Lists (7)
Sort Name ascending (A-Z)
Stars
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
ODE Policy: Robot Learning via Action Dynamics, Not Actions (arXiv:2611.01729)
CantonMonkey / RLinf
Forked from RLinf/RLinfRLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
An Agentic Framework for Vision-Language Navigation
Reverse engineer anything with agents, from app behavior down to native binaries.
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
A Collection of LiDAR-Camera-Calibration Papers, Toolboxes and Notes
CUDA-accelerated visual odometry and SLAM library for fast, accurate, low-latency camera tracking
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
Robust LiDAR SLAM with a versatile plug-and-play loop closing and pose-graph optimization.
gisbi-kim / FAST_LIO_SLAM
Forked from hku-mars/FAST_LIOLiDAR SLAM = FAST-LIO + Scan Context
【RA-L 2026】 A Robust and Efficient LiDAR-Inertial Odometry System with a Compact Mapping Strategy.
[ICCV'25] GS-LIVM: Real-Time Photo-Realistic LiDAR-Inertial-Visual Mapping with Gaussian Splatting
SG-SLAM: A Real-Time RGB-D Visual SLAM toward Dynamic Scenes with Semantic and Geometric Information
GLIM: versatile and extensible point cloud-based 3D localization and mapping framework
dddmr_navigation is the 3D navigation solution for mobile robots includes mapping/localization/perception/path planning/controller/navigation stack
[NeurIPS 2024] SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
🚀 [RA-L 2026] vision-driven Situational Graphs (vS-Graphs)
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
The agent that grows with you
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
Real-time SLAM with deep features (XFeat + ORB-SLAM3)
Infinite Photorealistic Worlds using Procedural Generation
ORB-SLAM3 with SuperPoint, LightGlue, and NetVLAD/CosPlace replacing handcrafted features with learned deep learning components for improved visual SLAM accuracy