AI.info

Hanrong Ye

Explore Hanrong Ye on AI.info.

• Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
• GSPN-2: Efficient Parallel Sequence Modeling
• ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
• QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs