Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker/Zotero

Autonomous agents for everyone

stock股票.获取股票数据,计算股票指标,筹码分布,识别股票形态,综合选股,选股策略,股票验证回测,股票自动交易,支持PC及移动设备。

Agno is a lightweight framework for building multi-modal Agents

KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Real-time dense scene reconstruction with SLAM3R

Official implementation of "DepthLab: From Partial to Complete"

4DS BetterDepth Buffer Anytime ChronoDepth Depth Any Video Depth Anything Depth Pro DepthCrafter DINOv2 FutureDepth GenPercept GeoWizard LightedDepth Marigold Metric3D MiDaS MoGe MonST3R NeWCRFs NV…

HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction

[Arxiv'24] LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding

Code for MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

[AAAI 2025] Offical implementation of "DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input"

A generative world for general-purpose robotics & embodied AI learning.

Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving

A minimal and universal controller for FLUX.1.

MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM

Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"

On the Road with GPT-4V(ision): Early Explorations of Visual-Language Model on Autonomous Driving

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

3D Edge Mapping using Edge-Specialized Gaussian Splatting

Official repository for "SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE"

[RA-L2024/ICRA2025] Official implementation for paper "Diverse Controllable Diffusion Policy with Signal Temporal Logic."

pySLAM is a visual SLAM pipeline in Python for monocular, stereo and RGBD cameras. It supports many modern local and global features, different loop-closing methods, a volumetric reconstruction pip…