Yuandong Tian
- AdvPrefix: An Objective for Nuanced LLM Jailbreaks
- Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
- NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
- ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization
- Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought