← authors · overview

• Regiongpt: Towards Region Understanding Vision Language Model
  2024 · 48 citations
• LITA: Language Instructed Temporal-localization Assistant
  2024 · 35 citations
• Scaling Vision Pre-training To 4K Resolution
  2025 · 3 citations
• Nemotron 3 Nano Omni: Efficient And Open Multimodal Intelligence
  2026