Deepak Kumar

kkumardeepak8

6 1

AI & ML interests

Into NLP, diffusion models and AI agents.

Recent Activity

liked a model 11 days ago

YuyaoTechnology/MatterSeek-New-Materials-Reverse-Design

upvoted a paper 11 days ago

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

upvoted a paper about 1 month ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

View all activity

Organizations

None yet

liked a model 11 days ago

YuyaoTechnology/MatterSeek-New-Materials-Reverse-Design

Text Generation • Updated about 15 hours ago • 2.92k

upvoted a paper 11 days ago

Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents

Paper • 2611.02075 • Published 15 days ago • 83

upvoted a paper about 1 month ago

LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketches

Paper • 2610.06647 • Published Oct 5 • 35

updated a model about 2 months ago

kkumardeepak8/vit-matching

24.8k • Updated Oct 1 • 6

published a model about 2 months ago

kkumardeepak8/vit-matching

24.8k • Updated Oct 1 • 6

upvoted 3 papers about 2 months 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 • 169

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

Paper • 2609.17488 • Published Sep 15 • 271

upvoted a paper 2 months ago

Does On-Policy Distillation Really Distill? From Noisy Teacher to Self-Improvement

Paper • 2608.31046 • Published Aug 31 • 85

updated a model 3 months ago

kkumardeepak8/embedding

Updated Aug 25

published a model 3 months ago