arxiv:2605.31159
Boris Shaposhnikov
borisshapa
AI & ML interests
NLP
Recent Activity
authored a paper 3 days ago
Trust-Region Behavior Blending for On-Policy Distillation upvoted a paper 12 days ago
Trust-Region Behavior Blending for On-Policy Distillation upvoted a paper 4 months ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the RareOrganizations
None yet
models 7
borisshapa/sft-llama3.1-8b-uch
8B • Updated • 3
borisshapa/ppo-4x-mistral-7b-smallsft-tldr
Text Generation • 7B • Updated • 3
borisshapa/ppo-2x-mistral-7b-smallsft-tldr
Text Generation • 7B • Updated • 2
borisshapa/ppo-8x-mistral-7b-smallsft-tldr
Text Generation • 7B • Updated • 2
borisshapa/sft-qwen2.5-0.5b-uf
Updated
borisshapa/rm-opt-350m-hs2
Text Generation • 0.3B • Updated • 4
borisshapa/sft-opt-350m-hs2
Text Generation • 0.3B • Updated • 2
datasets 0
None public yet