Tao Sun
Home
Research
Publications
Updates
Contact
Reasoning
ARC: A Reasoning Recipe for Robot Foundation Models
Action-grounded causal reasoning improves robot foundation models using automatically labeled existing demonstrations.
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
Scaling reasoning through reinforcement learning, with advances in training data, reward modeling, algorithms, and distributed infrastructure.
Cite
×