Publications

3 results for Sarath Chandar

Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs
- - Megh Thakkar
  - Quentin Fournier
  - et al.
- 2025
- ACL 2025
A Generalist Hanabi Agent
- - Arjun Sudhakar
  - Hadi Nekoei
  - et al.
- 2025
- ICLR 2025
Combining Domain and Alignment Vectors to Achieve Better Knowledge-Safety Trade-offs in LLMs
- - Megh Thakkar
  - Yash More
  - et al.
- 2024
- NeurIPS 2024