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 1 day ago
deepseek-ai/DeepSeek-V4-Flash upvoted a collection 2 months ago
Gemma 4 liked a model 2 months ago
Qwen/Qwen3.5-9BOrganizations
None yet