😍
Out sick
Stars
multimodal
6 repositories
Tracking and collecting papers/projects/others related to Segment Anything.
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
LAVIS - A One-stop Library for Language-Vision Intelligence
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系,成为中文AIGC和认知智能的基础设施。