs in Equivariant Tensor Products with Spherical Signals
YuQing Xie, Ameya Daigavane, Mit Kotak, Tess Smidt
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Reassessing How to Compare and Improve the Calibration of Machine Learning Models
Muthu Chidambaram, Rong Ge
- Published: 22 Jan 2025, Last Modified: 23 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Uncertainty-aware Guided Diffusion for Missing Data in Sequential Recommendation
Wenyu Mao, Zhengyi Yang, Jiancan Wu, Haozhe Liu, Yancheng Yuan, Xiang Wang, Xiangnan He
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
Dongseong Hwang
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Generalized Principal-Agent Problem with a Learning Agent
Tao Lin, Yiling Chen
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Accelerated Online Reinforcement Learning using Auxiliary Start State Distributions
Aman Mehra, Alexandre Capone, Jeff Schneider
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Time Transfer: On Optimal Learning Rate and Batch Size In The Infinite Data Limit
Oleg Filatov, Jan Ebert, Jiangtao Wang, Stefan Kesselheim
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
Tony Alex, Sara Atito, Armin Mustafa, Muhammad Awais, Philip J B Jackson
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Contextually Guided Transformers via Low-Rank Adaptation
Andrey Zhmoginov, Jihwan Lee, Max Vladymyrov, Mark Sandler
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods
Hossein Taheri, Christos Thrampoulidis, Arya Mazumdar
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Salutary Labeling with Zero Human Annotation
Wenxiao Xiao, Hongfu Liu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Adaptive Source Localization on Complex Networks via Conditional Diffusion Model
Hongyi Chen, Jingtao Ding, Xiaojun Liang, Yong Li, Xiao-Ping Zhang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
HumanoidOlympics: Sports Environments for Physically Simulated Humanoids
Zhengyi Luo, Jiashun Wang, Kangni Liu, Haotian Zhang, Chen Tessler, Jingbo Wang, Ye Yuan, Jinkun Cao, Zihui Lin, Fengyi Wang, Jessica K. Hodgins, Kris M. Kitani
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
HiDF: A Human-Indistinguishable Deepfake Dataset
Chaewon Kang, Seoyoon Jeong, jonghyun lee, Daejin Choi, Simon S. Woo, Jinyoung Han
- 26 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
VideoPanda: Video Panoramic Diffusion With Multi-view Attention
Kevin Xie, Amirmojtaba Sabour, Jiahui Huang, Despoina Paschalidou, Umar Iqbal, Sanja Fidler, Xiaohui Zeng
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning
Alex Beutel, Kai Yuanqing Xiao, Johannes Heidecke, Lilian Weng
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Targeted Attack Improves Protection against Unauthorized Diffusion Customization
Boyang Zheng, Chumeng Liang, Xiaoyu Wu
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
OCEAN: Online Multi-modal Root Cause Analysis for Microservice Systems
Lecheng Zheng, Zhengzhang Chen, Haifeng Chen, Jingrui He
- 26 Sept 2024 (modified: 01 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Diffusion & Adversarial Schrödinger Bridges via Iterative Proportional Markovian Fitting
Sergei Kholkin, Grigoriy Ksenofontov, David Li, Nikita Maksimovich Kornilov, Nikita Gushchin, Evgeny Burnaev, Alexander Korotin
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Unifying All Species: LLM-based Hyper-Heuristics for Multi-objective Optimization
Haolong Qian, Shuting Dong, Hao Yu, Chun Yuan
- 26 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Incrementally Adapting Generative Vision-Language Models with Task Codebook
Jinghao Zhou, Ahmet Iscen, Mathilde Caron, Christian Rupprecht, Philip Torr, Cordelia Schmid
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Limitations of General Purpose Domain Generalisation Methods
Henry Gouk, Ondrej Bohdal, Da Li, Timothy Hospedales
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Unlocking the Power of GANs in Non-Autoregressive Text Generation
Da Ren, Yi Cai, Qing Li
- 26 Sept 2024 (modified: 17 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Diversity-Rewarded CFG Distillation
Geoffrey Cideron, Andrea Agostinelli, Johan Ferret, Sertan Girgin, Romuald Elie, Olivier Bachem, Sarah Perrin, Alexandre Rame
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone