AI.info

Jiayi Ji

Explore Jiayi Ji on AI.info.

• MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation
• Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
• JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
• MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification
• GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification