Publications

38 results at ICML 2025

Learning interpretable positional encodings in transformers depends on initialization
- - Taku Ito
  - Luca Cocchi
  - et al.
- 2025
- ICML 2025
Control Flow Operators in PyTorch
- - Yidi Wu
  - Thomas Bohnstingl
  - 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
ST-WEBAGENTBENCH: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- - Ido Levy
  - Ben Wiesel
  - 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
Representing Prompting Patterns with PDL: Compliance Agent Case Study
- - Mandana Vaziri
  - Louis Mandel
  - et al.
- 2025
- ICML 2025
Workshop on Collaborative and Federated Agentic Workflows (CFAgentic @ ICML'25)
- - Alexander Erben
  - Gauri Joshi
  - et al.
- 2025
- ICML 2025
Modern Methods in Associative Memory
- - Dmitry Krotov
  - Benjamin Hoover
  - et al.
- 2025
- ICML 2025