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
updated a model 1 day ago
Rob1234567/qwen3.5-4b-ariadna-grpo-v1-gguf updated a model 1 day ago
Rob1234567/qwen3.5-4b-ariadna-grpo-v1 published a model 3 days ago
Rob1234567/qwen3.5-4b-ariadna-grpo-v1-ggufOrganizations
None yet
Inquiry regarding Banking Domain data mentioned in Nemotron 3 Nano Paper (arXiv:2512.20848, p. 17)
#4 opened 6 months ago
by Rob1234567