दिव्या गुप्ता

punemehta

·

AI & ML interests

Learning ML every day. Love open source and cool models.

Recent Activity

liked a Space 6 days ago

YuyaoTechnology/MatterSeek

new activity 8 days ago

YuyaoTechnology/MatterSeek-New-Materials-Reverse-Design:Units are tiny details until they aren't

liked a model 8 days ago

YuyaoTechnology/MatterSeek-New-Materials-Reverse-Design

View all activity

Organizations

None yet

upvoted a paper 27 days ago

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

Paper • 2610.19789 • Published 29 days ago • 43

upvoted 2 papers about 1 month ago

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

Paper • 2609.39102 • Published Sep 30 • 150

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

Paper • 2609.36484 • Published Sep 29 • 168

upvoted a paper about 2 months ago

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

Paper • 2609.29845 • Published Sep 24 • 89