ICLR 2025 Conference Submissions

Near-Exact Privacy Amplification for Matrix Mechanisms
Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque, Thomas Steinke, Abhradeep Guha Thakurta
- Published: 22 Jan 2025, Last Modified: 26 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
LOCAL: Latent Orthonormal Contrastive Learning for Paired Images
Fei Dou, Jin Lu, Tan Zhu, Jinbo Bi
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
PROVABLY EFFICIENT FEDERATED ACTIVE MULTI-TASK REPRESENTATION LEARNING
Jiabin Lin, Shana Moothedath, Tuan Anh Le
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Zero redundancy distributed learning with differential privacy
Zhiqi Bu, Ruixuan Liu, Justin Chiu, Sheng Zha, George Karypis
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Tensor-GaLore: Memory-Efficient Training via Gradient Tensor Decomposition
Robert Joseph George, David Pitt, Jiawei Zhao, Jean Kossaifi, Cheng Luo, Yuandong Tian, Anima Anandkumar
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers
Yingyu Liang, Heshan Liu, Zhenmei Shi, Zhao Song, Zhuoyan Xu, Junze Yin
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
Hsun-Yu Kuo, Yin-Hsiang Liao, Yu-Chieh Chao, Wei-Yun Ma, Pu-Jen Cheng
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy, Mirza Sanjida Alam, Hengbo Tong, Swarna Das, Earl T. Barr, Wei Le
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Building Reliable Conditional Diffusion Models for Protein Generation
Zinan Ling, Bo Hui, Yi Shi, Da Yan
- 26 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning a Bi-directional Driving Data Generator via Large Multi-modal Model Tuning
Xinzhi Zhong, Andrew Silva, Pradyumna Tambwekar, Jonathan DeCastro, Soyoung Ahn, Guy Rosman
- 26 Sept 2024 (modified: 27 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Test-Time Alignment via Hypothesis Reweighting
Yoonho Lee, Jonathan Williams, Henrik Marklund, Archit Sharma, Eric Mitchell, Anikait Singh, Chelsea Finn
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Improving Semantic Understanding in Speech Language Models via Brain-tuning
Omer Moussa, Dietrich Klakow, Mariya Toneva
- Published: 22 Jan 2025, Last Modified: 18 May 2025
- ICLR 2025 Poster
- Readers: Everyone
BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments
Xinghao Wang, Pengyu Wang, Bo Wang, Dong Zhang, Yunhua Zhou, Xipeng Qiu
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Perlin Noise for Exploration in Reinforcement Learning
Dominik Roth, Onur Celik, Fabian Otto, Gerhard Neumann
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
ACES: Automatic Cohort Extraction System for Event-Stream Datasets
Justin Xu, Jack Gallifant, ALISTAIR JOHNSON, Matthew B.A. McDermott
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Memorization and the Orders of Loss: A Learning Dynamics Perspective
Deepak Ravikumar, Efstathia Soufleri, Abolfazl Hashemi, Kaushik Roy
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Inference-Friendly Models With MixAttention
Shashank Rajput, Ying Sheng, Sean Owen, Vitaliy Chiley
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
Zihan Zhang, Xiangyang Ji, Yuan Zhou
- Published: 22 Jan 2025, Last Modified: 02 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Systems with Switching Causal Relations: A Meta-Causal Perspective
Moritz Willig, Tim Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting
- Published: 22 Jan 2025, Last Modified: 16 May 2025
- ICLR 2025 Spotlight
- Readers: Everyone
pMixFed: Mixing up model coefficients for Efficient Personalized Federated Learning
Yasaman Saadati, Mohammad Rostami, M. Hadi Amini
- 26 Sept 2024 (modified: 01 Nov 2024)
- ICLR 2025 Conference Desk Rejected Submission
- Readers: Everyone
FairlyUncertain: A Comprehensive Benchmark of Uncertainty in Algorithmic Fairness
Lucas Rosenblatt, R. Teal Witter
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
Hongkang Li, Yihua Zhang, Shuai Zhang, Pin-Yu Chen, Sijia Liu, Meng Wang
- Published: 22 Jan 2025, Last Modified: 17 May 2025
- ICLR 2025 Oral
- Readers: Everyone
Provably Efficient Linear Bandits with Instantaneous Constraints in Non-Convex Feature Spaces
Amirhossein Roknilamouki, Ming Shi, Fatemeh Nourzad, Eylem Ekici, Arnob Ghosh, Ness Shroff
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Generalization and Knowledge Transfer in Abstract Visual Reasoning Models
Mikołaj Małkiński, Jacek Mańdziuk
- 26 Sept 2024 (modified: 19 Jan 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Bandits with Anytime Knapsacks
Eray Can Elumar, Cem Tekin, Osman Yagan
- 26 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone