Stars
A library for differentiable robotics on manifolds.
[ECCV 2024] Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting
[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields
Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
Official inference repo for FLUX.1 models
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
RoGs: Large Scale Road Surface Reconstruction with Meshgrid Gaussian
🚀 SnapTeX：本地离线运行的 Windows 截图识别神器！精准实现数学公式转 LaTeX 以及中英文混排 OCR。零配置、毫秒级响应、完全保护隐私，论文与笔记工作者的得力助手。
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
持续维护的企业面试题库网站，帮你拿到满意 offer！⭐️ 2026年最新Java面试题、前端面试题、AI大模型面试题、AI Agent面试题、RAG面试题、C++面试题、Go面试题、Python面试题、测试面试题、运维面试题、后端面试题、操作系统面试题、计算机网络面试题、Redis面试题、MySQL数据库面试题、算法面试题、Spring面试题、JVM面试题、Java并发面试题、Linux面…
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
[CVPR 2026 Highlight, the CVPR Compute Gold Star] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"
[GDGS] A real-time 3D Gaussian Splatting (3DGS) rendering plugin for the Godot Engine. Godot引擎的实时3DGS渲染插件
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
Dexbotic: Open-Source Vision-Language-Action Toolbox
This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.
[AAAI 2026] OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
An implementation of DashGaussian, a powerful 3DGS training acceleration method. Accepted by CVPR 2025 (highlight).
[CVPR 2025 Oral & Best Paper Finalist] Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models
Sample codes for my CUDA programming book
校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。