Yuandong Tian
tydsh
AI & ML interests
Reinforcement Learning, Optimization, Representation Learning
Recent Activity
authored
a paper
12 days ago
Deep Think with Confidence
authored
a paper
6 months ago
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning
Tasks
authored
a paper
7 months ago
Token Assorted: Mixing Latent and Text Tokens for Improved Language
Model Reasoning
Organizations
None yet