[CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

PhyAgentOS is a self-evolving embodied AI operating system built on agentic workflows.

RPent: Agentic Infrastructure for the Physical World

Simulation benchmarks of GR1 Tabletop Tasks for GR00T N1

Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

Standard Open Arm 100

A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

[ECCV 2026] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

A simulation evaluation platform for DROID

PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

A Curated List of Vision-Language-Action (VLA) and World Action Models (WAM) Research and Beyond

A community-maintained Python framework for creating mathematical animations.

Teams-first Multi-agent orchestration for Claude Code

[ECCV 2026] WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

👀「大模型」2小时从0训练65M参数的视觉多模态VLM！Train a 65M-parameter VLM from scratch in just 2h!

The simplest, fastest repository for training/finetuning small-sized VLMs.

3DSGrasp: 3D Shape-Completion for Robotic Grasp

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

[CVPR2025]

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

📄 适合中文的简历模板收集（LaTeX，HTML/JS and so on）由 @hoochanlon 维护