Sifei Liu

Latest

• 4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation
• OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM
• Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
• GroPrompt: Efficient Grounded Prompting and Adaptation for Referring Video Object Segmentation