A. Das

AaravDasje

4

·

AI & ML interests

Gardening and gradient descent

Recent Activity

upvoted a paper 18 days ago

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

upvoted a paper 18 days ago

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

updated a model 24 days ago

AaravDasje/cnn-transformer-matching-v3

View all activity

Organizations

None yet

upvoted 2 papers 18 days ago

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

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

Paper • 2609.39102 • Published 28 days ago • 235

upvoted a paper 24 days ago

GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis

Paper • 2609.38923 • Published 28 days ago • 78

upvoted a paper about 2 months ago

AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing

Paper • 2609.08936 • Published Sep 8 • 155