Manoj Devi

manojdevi

4 4

·

AI & ML interests

Self-taught ML practitioner. Coffee-driven.

Recent Activity

liked a Space 4 days ago

salaz055/ImageSegmentationTest

liked a model 4 days ago

Edge0/Audio8-ASR-Infinite

upvoted a paper 4 days ago

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

View all activity

Organizations

None yet

upvoted 2 papers 4 days ago

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

Paper • 2609.36484 • Published 6 days ago • 501

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

Paper • 2609.39102 • Published 5 days ago • 431

upvoted 2 papers 16 days ago

Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model

Paper • 2609.18323 • Published 19 days ago • 133

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published 20 days ago • 815