Publications

38 results at ICML 2025

SPRI: Aligning Large Language Models with Context-Situated Principles
- - Hongli Zhan
  - Muneeza Azmat
  - et al.
- 2025
- ICML 2025
Conference paper
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
- - Mateo Espinosa Zarlenga
  - Gabriele Dominici
  - et al.
- 2025
- ICML 2025
Conference paper
A Unified Framework for Generative AI Safety
- - Pin-Yu Chen
- 2025
- ICML 2025
Invited talk
Open-source federated learning across multi cloud environment
- - Leonardo P. Tizzei
  - Gabby Nyirjesy
  - et al.
- 2025
- ICML 2025
Workshop paper
Dropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
- - Jenny Yijian Huang
  - Yunyi Shen
  - et al.
- 2025
- ICML 2025
Workshop paper
ST-WEBAGENTBENCH: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- - Ido Levy
  - Ben Wiesel
  - et al.
- 2025
- ICML 2025
Workshop paper
Control Flow Operators in PyTorch
- - Yidi Wu
  - Thomas Bohnstingl
  - et al.
- 2025
- ICML 2025
Workshop paper
MAD-MAX: Modular And Diverse Malicious AttackMiXtures for Automated LLM Red Teaming
- - Stefan Schoepf
  - Muhammad Zaid Hameed
  - et al.
- 2025
- ICML 2025
Workshop paper
In-Context Bias Propagation in LLM-Based Tabular Data Generation
- - Pol Garcia Recasens
  - Alberto Gutierrez-torre
  - et al.
- 2025
- ICML 2025
Workshop paper
Learning interpretable positional encodings in transformers depends on initialization
- - Taku Ito
  - Luca Cocchi
  - et al.
- 2025
- ICML 2025
Workshop paper