Samson Han

samsonhan's activity

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

upvoted 2 papers 17 days ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 28 days ago • 235

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

Paper • 2609.36484 • Published 29 days ago • 208

updated a model 19 days ago

samsonhan/multimodal-generation-beta

24.8k • Updated 19 days ago • 16

published a model 19 days ago

samsonhan/multimodal-generation-beta

24.8k • Updated 19 days ago • 16

upvoted a paper 19 days ago

STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization

Paper • 2609.38169 • Published 29 days ago • 157