ICLR 2025 Conference Submissions

DrugAgent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction and Repurposing
Yoshitaka Inoue, Tianci Song, Tianfan Fu, Augustin Luna
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Provable Convergence Bounds for Hybrid Dynamical Sampling and Optimization
Matthew X. Burns, Qingyuan Hou, Michael Huang
- Published: 22 Jan 2025, Last Modified: 06 May 2025
- ICLR 2025 Poster
- Readers: Everyone
Which Attention Heads Matter for In-Context Learning?
Kayo Yin, Jacob Steinhardt
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
CTSyn: A Foundation Model for Cross Tabular Data Generation
Xiaofeng Lin, Chenheng Xu, Matthew Yang, Guang Cheng
- Published: 22 Jan 2025, Last Modified: 03 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Learning from others' mistakes: Finetuning machine translation models with span-level error annotations
Lily H Zhang, Hamid Dadkhahi, Mara Finkelstein, Firas Trabelsi, Jiaming Luo, Markus Freitag
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Solving hidden monotone variational inequalities with surrogate losses
Ryan D'Orazio, Danilo Vucetic, Zichu Liu, Junhyung Lyle Kim, Ioannis Mitliagkas, Gauthier Gidel
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning
Jeffrey Olmo, Jared Wilson, Max Forsey, Bryce Hepner, Thomas Vincent Howe, David Wingate
- 27 Sept 2024 (modified: 07 Oct 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Stochastic Process Learning via Operator Flow Matching
Yaozhong Shi, Zachary E Ross, Domniki Asimaki, Kamyar Azizzadenesheli
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Long Tail Classification Through Cost Sensitive Loss Functions
Varad Shinde, Nikhil Kumar Shrey, SUBHAJIT SIDHANTA, Harshil Bhargava, Supratik Mukhopadhyay, Linta Islam, Yimin Zhu
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Investigating Factuality in Long-Form Text Generation: The Roles of Self-Known and Self-Unknown
Lifu Tu, Rui Meng, Shafiq Joty, Yingbo Zhou, Semih Yavuz
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Win Rate is All that Can Matter from Preference Data Alone
Lily H Zhang, Rajesh Ranganath
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
TorchTitan: One-stop PyTorch native solution for production ready LLM pretraining
Wanchao Liang, Tianyu Liu, Less Wright, Will Constable, Andrew Gu, Chien-Chin Huang, Iris Zhang, Wei Feng, Howard Huang, Junjie Wang, Sanket Purandare, Gokul Nadathur, Stratos Idreos
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
Reducing Symmetry Mismatch Caused by Freely Placed Cameras in Robotic Learning
David Klee, Dian Wang, Robert Platt, Robin Walters
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
On Gradient-Weight Alignment
Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
A Little Depth Goes a Long Way: the Expressive Power of Log-Depth Transformers
William Merrill, Ashish Sabharwal
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Chunk-Distilled Language Modeling
Yanhong Li, Karen Livescu, Jiawei Zhou
- Published: 22 Jan 2025, Last Modified: 16 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
When does compositional structure yield compositional generalization? A kernel theory.
Samuel Lippl, Kim Stachenfeld
- Published: 22 Jan 2025, Last Modified: 01 Apr 2025
- ICLR 2025 Poster
- Readers: Everyone
How To Evaluate Your Medical Time Series Classification?
Yihe Wang, Taida Li, Yujun Yan, WenZhan Song, Xiang Zhang
- 27 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
BadJudge: Backdoor Vulnerabilities of LLM-As-A-Judge
Terry Tong, Fei Wang, Zhe Zhao, Muhao Chen
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
System Aware Unlearning Algorithms: Use Lesser, Forget Faster
Linda Lu, Ayush Sekhari, Karthik Sridharan
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation
Song Wang, Zihan Chen, Peng Wang, Zhepei Wei, Zhen Tan, Yu Meng, Cong Shen, Jundong Li
- 27 Sept 2024 (modified: 16 Dec 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
WaveletGPT: Wavelet Inspired LLMs
Prateek Verma
- 27 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
The Value of Sensory Information to a Robot
Arjun Krishna, Edward S. Hu, Dinesh Jayaraman
- Published: 22 Jan 2025, Last Modified: 16 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Sensor-Invariant Tactile Representation
Harsh Gupta, Yuchen Mo, Shengmiao Jin, Wenzhen Yuan
- Published: 22 Jan 2025, Last Modified: 13 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
NutriBench: A Dataset for Evaluating Large Language Models in Nutrition Estimation from Meal Descriptions
Mehak Preet Dhaliwal, Andong Hua, Laya Pullela, Ryan Burke, Yao Qin
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone