ICLR 2025 Conference Submissions

Matrix Product Sketching via Coordinated Sampling
Majid Daliri, Juliana Freire, Danrong Li, Christopher Musco
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
A Phase Transition Induces Catastrophic Overfitting in Adversarial Training
Elias Abad Rocamora, Noam Itzhak Levi, Volkan Cevher
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Robustness of Vision-Language Models Against Distractions
Ming Liu, Hao Chen, Jindong Wang, Wensheng Zhang
- 27 Sept 2024 (modified: 22 Oct 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gaze
Yunsoo Kim, Jinge Wu, Honghan Wu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
Zhen Qin, Zhuqing Liu, Songtao Lu, Yingbin Liang, Jia Liu
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Preserving Deep Representations in One-Shot Pruning: A Hessian-Free Second-Order Optimization Framework
Ryan Lucas, Rahul Mazumder
- Published: 22 Jan 2025, Last Modified: 06 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Characterizing Context Influence and Hallucination in Summarization
James Flemings, Wanrong Zhang, Bo Jiang, Zafar Takhirov, Murali Annavaram
- 27 Sept 2024 (modified: 03 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Capturing the Temporal Dependence of Training Data Influence
Jiachen T. Wang, Dawn Song, James Zou, Prateek Mittal, Ruoxi Jia
- Published: 22 Jan 2025, Last Modified: 14 Mar 2025
- ICLR 2025 Oral
- Readers: Everyone
FEABench: Evaluating Language Models on Real World Physics Reasoning Ability
Nayantara Mudur, Hao Cui, Subhashini Venugopalan, Paul Raccuglia, Michael Brenner, Peter Christian Norgaard
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Learning from Preferences and Mixed Demonstrations in General Settings
Jason Ross Brown, Carl Henrik Ek, Robert D. Mullins
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Wasserstein Distances, Neuronal Entanglement, and Sparsity
Shashata Sawmya, Linghao Kong, Ilia Markov, Dan Alistarh, Nir N Shavit
- Published: 22 Jan 2025, Last Modified: 28 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith Menon Suriyakumar, Rohan Alur, Ayush Sekhari, Manish Raghavan, Ashia C. Wilson
- 27 Sept 2024 (modified: 21 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Chemistry-Inspired Diffusion with Non-Differentiable Guidance
Yuchen Shen, Chenhao Zhang, Sijie Fu, Chenghui Zhou, Newell Washburn, Barnabas Poczos
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
A Simple Baseline for Predicting Future Events with Auto-Regressive Tabular Transformers
Alex Stein, Samuel Sharpe, Doron L Bergman, Senthil Kumar, John P Dickerson, Tom Goldstein, Micah Goldblum
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Convergence of Adam-Type Algorithms for Bilevel Optimization under Unbounded Smoothness
Xiaochuan Gong, Jie Hao, Mingrui Liu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning
Moritz Reuss, Jyothish Pari, Pulkit Agrawal, Rudolf Lioutikov
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
Daniel Cai, Randall Balestriero
- Published: 22 Jan 2025, Last Modified: 27 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Lie Group-Induced Dynamics in Score-Based Generative Modeling
Marco Bertolini, Tuan Le, Djork-Arné Clevert
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
Xiaoxuan Hou, Jiayi Yuan, Joel Z Leibo, Natasha Jaques
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control
Songyuan Zhang, Oswin So, Mitchell Black, Chuchu Fan
- Published: 22 Jan 2025, Last Modified: 13 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Aligning Language Models with Demonstrated Feedback
Omar Shaikh, Michelle S. Lam, Joey Hejna, Yijia Shao, Hyundong Justin Cho, Michael S. Bernstein, Diyi Yang
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Are LLMs Prescient? A Continuous Evaluation using Daily News as the Oracle
Hui Dai, Ryan Teehan, Mengye Ren
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Adversarial Robustness of In-Context Learning in Transformers for Linear Regression
Usman Anwar, Johannes von Oswald, Louis Kirsch, David Krueger, Spencer Frei
- 27 Sept 2024 (modified: 12 May 2025)
- Submitted to ICLR 2025
- Readers: Everyone
See It from My Perspective: How Language Affects Cultural Bias in Image Understanding
Amith Ananthram, Elias Stengel-Eskin, Mohit Bansal, Kathleen McKeown
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities
Andrey Anurin, Jonathan Ng, Kibo Schaffer, Ziyue Wang, Jason Hoelscher-Obermaier, Esben Kran
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone