BAAI-DCAI

Bunny. A family of lightweight multimodal models.

M3D. M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models

SegVol. The official code for "SegVol: Universal and Interactive Volumetric Medical Image Segmentation".

SpatialBot. The official repo for "SpatialBot: Precise Spatial Understanding with Vision Language Models.

Visual-Instruction-Tuning. SVIT: Scaling up Visual Instruction Tuning

Dataset-Pruning. Dataset pruning for ImageNet and LAION-2B.

Training-Data-Synthesis. [ICLR 2024] Real-Fake: Effective Training Data Synthesis Through Distribution Matching

DataOptim. A collection of visual instruction tuning datasets.

MMVU. Python