दिव्या गुप्ता

punemehta's activity

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

upvoted a paper 1 day ago

More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning

Paper • 2610.19789 • Published 3 days ago • 83

upvoted 2 papers 15 days ago

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

Paper • 2609.39102 • Published 17 days ago • 665

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

Paper • 2609.36484 • Published 18 days ago • 564

upvoted a paper 20 days ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

Paper • 2609.29845 • Published 23 days ago • 105