Roman Nekrasov
Rob1234567
AI & ML interests
Areas of interest: agentic mid-training, reinforcement learning with reward verification (RLVR), scaling agent environments, interleaved agent reasoning with tools
Recent Activity
liked
a model
about 5 hours ago
Qwen/Qwen3-Coder-30B-A3B-Instruct
liked
a model
3 days ago
google/medasr
upvoted
a
collection
3 days ago
MedGemma Release
Organizations
None yet