ICLR 2025 Conference Submissions

2-Rectifications are Enough for Straight Flows: A Theoretical Insight into Wasserstein Convergence
Saptarshi Roy, Vansh Bansal, Purnamrita Sarkar, Alessandro Rinaldo
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Watermark Smoothing Attacks against Language Models
Hongyan Chang, Hamed Hassani, Reza Shokri
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Understanding Contrastive Learning through Variational Analysis and Neural Network Optimization Perspectives
Jeff Calder, Wonjun Lee
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CulturalBench: a Robust, Diverse and Challenging Benchmark on Measuring (the Lack of) Cultural Knowledge of LLMs
Yu Ying Chiu, Liwei Jiang, Bill Yuchen Lin, Chan Young Park, Shuyue Stella Li, Sahithya Ravi, Mehar Bhatia, Maria Antoniak, Yulia Tsvetkov, Vered Shwartz, Yejin Choi
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Declarative characterizations of direct preference alignment algorithms
Kyle Richardson, Vivek Srikumar, Ashish Sabharwal
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images
Sichen Zhu, Yuchen Zhu, Molei Tao, Peng Qiu
- Published: 22 Jan 2025, Last Modified: 09 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Diffusion State-Guided Projected Gradient for Inverse Problems
Rayhan Zirvi, Bahareh Tolooshams, Anima Anandkumar
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Variational Neuro-Symbolic Generative Temporal Point Process
Chao Yang, Yang Yang, Wendi Ren, Shuang Li
- 28 Sept 2024 (modified: 25 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
MADGEN: Mass-Spec attends to De Novo Molecular generation
Yinkai Wang, Xiaohui Chen, Liping Liu, Soha Hassoun
- Published: 22 Jan 2025, Last Modified: 28 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Interpreting neural networks depends on the level of abstraction: Revisiting modular addition
Gavin McCracken, Gabriela Moisescu-Pareja, Vincent Létourneau, Doina Precup, Jonathan Love
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning
Ming Li, Pei Chen, Chenguang Wang, Hongyu Zhao, Yijun Liang, YuPeng Hou, Fuxiao Liu, Tianyi Zhou
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Solving Normalized Cut Problem with Constrained Action Space
Qize Jiang, Linsey Pang, Alice Gatti, Mahima Aggarwal, Giovanna Vantini, Xiaosong Ma, Weiwei Sun, Sanjay Chawla
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Towards Federated RLHF with Aggregated Client Preference for LLMs
Feijie Wu, Xiaoze Liu, Haoyu Wang, Xingchen Wang, Lu Su, Jing Gao
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SIG: Self-Interpretable Graph Neural Network for Continuous-time Dynamic Graphs
Lanting Fang, Yulian Yang, Kai Wang, Shanshan Feng, Kaiyu Feng, Jie Gui, Hanning Yuan, Yew-Soon Ong
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Overcoming Slow Decision Frequencies in Continuous Control: Model-Based Sequence Reinforcement Learning for Model-Free Control
Devdhar Patel, Hava T Siegelmann
- Published: 22 Jan 2025, Last Modified: 14 May 2025
- ICLR 2025 Poster
- Readers: Everyone
CAD-Editor: Text-based CAD Editing through Adapting Large Language Models with Synthetic Data
Yu Yuan, Shizhao Sun, Qi Liu, Jiang Bian
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DATASEA - AN AUTOMATIC FRAMEWORK FOR COMPREHENSIVE DATASET PROCESSING USING LARGE LANGUAGE MODELS
Yang Xiang, Xinye Yang, Yanghao Wu
- 28 Sept 2024 (modified: 01 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Physics of Language Models: Part 3.2, Knowledge Manipulation
Zeyuan Allen-Zhu, Yuanzhi Li
- Published: 22 Jan 2025, Last Modified: 12 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Logic-Logit: A Logic-Based Approach to Choice Modeling
Shuhan Zhang, Wendi Ren, Shuang Li
- Published: 22 Jan 2025, Last Modified: 12 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
A Neural Architecture Dataset for Adversarial Robustness
Bowen Zheng, Ran Cheng, Shihua Huang, Zhichao Lu, Vishnu Boddeti
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Interpretability of Language Models for Learning Hierarchical Structures
Zeyuan Allen-Zhu, Yuanzhi Li
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Inference of Evolving Mental States from Irregular Action Events to Understand Human Behaviors
Chao Yang, Shuting Cui, Yang Yang, Shuang Li
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On the Local Complexity of Linear Regions in Deep ReLU Networks
Niket Nikul Patel, Guido Montufar
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Task Facet Learning: A Structured Approach to Prompt Optimization
Gurusha Juneja, Gautam Jajoo, Hua Li, Jian Jiao, Nagarajan Natarajan, Amit Sharma
- 28 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Physics of Language Models: Part 3.3, Knowledge Capacity Scaling Laws
Zeyuan Allen-Zhu, Yuanzhi Li
- Published: 22 Jan 2025, Last Modified: 12 May 2025
- ICLR 2025 Spotlight
- Readers: Everyone