An agentic skills framework & software development methodology that works.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

zero-shot voice conversion & singing voice conversion, with real-time support

PyTorch implementation for the paper "Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving"

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

Essential reads for every AI engineer interested in building AI apps.

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Generative Agents: Interactive Simulacra of Human Behavior

Code Release for HARMONI: Using 3D Computer Vision and Audio Analysis to Quantify Caregiver–Child Behavior and Interaction from Videos (Science Advances)

[WACV 2024 Survey Paper] Multimodal Large Language Models for Autonomous Driving

(NeurIPS 2025) Official implementation for "MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?"

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Character Animation (AnimateAnyone, Face Reenactment)

DN-Splatter + AGS-Mesh: Depth and Normal Priors for Gaussian Splatting

TC4D: Trajectory-Conditioned Text-to-4D Generation

Sample code and notebooks for Generative AI on Google Cloud, with Gemini Enterprise Agent Platform

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

A list of Human-Object Interaction Learning.

State-of-the-art 2D and 3D Face Analysis Project

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

TripoSR: Fast 3D Object Reconstruction from a Single Image

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

A framework for 4D reconstruction from monocular videos.

Official Repository of [CVPR'24 Highlight Diffportrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis]

Grok open release

Add-on for Blender that allows the transfer of animations and poses from one armature to another