ICLR 2025 Conference Submissions

Generalization v.s. Memorization: Tracing Language Models’ Capabilities Back to Pretraining Data
Xinyi Wang, Antonis Antoniades, Yanai Elazar, Alfonso Amayuelas, Alon Albalak, Kexun Zhang, William Yang Wang
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Contextual Bandits with Entropy-based Human Feedback
Raihan Seraj, Tristan Sylvain, Lili Meng
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Safety Self-Alignment
Zhili Liu, Yunhao GOU, Kai Chen, Lanqing HONG, Jiahui Gao, Fei Mi, Yu Zhang, Zhenguo Li, Xin Jiang, Qun Liu, James Kwok
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the onset of memorization to generalization transition in diffusion models
Indranil Halder, Cengiz Pehlevan
- 26 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
EraseDiff: Erasing Data Influence in Diffusion Models
Jing Wu, Trung Le, Munawar Hayat, Mehrtash Harandi
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Transformers Handle Endogeneity in In-Context Linear Regression
Haodong Liang, Krishna Balasubramanian, Lifeng Lai
- Published: 22 Jan 2025, Last Modified: 11 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Data Valuation for Graphs
Simone Antonelli, Aleksandar Bojchevski
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Grokking at the Edge of Linear Separability
Alon Beck, Noam Itzhak Levi, Yohai Bar-Sinai
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
How Does Critical Batch Size Scale in Pre-training?
Hanlin Zhang, Depen Morwani, Nikhil Vyas, Jingfeng Wu, Difan Zou, Udaya Ghai, Dean Foster, Sham M. Kakade
- Published: 22 Jan 2025, Last Modified: 23 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Actionable Inverse Classification with Action Fairness Guarantees
Kemal Kirtac
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
Vibhhu Sharma, Bryan Wilder
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
The logic of rational graph neural networks
Sammy Khalife
- 26 Sept 2024 (modified: 18 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning DAGs and Root Causes from Time-Series Data
Panagiotis Misiakos, Markus Püschel
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MAD-Sherlock: Multi-Agent Debates for Out-of-Context Misinformation Detection
Kumud Lakara, Juil Sock, Christian Rupprecht, Philip Torr, John Collomosse, Christian Schroeder de Witt
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Reshaping Model Output Space Via Deep Kernel Density Estimation Networks
Lior Katz, Tomer Melamed
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Federated Granger Causality Learning For Interdependent Clients With State Space Representation
Ayush Mohanty, Nazal Mohamed, Paritosh Ramanan, Nagi Gebraeel
- Published: 22 Jan 2025, Last Modified: 18 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Improving Source Extraction with Diffusion and Consistency Models
Tornike Karchkhadze, Mohammad Rasool Izadi, Shuo Zhang
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Convex Formulations for Training Two-Layer ReLU Neural Networks
Karthik Prakhya, Tolga Birdal, Alp Yurtsever
- Published: 22 Jan 2025, Last Modified: 07 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
On Temperature Scaling and Conformal Prediction of Deep Classifiers
Lahav Dabah, Tom Tirer
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Steering Language Models with Activation Engineering
Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J Vazquez, Ulisse Mini, Monte MacDiarmid
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Optimizing Learning for Robust Hyperbolic Deep Learning in Computer Vision
Ahmad Bdeir, Niels Landwehr
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Beyond Linear Approximations: A Novel Pruning Approach for Attention Matrix
Yingyu Liang, Jiangxuan Long, Zhenmei Shi, Zhao Song, Yufa Zhou
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Closed-Form Merging of Parameter-Efficient Modules for Federated Continual Learning
Riccardo Salami, Pietro Buzzega, Matteo Mosconi, Jacopo Bonato, Luigi Sabetta, Simone Calderara
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Towards a Unified and Verified Understanding of Group-Operation Networks
Wilson Wu, Louis Jaburi, jacob drori, Jason Gross
- Published: 22 Jan 2025, Last Modified: 11 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
A Unified Causal Framework for Auditing Recommender Systems for Ethical Concerns
Vibhhu Sharma, Shantanu Gupta, Nil-Jana Akpinar, Zachary Chase Lipton, Liu Leqi
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone