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
published a dataset about 6 hours ago
Rob1234567/ariadna-cpt-corpus updated a model about 11 hours ago
Rob1234567/qwen3.5-4b-ariadna-grpo-v1 published a model about 20 hours ago
Rob1234567/qwen3.5-4b-ariadna-grpo-v1Organizations
None yet