Publications

960 results for Trustworthy AI

DOES YOUR MODEL UNDERSTAND GENES? A MODALITY-AGNOSTIC BENCHMARK OF GENE PROPERTIES
- - Yoav Kan-Tor
  - Michael Morris Danziger
  - et al.
- 2025
- ISMB 2025
Poster
Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts
- - Mateo Espinosa Zarlenga
  - Gabriele Dominici
  - et al.
- 2025
- ICML 2025
Conference paper
ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
- - Alec Helbling
  - Tuna Meral
  - 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
Position: Theory of Mind Benchmarks are Broken for Large Language Models
- - Matthew Riemer
  - Zahra Ashktorab
  - et al.
- 2025
- ICML 2025
Conference paper
A Unified Framework for Generative AI Safety
- - Pin-Yu Chen
- 2025
- ICML 2025
Invited talk
Rethinking Unlearning for Large Reasoning Models Download PDF
- - Changsheng Wang
  - Chongyu Fan
  - 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
ST-WEBAGENTBENCH: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- - Ido Levy
  - Ben Wiesel
  - 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