Pari

PariKuhj

4 7

·

AI & ML interests

Into NLP, diffusion models and AI agents.

Recent Activity

upvoted a paper 5 days ago

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

upvoted a paper 5 days ago

Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

upvoted a paper 5 days ago

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

View all activity

Organizations

None yet

upvoted 3 papers 5 days ago

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

Paper • 2609.36484 • Published 16 days ago • 562

Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

Paper • 2610.12421 • Published 7 days ago • 44

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

Paper • 2609.39102 • Published 15 days ago • 664

upvoted a paper about 1 month ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published Sep 9 • 146