Publications

Position: Theory of Mind Benchmarks are Broken for Large Language Models
- - Matthew Riemer
  - Zahra Ashktorab
  - et al.
- 2025
- ICML 2025
Conference paper
ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Tasks
- - Saurabh Jha
  - Rohan Arora
  - et al.
- 2025
- ICML 2025
Conference paper
Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- - Changsheng Wang
  - Yihua Zhang
  - et al.
- 2025
- ICML 2025
Conference paper
LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
- - Chen-chia Chang
  - Wan-hsuan Lin
  - et al.
- 2025
- ICML 2025
Conference paper
SPRI: Aligning Large Language Models with Context-Situated Principles
- - Hongli Zhan
  - Muneeza Azmat
  - et al.
- 2025
- ICML 2025
Conference paper
A Hitchhiker's Guide to Scaling Law Estimation
- - Leshem Choshen
  - Yang Zhang
  - et al.
- 2025
- ICML 2025
Conference paper
Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding
- - Ziyao Wang
  - Muneeza Azmat
  - et al.
- 2025
- ICML 2025
Conference paper
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
- - Zhining Liu
  - Ze Yang
  - et al.
- 2025
- ICML 2025
Conference paper
Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations
- - Jeet Mohapatra
  - Nima Dehmamy
  - et al.
- 2025
- ICML 2025
Conference paper
Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search
- - Maohao Shen
  - Guangtao Zeng
  - et al.
- 2025
- ICML 2025
Conference paper