Pavlo Molchanov
发表论文 147 篇 · 总被引 15668 次 · h-index 50
代表论文
- GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization (2026 · arXiv.org · 被引 130)
- Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning (2026 · 被引 19)
- Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning (2026 · 被引 10)
- C-RADIOv4 (Tech Report) (2026 · arXiv.org · 被引 8)
- Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding (2026 · 被引 8)
- Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence (2026 · arXiv.org · 被引 8)