Stars
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Janus-Series: Unified Multimodal Understanding and Generation Models
DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.
Exocompilation for productive programming of hardware accelerators
An optimized neural network operator library for chips base on Xuantie CPU.
[CVPR 2025] UniScene: Unified Occupancy-centric Driving Scene Generation
AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。
AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
HE-Drive: Human-Like End-to-End Driving with Vision Language Models
An implementation of EMMA (End-to-End Multimodal Model for Autonomous Driving) using the Claude API, based on the EMMA paper.
Bridging Large Vision-Language Models and End-to-End Autonomous Driving
[ECCV 2024] This is the official implementation of PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer
[IEEE T-PAMI 2024] All you need for End-to-end Autonomous Driving
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
[TPAMI 2025 & CVPR 2023] IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching
[ECCV 2024] The official implementation of DualBEV
[NeurIPS 2024] Official code of ”LION: Linear Group RNN for 3D Object Detection in Point Clouds“
【CVPR 2024】Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving