A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. Topics

This is the official implementation of our paper "SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning"

The official repository of "WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG"

Helios: Real Real-Time Long Video Generation Model

Code repo for paper: Effective Strategies for Asynchronous Software Engineering Agents

[CVPR 2026] Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement

Source Code for our ICLR'26 paper

WorldCache: Content-Aware Caching for Accelerated Video World Models

Self-referential self-improving agents that can optimize for any computable task

Automate the process of making money online.

Claude Code skills that turn any codebase into an interactive knowledge graph you can explore, search, and ask questions about (Multi-platform e.g., Codex are supported).

Advancing AI by embracing human-likeness for better AI understanding, human–AI collaboration, and social simulation, bridging technology and genuine human experience.

Turn Claude Code into a full game dev studio — 48 AI agents, 36 workflow skills, and a complete coordination system mirroring real studio hierarchy.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

PraisonAI 🦞 - Your 24/7 AI employee team. Automate and solve complex challenges with low-code multi-agent AI that plans, researches, codes, and delivers to Telegram, Discord, and WhatsApp. Handoffs…

An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

A simple CLI for orchestrating Claude Code, Codex, and OpenCode

Official Repository for STTS.

OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder

Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"

SOMA: Unifying Parametric Human Body Models

Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning

Official Project Page for FALCON: Fast-Weight Attention for Continual Learning (https://yifanzhang-pro.github.io/FALCON)

Official Implementation of "Visual-ERM: Reward Modeling for Visual Equivalence"

TerraInk: The Cartographic Poster Engine that creates unique and customizable map posters