A highly robust and accurate LiDAR-only, LiDAR-inertial odometry

ProtoMotions is a GPU-accelerated simulation and learning framework for training physically simulated digital humans and humanoid robots.

The developer-first platform for scaling complex Physical AI workloads across heterogeneous compute—unifying training GPUs, simulation clusters, and edge devices in a simple YAML

PACE: A systematic approach for sim-to-real transfer of legged robots, identifying actuator and joint dynamics with standard joint encoders.

Muon is an optimizer for hidden layers in neural networks

Raycaster that supports multiple and dynamic mesh. Designed primarily to be used with Isaac Sim.

A PyTorch Library for Accelerating 3D Deep Learning Research

Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning

GCR-PPO is a modification of PPO for multi-objective robot RL that: - uses a multi-head critic to obtain per-reward advantages and gradients, - applies priority-aware gradient surgery (PCGrad-style…

Simple code for generating a color-coded latex table from raw data

Plugin for the simulation of the Livox Mid-360

A Robust Approach for LiDAR-Inertial Odometry Without Sensor-Specific Modelling

HybVIO visual-inertial odometry and SLAM system

Official Implementation of "Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning"

Build your own visual reasoning model

Open-source and strong foundation image recognition models.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO and designed for fine-tuning.

ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

Witness the aha moment of VLM with less than $3.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

Visual Imitation Enables Contextual Humanoid Control. CoRL 2025, Best Student Paper Award.

An implementation of GRPO for Unsloth's VLMs training