IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks

[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Pytorch Code for "[CVPR24, TPAMI25] LEGaussians: Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding"

[CVPR 2024 🔥] Grounding Large Multimodal Model (GLaMM), the first-of-its-kind model capable of generating natural language responses that are seamlessly integrated with object segmentation masks.