ICLR 2025 Conference Submissions

Mitigating Distribution Shifts: Uncertainty-Aware Offline-to-Online Reinforcement Learning
Mohamad H. Danesh, Maxime Wabartha, Joelle Pineau, Hsiu-Chin Lin
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Accessing Vision Foundation Models via ImageNet-1K
Yitian Zhang, Xu Ma, Yue Bai, Huan Wang, Yun Fu
- Published: 22 Jan 2025, Last Modified: 20 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Quantized Approximately Orthogonal Recurrent Neural Networks
Armand Foucault, Francois Malgouyres, Franck Mamalet
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Optimizing Adaptive Attacks against Content Watermarks for Language Models
Abdulrahman Diaa, Toluwani Aremu, Nils Lukas
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Binary Losses for Density Ratio Estimation
Werner Zellinger
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
StagFormer: A Staggered Transformer for Decoding Layers in Parallel
Dylan J Cutler, Arun Kandoor, Nishanth Dikkala, Xin Wang, Nikunj Saunshi, Rina Panigrahy
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
How transformers learn structured data: insights from hierarchical filtering
Jerome Garnier-Brun, Marc Mezard, Emanuele Moscato, Luca Saglietti
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Gradient Storm: Stronger Backdoor Attacks Through Expanded Parameter Space Coverage
Arman Malekzadeh, Abolfazl Motahari
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Explainable Transfer Learning on Graphs Using a Novel Label Frequency Representation
Francesco Leonardi, Kaspar Riesen
- 25 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports
Yi Xu, Yun Fu
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
SWEb: A Large Web Dataset for the Scandinavian Languages
Tobias Norlund, Tim Isbister, Amaru Cuba Gyllensten, Paul Gabriel dos Santos, Danila Petrelli, Ariel Ekgren, Magnus Sahlgren
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
RTDiff: Reverse Trajectory Synthesis via Diffusion for Offline Reinforcement Learning
Qianlan Yang, Yu-Xiong Wang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Generalization, Expressivity, and Universality of Graph Neural Networks on Attributed Graphs
Levi Rauchwerger, Stefanie Jegelka, Ron Levie
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Gap-Aware Preference Optimization: Enhancing Model Alignment with Perception Margin
Lou Jieming, Chen Xiuyu, Jiqing Liu, Weide Liu
- 25 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
I-Con: A Unifying Framework for Representation Learning
Shaden Naif Alshammari, John R. Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton
- Published: 22 Jan 2025, Last Modified: 26 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG
Bowen Jin, Jinsung Yoon, Jiawei Han, Sercan O Arik
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Information-theoretic Generalization Analysis for Vector-Quantized VAEs
Futoshi Futami, Masahiro Fujisawa
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
RankNovo: A Universal Reranking Approach for Robust De Novo Peptide Sequencing
Zijie Qiu, Jiaqi Wei, Xiang Zhang, Sheng Xu, Kai Zou, Zhi Jin, ZhiQiang Gao, Nanqing Dong, Siqi Sun
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Refining Counterfactual Explanations With Joint-Distribution-Informed Shapley Towards Actionable Minimality
Lei You, Yijun Bian, Lele Cao
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Unlocking Full Dynamic Optimization of District Energy Systems through State-Space Model Learning
Taha Boussaid, François Rousset, Marc CLAUSSE, Vasile-Marian Scuturici
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold
Sixin Zhang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Explanations of GNN on Evolving Graphs via Axiomatic Layer edges
Yazheng Liu, Sihong Xie
- Published: 22 Jan 2025, Last Modified: 04 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Understanding and Enhancing Context-Augmented Language Models Through Mechanistic Circuits
Samyadeep Basu, Vlad I Morariu, Zichao Wang, Ryan A. Rossi, Nanxuan Zhao, Soheil Feizi, Varun Manjunatha
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning positional encodings in transformers depends on initialization
Takuya Ito, Luca Cocchi, Tim Klinger, Parikshit Ram, Murray Campbell, Luke J. Hearne
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Agent Workflow Memory
Zhiruo Wang, Jiayuan Mao, Daniel Fried, Graham Neubig
- 25 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone