Stars
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
The open-source CapCut alternative
Skills for Designers and Engineers.
Curated papers, taxonomy, benchmarks, and decision guides for credit assignment in reasoning and agentic LLM reinforcement learning.
Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.
DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge files. Turn your AI coding assistant into a full video pro…
Real-time AI coding agent status panel in your MacBook notch — live status, approvals & replies for 13 AI tools, with iPhone & Apple Watch companions
A curated list of papers, code, and resources for one-step diffusion models that turn noise into high-quality samples in a single neural network forward pass.
My Python scripts to make high-quality figures for publications in top AI conferences and journals.
Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
An LLM post-training framework with vLLM for RL Scaling
Academic Research Skills for Claude Code: research → write → review → revise → finalize
A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.
LLaDA2.0-Uni: Understanding and Generation the World.
ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches…
Awesome Multimodal Modeling [Covers MLLM, UMM, and NMM]
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
Harness engineering beginner tutorial, from 0 to 1
[ECCV 2026] Official implementation of "TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning"
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.
🛠️ Awesome tools & guides for harness engineering.
[Preprint] Self-Adversarial One Step Generation via Condition Shifting
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
The agent that grows with you