OmniMamba: Efficient and Unified Multimodal Understanding and Generation via State Space Models

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

The first decoder-only multimodal state space model

This repository give a guidline to learn CUDA and TensorRT from the beginning.

project page of "RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning"

[CVPR 2025] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models

[CVPR 2025] Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

(TPAMI 2024) A Survey on Open Vocabulary Learning

Official implementation of CVPR24 Highlight paper "Open-vocabulary object 6D pose estimation"

Bridging Large Vision-Language Models and End-to-End Autonomous Driving

[ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models

Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream [CVPR2024]

Free and Open Source, Distributed, RESTful Search Engine

Open source RabbitMQ: core server and tier 1 (built-in) plugins

🚌 The IK Analysis plugin integrates Lucene IK analyzer into Elasticsearch and OpenSearch, support customized dictionary.

Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"

📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

Several simple examples for popular neural network toolkits calling custom CUDA operators.

[CVPR 2025] DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention

[AAAI 2025] Linear-complexity Visual Sequence Learning with Gated Linear Attention

A Framework of Small-scale Large Multimodal Models

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

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

LAVIS - A One-stop Library for Language-Vision Intelligence

SAM with text prompt

[CVPR 2024] Code for "Improving the Generalization of Segmentation Foundation Model under Distribution Shift via Weakly Supervised Adaptation"