Throughout the past few years, I’ve had the privilege to attend quite a few talks, especially via RAiD.
Here is an exhaustive list of all the talks I have attended that are documented here:
| Title of Talk | Speaker | Venue(s) |
|---|---|---|
| Towards Building Safe and Secure AI: Lessons & Open Challenges | Prof Dawn Song @ UC Berkeley | LM Safety Workshop 2025, ICLR 2025 |
| Can We Provide Formal Guarantees for LLM Safety? | Prof Gagandeep Singh @ UIUC | LM Safety Workshop 2025 |
| Large Model Safety: The Narrow Path between Cavalier Building and Paralyzing Fear | Prof Christopher Manning @ Stanford | LM Safety Workshop 2025 |
| Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? | Prof Yoshua Bengio @ University of Montreal | LM Safety Workshop 2025, ICLR 2025 |
| Building Safe and Robust AI Systems | Prof Zico Kolter @ CMU | ICLR 2025 |