Publications

37 results at ICML 2025

Regress, Don't Guess: A Regression-like Loss on Number Tokens for Language Models
- - Jonas Zausinger
  - Lars Pennig
  - et al.
- 2025
- ICML 2025
Aligning Protein Conformation Ensemble Generation with Physical Feedback
- - Jiarui Lu
  - Xiaoyin Chen
  - et al.
- 2025
- ICML 2025
A Unified Framework for Generative AI Safety
- - Pin-Yu Chen
- 2025
- ICML 2025
Learning interpretable positional encodings in transformers depends on initialization
- - Taku Ito
  - Luca Cocchi
  - et al.
- 2025
- ICML 2025
Representing Prompting Patterns with PDL: Compliance Agent Case Study
- - Mandana Vaziri
  - Louis Mandel
  - et al.
- 2025
- ICML 2025
MAD-MAX: Modular And Diverse Malicious AttackMiXtures for Automated LLM Red Teaming
- - Stefan Schoepf
  - Muhammad Zaid Hameed
  - et al.
- 2025
- ICML 2025
Noisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
- - Changsheng Wang
  - Yihua Zhang
  - et al.
- 2025
- ICML 2025
Modeling Human Behavior Without Humans: Prospect Theoretic Multi-Agent Reinforcement Learning
- - Sheyan Lalmohammed
  - Khush Gupta
  - et al.
- 2025
- ICML 2025
Control Flow Operators in PyTorch
- - Yidi Wu
  - Thomas Bohnstingl
  - et al.
- 2025
- ICML 2025
Rethinking Unlearning for Large Reasoning Models Download PDF
- - Changsheng Wang
  - Chongyu Fan
  - et al.
- 2025
- ICML 2025