linjc16/TrialAlign
Viewer
•
Updated
•
1.72M
•
11
•
2
Jiacheng Lin
linjc16
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 18 hours ago
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific
Fine-Tuning in LLMs
upvoted
a
paper
about 23 hours ago
Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning
upvoted
a
paper
14 days ago
Agentic Reasoning for Large Language Models
Organizations
