🔄 In a Training Loop

Constantin

Alexandre-Numind

·

https://www.numind.ai/

AI & ML interests

Training AI models @Numind

Recent Activity

upvoted a paper 4 days ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

upvoted a paper 4 days ago

On-Policy Self-Distillation without Any Supervision

liked a model 11 days ago

numind/NuExtract3-GGUF

View all activity

Organizations

upvoted 2 papers 4 days ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

Paper • 2608.03573 • Published 11 days ago • 52

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 8 days ago • 204

liked a model 11 days ago

numind/NuExtract3-GGUF

Image-Text-to-Text • 4B • Updated May 20 • 4.73k • 37

upvoted a paper 14 days ago

Beacon: Knowing When and How to Perform Agentic Visual Reasoning

Paper • 2607.28595 • Published 18 days ago • 55

liked a Space about 1 month ago

GLAM Extraction Leaderboard

GLAM document extraction leaderboard (POC)

upvoted a paper about 1 month ago

DOPD: Dual On-policy Distillation

Paper • 2606.30626 • Published Jun 29 • 114