AI agents running research on single-GPU nanochat training automatically

DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

[CVPR 2025] Offcial implementation of PhysFlow: Unleashing the Potential of Multi-modal Foundation Models and Video Diffusion for 4D Dynamic Physical Scene Simulation

Code for the Molmo Vision-Language Model

Cosmos Policy

Unofficial implementation of the Dreamer 4 world model in PyTorch.

Learning to Compress Prompts with Gist Tokens - https://arxiv.org/abs/2304.08467

Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr0…

Official implementation of SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

[ICRA, 2025] SplatSim: Zero-Shot Sim2Real Transfer of RGB Manipulation Policies Using Gaussian Splatting

[CVPR 2026] A PyTorch implementation of the paper "EDGS: Eliminating Densification for Efficient Convergence of 3DGS"

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

[CoRL 2025] Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware

Native and Compact Structured Latents for 3D Generation

Inverse kinematics and subproblem solutions from "IK-Geo: Unified robot inverse kinematics using subproblem decomposition" implemented in MATLAB, C++, Rust, and Python.

Lightweight implementation of Robotic World Model (RWM) and Uncertainty-Aware Robotic World Model (RWM-U)

Automated, hardware-independent Hand-Eye Calibration for ROS2

High-Level Control Library for Franka Robots with Python and C++ Support

desktop app to browse and analyze your Claude Code conversation history

Event-based Vision Resources. Community effort to collect knowledge on event-based vision technology (papers, workshops, datasets, code, videos, etc)

[NeurIPS 2025] Tracking and Understanding Object Transformations

Best Papers of Top Venues like CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, ...

Official implementation of ICCV 2025 paper "EgoAgent: A Joint Predictive Agent Model in Egocentric Worlds".

provides all the codes from the book "RL from basics(바닥부터 배우는 강화학습)"

MUKCa: Accurate and Affordable Cobot Calibration Without External Measurement Devices