From a single casual image to a visually consistent and physically stable interactive 3D scene.

The agent that grows with you

A generative 3D world model for embodied reasoning and planning under partial observability.

Code and website for "MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation".

An end-to-end open ecosystem for robot learning

High rate event camera data simulation in Isaac Sim, accelerated by motion-vector frame interpolation.

An Obsidian plugin for day planning with a clean UI and a simple task format

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds

Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents

Official repo for GraspGen: A Diffusion-based Framework for 6-DOF Grasping

Solutions to Linear Algebra Done Right, by Sheldon Axler.

[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Official implementation of Continuous 3D Perception Model with Persistent State

Doing simple retrieval from LLM models at various context lengths to measure accuracy

TradingAgents: Multi-Agents LLM Financial Trading Framework

Infinite Photorealistic Worlds using Procedural Generation

PAIR-kernel

Your Semester Made Easier | Course Scheduling & Social Tools for Students

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

[NeurIPS 2025] Official implementation for the paper "SeePhys: Does Seeing Help Thinking? -- Benchmarking Vision-Based Physics Reasoning"

The simplest, fastest repository for training/finetuning medium-sized GPTs.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

EchoShield is a floating chat assistant designed to enhance digital communication by integrating real-time AI interaction and non-violent communication guidance.