Learning interpretable positional encodings in transformers depends on initialization
- Taku Ito
- Luca Cocchi
- et al.
- 2025
- ICML 2025
Workshop paper
Publications
934 results for Trustworthy AI
MAD-MAX: Modular And Diverse Malicious AttackMiXtures for Automated LLM Red Teaming
- Stefan Schoepf
- Muhammad Zaid Hameed
- et al.
- 2025
- ICML 2025
Workshop paperST-WEBAGENTBENCH: A Benchmark for Evaluating Safety and Trustworthiness in Web Agents
- Ido Levy
- Ben Wiesel
- et al.
- 2025
- ICML 2025
Workshop paperIn-Context Bias Propagation in LLM-Based Tabular Data Generation
- Pol Garcia Recasens
- Alberto Gutierrez-torre
- et al.
- 2025
- ICML 2025
Workshop paperRethinking Unlearning for Large Reasoning Models Download PDF
- Changsheng Wang
- Chongyu Fan
- et al.
- 2025
- ICML 2025
Workshop paperNoisy But Forgotten: LLM Unlearning are Robust against Perturbed Data in the Wild
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- ICML 2025
Workshop paperDropping Just a Handful of Preferences Can Change Top Large Language Model Rankings
- Jenny Yijian Huang
- Yunyi Shen
- et al.
- 2025
- ICML 2025
Workshop paperPredicting Glucose Levels in Diabetic Kidney Transplant Recipients Using Multivariate Temporal Modeling Across Clinically Defined Subcohorts
- Carla Agurto
- Eduardo Castro
- et al.
- 2025
- ICDH 2025
Conference paperVoice-based AI Agents: Filling the Economic Gaps in Digital Health Delivery
- Bo Wen
- Chen Wang
- et al.
- 2025
- ICDH 2025
Invited talkHumble AI in the real-world: the case of algorithmic hiring
- Rahul Nair
- Inge Vejsbjerg
- et al.
- 2025
- CHIWORK 2025
Conference paper