A. Shah

Shahayaan

5 5

·

AI & ML interests

Interested in machine learning, NLP and open source AI.

Recent Activity

upvoted a paper about 15 hours ago

LeWAM: End-to-End World and Action Modeling with JEPAs

upvoted a paper 13 days ago

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

upvoted a paper 13 days ago

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

View all activity

Organizations

None yet

upvoted a paper about 15 hours ago

LeWAM: End-to-End World and Action Modeling with JEPAs

Paper • 2610.12818 • Published 7 days ago • 64

upvoted 2 papers 13 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 • 561

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

Paper • 2609.39102 • Published 15 days ago • 664

upvoted 2 papers about 2 months ago

Self-OPD: On-Policy Distillation for Flow Matching Models without Teacher

Paper • 2608.26872 • Published Aug 27 • 57

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Paper • 2608.26105 • Published Aug 26 • 151