Yuandong Tian's picture

4 1

Yuandong Tian

tydsh

·

https://yuandong-tian.com/

AI & ML interests

Reinforcement Learning, Optimization, Representation Learning

Recent Activity

authored a paper 3 days ago

Token Assorted: Mixing Latent and Text Tokens for Improved Language Model Reasoning

authored a paper 12 days ago

Towards General-Purpose Model-Free Reinforcement Learning

authored a paper 16 days ago

Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary Feedback

View all activity

Organizations

None yet

Papers 21

arxiv:2502.03275

arxiv:2501.16142

arxiv:2501.10799

arxiv:2412.06769

models

None public yet

datasets

None public yet