Justin Wang

Justin6657's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 20 days ago

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published 23 days ago • 38

Learning from Teacher Continuations at Student States

Paper • 2609.36246 • Published 22 days ago • 41

upvoted a paper 9 months ago

Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Paper • 2602.01058 • Published Feb 1 • 45