Tianqing Li's starred repositories
llm-course
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Grounded-Segment-Anything
Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
MotionDiffuse
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
DynamicViT
[NeurIPS 2021] [T-PAMI] DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
MultiBench
[NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning
AmadeusGPT
[NeurIPS 2023] We turn natural language descriptions of behaviors into machine-executable code
3D-deformable-attention
[ICCV 2023] Official implementation of the paper "DFA3D: 3D Deformable Attention For 2D-to-3D Feature Lifting"
SlotFormer
Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models
Pose-Segment-Anything
Marrying Pose Estimation model with Segment Anything & Stable Diffusion, Automatically Joint Detection , Segment and edit any part of your body.
context_general_bci
Towards large neural data models.