Shaobai Jiang
shaobaij
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 14 hours ago
Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual
Post-Training
upvoted
a
paper
about 19 hours ago
SWE-Universe: Scale Real-World Verifiable Environments to Millions
upvoted
a
paper
about 19 hours ago
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
Organizations
None yet