GPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

[RSS 2026] Causal video-action world model for generalist robot control

Official repo for "Let ViT Speak: Generative Language-Image Pre-training"

Unified Codebase for Advanced World Models.

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons

Official code of Motus: A Unified Latent Action World Model

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

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

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models

Light Image Video Generation Inference Framework

The agent engineering platform.

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

ThinkGen: Generalized Thinking for Visual Generation

Your image is almost there!

[CVPR2026] Efficient Long Video Generation via Next-Frame-Rate Prediction

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Official JAX implementation of End-to-End Test-Time Training for Long Context

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

[DEIMv2] Real Time Object Detection Meets DINOv3

You can easily calculate FVD, PSNR, SSIM, LPIPS for evaluating the quality of generated or predicted videos.

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''