ICLR 2025 Conference Submissions

Enhancing Multi-Agent Learning in Real-World Interactive Environments through Process Reward Decomposition
Zhitao He, Zijun Liu, Peng Li, Yi Fung, Ming Yan, Ji Zhang, Fei Huang, Yang Liu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Eliminating Position Bias of Language Models: A Mechanistic Approach
Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
- Published: 22 Jan 2025, Last Modified: 31 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Continuous-Time Analysis of Adaptive Optimization and Normalization
Rhys Gould, Hidenori Tanaka
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
From Tokens to Lattices: Emergent Lattice Structures in Language Models
Bo Xiong, Steffen Staab
- Published: 22 Jan 2025, Last Modified: 10 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Clusters Agnostic Network Lasso Bandits
Sofien Dhouib, Steven Bilaj, Behzad Nourani-Koliji, Setareh Maghsudi
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
Tianhao Wu, Weizhe Yuan, Olga Golovneva, Jing Xu, Yuandong Tian, Jiantao Jiao, Jason E Weston, Sainbayar Sukhbaatar
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Demystifying Topological Message-Passing with Relational Structures: A Case Study on Oversquashing in Simplicial Message-Passing
Diaaeldin Taha, James Chapman, Marzieh Eidi, Karel Devriendt, Guido Montufar
- Published: 22 Jan 2025, Last Modified: 25 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
EOP: Unlocking Superior Problem Solving in Small LLMs
Zining Zhang, Bingsheng He
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysis
Lecheng Zheng, Zhengzhang Chen, Dongjie Wang, Chengyuan Deng, Reon Matsuoka, Haifeng Chen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Language Models Can Help to Learn High-Performing Cost Functions for Recourse
Eoin M. Kenny, Allan Anzagira, Tom Bewley, Freddy Lecue, Manuela Veloso
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generalized Consistency Trajectory Models for Image Manipulation
Beomsu Kim, Jaemin Kim, Jeongsol Kim, Jong Chul Ye
- Published: 22 Jan 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
HERTA: A High-Efficiency and Rigorous Training Algorithm for Unfolded Graph Neural Networks
Yongyi Yang, Jiaming Yang, Wei Hu, Michal Derezinski
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
DiffTell: A Comprehensive Dataset for Image Difference Captioning
Zonglin Di, Jing Shi, Yifei Fan, Hao Tan, Alexander Black, John Collomosse, Yang Liu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Matchmaker: Schema Matching with self-improving compositional LLM programs
Nabeel Seedat, Mihaela van der Schaar
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Fair Submodular Cover
Wenjing Chen, Shuo Xing, Samson Zhou, Victoria G. Crawford
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Revealing the 3D Cosmic Web through Gravitationally Constrained Neural Fields
Brandon Zhao, Aviad Levis, Liam Connor, Pratul P. Srinivasan, Katherine Bouman
- Published: 22 Jan 2025, Last Modified: 27 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Swing-by Dynamics in Concept Learning and Compositional Generalization
Yongyi Yang, Core Francisco Park, Ekdeep Singh Lubana, Maya Okawa, Wei Hu, Hidenori Tanaka
- Published: 22 Jan 2025, Last Modified: 13 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
MotherNet: Fast Training and Inference via Hyper-Network Transformers
Andreas C Mueller, Carlo A Curino, Raghu Ramakrishnan
- Published: 22 Jan 2025, Last Modified: 05 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Inference-time Alignment of LLMs at the Token Level
Yu Fei, Yasaman Razeghi, Sameer Singh
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, J Zico Kolter, Matt Fredrikson, Yarin Gal, Xander Davies
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
A Reasoning-Based Approach to Cryptic Crossword Clue Solving
Martin Andrews, Sam Witteveen
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CoINR: Compressed Implicit Neural Representations
Dhananjaya Jayasundara, Sudarshan Rajagopalan, Don Yasiru Lakshan Ranasinghe, Trac Tran, Vishal M. Patel
- 26 Sept 2024 (modified: 15 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Approximation algorithms for combinatorial optimization with predictions
Antonios Antoniadis, Marek Elias, Adam Polak, Moritz Venzin
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Learn from Interactions: General-Sum Interactive Inverse Reinforcement Learning
Yue Mao, Shicheng Liu, Minghui Zhu
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PlicoTabTransformer: Folding Tabular Embeddings Into M Vectors
Jonathan Chung, Giridhar Narasapura Rajagopalaiah
- 26 Sept 2024 (modified: 21 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone