ICLR 2025 Conference Submissions

Finally Rank-Breaking Conquers MNL Bandits: Optimal and Efficient Algorithms for MNL Assortment
Aadirupa Saha, Pierre Gaillard
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Efficient Top-m Data Values Identification for Data Selection
Xiaoqiang Lin, Xinyi Xu, See-Kiong Ng, Bryan Kian Hsiang Low
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery
Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, Vishal Dey, Mingyi Xue, Frazier N. Baker, Benjamin Burns, Daniel Adu-Ampratwum, Xuhui Huang, Xia Ning, Song Gao, Yu Su, Huan Sun
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SHARP: Accelerating Language Model Inference by SHaring Adjacent layers with Recovery Parameters
Yiping Wang, Hanxian Huang, Yifang Chen, Jishen Zhao, Simon Shaolei Du, Yuandong Tian
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
Hanlin Tang, Yang Lin, Jing Lin, Qingsen Han, Danning Ke, Shikuan Hong, Yiwu Yao, Gongyi Wang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
Mufei Li, Siqi Miao, Pan Li
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Feature Driven Graph Coarsening for Scaling Graph Representation Learning
Manoj Kumar, Sumit Kumar, Vipul Kumar Singh, Sandeep Kumar
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LLMPhy: Complex Physical Reasoning Using Large Language Models and World Models
Anoop Cherian, Radu Corcodel, Siddarth Jain, Diego Romeres
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MrT5: Dynamic Token Merging for Efficient Byte-level Language Models
Julie Kallini, Shikhar Murty, Christopher D Manning, Christopher Potts, Róbert Csordás
- Published: 22 Jan 2025, Last Modified: 02 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems
Xudong Gong, Feng Dawei, Kele Xu, weijia wang, Zhangjun Sun, Xing Zhou, Si Zheng, Bo Ding, Huaimin Wang
- Published: 22 Jan 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Commit0: Library Generation from Scratch
Wenting Zhao, Nan Jiang, Celine Lee, Justin T Chiu, Claire Cardie, Matthias Gallé, Alexander M Rush
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
Aleksandar Makelov, Georg Lange, Neel Nanda
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
CIRCUIT: A Benchmark for Circuit Interpretation and Reasoning Capabilities of LLMs
Lejla Skelic, Yan Xu, Matthew Cox, Wenjie Lu, Tao Yu, Ruonan Han
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CL-MFAP: A Contrastive Learning-Based Multimodal Foundation Model for Molecular Property Prediction and Antibiotic Screening
Gen Zhou, Sugitha Janarthanan, Yutong Lu, Pingzhao Hu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Disentangled Representation Learning for Parametric Partial Differential Equations
Ning Liu, Lu Zhang, Tian Gao, Yue Yu
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SeedLM: Compressing LLM Weights into Seeds of Pseudo-Random Generators
Rasoul Shafipour, David Harrison, Maxwell Horton, JEFFREY MARKER, Houman Bedayat, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi, Saman Naderiparizi
- Published: 22 Jan 2025, Last Modified: 16 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Dissecting Adversarial Robustness of Multimodal LM Agents
Chen Henry Wu, Rishi Rajesh Shah, Jing Yu Koh, Russ Salakhutdinov, Daniel Fried, Aditi Raghunathan
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Weighted Fair Regression under Selection Bias
Jue Wang, Raymond K. W. Wong, Thomas Lee
- 28 Sept 2024 (modified: 20 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Prompt Injection Benchmark for Foundation Model Integrated Systems
Jiongxiao Wang, Peiran Li, Siyuan Ma, Peiran Wang, Xiaogeng Liu, Jiashuo Sun, Yiming Liang, Tian Xia, Yu Wang, Weidi Luo, Chaowei Xiao
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
Andrew Estornell, Jean-Francois Ton, Yuanshun Yao, Yang Liu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
Pierfrancesco Beneventano, Blake Woodworth
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Theoretical Aspects of Bias and Diversity in Minimum Bayes Risk Decoding
Hidetaka Kamigaito, Hiroyuki Deguchi, Yusuke Sakai, Katsuhiko Hayashi, Taro Watanabe
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Enhancing Physics-Informed Neural Networks Through Feature Engineering
Shaghayegh Fazliani, Zachary Frangella, Madeleine Udell
- 28 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Interpretable Patterns in Random Initialization Unveil Final Representation
Xiaoman Delores Ding, Zifan Carl Guo, Eric J Michaud, Ziming Liu, Max Tegmark
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Greener GRASS: Enhancing GNNs with Encoding, Rewiring, and Attention
Tongzhou Liao, Barnabas Poczos
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone