Lulu Tang

SpaceR. SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

dust3r. DUSt3R: Geometric 3D Vision Made Easy

Awesome-LLM-3D. Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources

Swin3D_Task. The Experiment Code for Swin3D

See3D. [CVPR'25 Highlight] You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

LLM101n. LLM101n: Let's build a Storyteller

big_vision. Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

tokenize-anything. [ECCV 2024] Tokenize Anything via Prompting

3DTrans. An open-source codebase for exploring autonomous driving pre-training

Point-BERT. [CVPR 2022] Pre-Training 3D Point Cloud Transformers with Masked Point Modeling

RSPrompter. This is the pytorch implement of our paper "RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model"

samexporter. Exporting Segment Anything, MobileSAM, and Segment Anything 2 into ONNX format for easy deployment

Matcher. [ICLR'24 & IJCV‘25] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

OpenPCDet. OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

MDE-SpikingCamera. [ECCV2022] Spike Transformer: Monocular Depth Estimation for Spiking Camera