ICLR 2025 Conference Submissions

Distilling Reinforcement Learning into Single-Batch Datasets
Connor Wilhelm, Dan Ventura
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language Models
Hanzhu Chen, Xu Shen, Jie Wang, Zehao Wang, Qitan Lv, Junjie He, Rong Wu, Feng Wu, Jieping Ye
- Published: 22 Jan 2025, Last Modified: 15 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SyncFlow: Temporally Aligned Joint Audio-Video Generation from Text
Haohe Liu, Gael Le Lan, Xinhao Mei, Zhaoheng Ni, Anurag Kumar, Varun K. Nagaraja, Wenwu Wang, Mark D Plumbley, Yangyang Shi, Vikas Chandra
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Terry Yue Zhuo, Vu Minh Chien, Jenny Chim, Han Hu, Wenhao Yu, Ratnadira Widyasari, Imam Nur Bani Yusuf, Haolan Zhan, Junda He, Indraneil Paul, Simon Brunner, Chen GONG, James Hoang, Armel Randy Zebaze, Xiaoheng Hong, Wen-Ding Li, Jean Kaddour, Ming Xu, Zhihan Zhang, Prateek Yadav et al. (13 additional authors not shown)
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement
Xueyao Zhang, Xiaohui Zhang, Kainan Peng, Zhenyu Tang, Vimal Manohar, Yingru Liu, Jeff Hwang, Dangna Li, Yuhao Wang, Julian Chan, Yuan Huang, Zhizheng Wu, Mingbo Ma
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Benchmarking Mental State Representations in Language Models
Matteo Bortoletto, Constantin Ruhdorfer, Lei Shi, Andreas Bulling
- 26 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
AVSET-10M: An Open Large-Scale Audio-Visual Dataset with High Correspondence
Xize Cheng, Ziang Zhang, Minghui Fang, Zehan Wang, Ruofan Hu, Siqi Zheng, Rongjie Huang, Tao Jin, Zhou Zhao
- 26 Sept 2024 (modified: 14 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Leveraging One-To-Many Relationships in Multimodal Adversarial Defense for Robust Image-Text Retrieval
Futa Kai Waseda, Antonio Tejero-de-Pablos, Isao Echizen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Designing Mechanical Meta-Materials by Learning Equivariant Flows
Mehran Mirramezani, Anne S. Meeussen, Katia Bertoldi, Peter Orbanz, Ryan P Adams
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Stealing User Prompts from Mixture-of-Experts Models
Itay Yona, Jamie Hayes, Ilia Shumailov, Nicholas Carlini
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Understanding Link Predictor Generalizability Under Distribution Shifts
Jay Revolinsky, Harry Shomer, Jiliang Tang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Simulating Training Dynamics to Reconstruct Training Data from Deep Neural Networks
Hanling Tian, Yuhang Liu, Mingzhen He, Zhengbao He, Zhehao Huang, Ruikai Yang, Xiaolin Huang
- Published: 22 Jan 2025, Last Modified: 13 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning
Alexander Nikulin, Ilya Zisman, Alexey Zemtsov, Vladislav Kurenkov
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Geometric Neural Process Fields
Wenzhe Yin, Zehao Xiao, Jiayi Shen, Yunlu Chen, Cees G. M. Snoek, Jan-Jakob Sonke, Efstratios Gavves
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Common Neighbor Induced Message Passing for Inductive Link Prediction in Knowledge Graphs
Hanzhu Chen, Jie Wang, Qitan Lv, Xiaoqi Ni, Yuhang Jiang, Zhihao Shi, Bin Li
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Towards a Complete Logical Framework for GNN Expressiveness
Tuo Xu
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
How Far Are We from True Unlearnability?
Kai Ye, Liangcai Su, Chenxiong Qian
- Published: 22 Jan 2025, Last Modified: 08 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Bridging the Gap between Database Search and \emph{De Novo} Peptide Sequencing with SearchNovo
Jun Xia, Sizhe Liu, Jingbo Zhou, Shaorong Chen, hongxin xiang, Zicheng Liu, Yue Liu, Stan Z. Li
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Structure-Preserving Text-Based Editing for Few-Step Diffusion Models
Eunseo Koh, Sangeek Hyun, MinKyu Lee, Jiwoo Chung, Jae-Pil Heo
- 26 Sept 2024 (modified: 17 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
One Pass Streaming Algorithm for Super Long Token Attention Approximation in Sublinear Space
Raghavendra Addanki, Chenyang Li, Zhao Song, Chiwun Yang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Rethinking Invariance Regularization in Adversarial Training to Improve Robustness-Accuracy Trade-off
Futa Kai Waseda, Ching-Chun Chang, Isao Echizen
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Latent Point Collapse Induces an Information Bottleneck in Deep Neural Network Classifiers
Luigi Sbailò, Luca M Ghiringhelli
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Mixed Hierarchical Oracle and Multi-Agent Benchmark in Two-player Zero-sum Games
Hongsong Tang, Bo Chen, Yingzhuo Liu, Yaodong Yang, Junge Zhang, Liuyu Xiang, Jianchun Xu, Zhaofeng He
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PFT: Enhancing Prompt Injection Robustness via Position-Enhanced Finetuning
Zihao Wang, Yibo Jiang, Jiahao Yu, Heqing Huang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Pareto-Optimal Learning from Preferences with Hidden Context
Ryan Boldi, Li Ding, Lee Spector, Scott Niekum
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone