[Tech Report] Democratizing the Training of Video World Models from Scratch. 🔥 🔥 🔥

https://fmhy.net/

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

Infinite Interactive World Rollout on a Single Desktop GPU

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

[RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

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

UE5-based Data Engine used in OmniX

Official JAX implementation of MAGVIT: Masked Generative Video Transformer

A curated list of research and projects on world models

Infinite Worlds with Versatile Interactions

AI chat and agent tooling for Godot, with both MCP support and in-built native chat window.

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

Advancing Open-source World Models

Box3D is a 3D physics engine for games

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static bin…

A Foundation Model for Generalist Gaming Agents

An image-to-world skillset for Claude.

MVP Engine - The Next-Generation Framework for Multimodal Model Training with Agents

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

IEEE CoG & NeurIPS workshop paper 'Counter-Strike Deathmatch with Large-Scale Behavioural Cloning'

Turn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Moonshot kimi k3 terminal based coding agent & harness running on your own Cloudflare account.