Lists (5)
Starred repositories
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
A curated collection of SuperMimic implementations, extensions, demos, and resources.
Official Implementation of "DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models"
A Foundation Model for Whole-Body Humanoid Control
GPT-Policy: In-Context Robot Learning with VLM Agents
Motus2: A Self-Evolving General World Model for Dexterous Manipulation
RPent: Agentic Infrastructure for the Physical World
Unified World Model Inference & Evaluation Infrastructure
[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching
SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles
The first continuous diffusion language model that rivals discrete counterparts on standard language modeling benchmarks like LM1B and OpenWebText.
HY-Embodied: Embodied Foundation Models for Real-World Agents
AI agents running research on single-GPU nanochat training automatically
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
Memory-Dependent Manipulation Benchmark based on RoboTwin
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
A Curated List of Awesome Video World Models with AR Diffusion: Covering Algorithms, Applications, and Infrastructure, Aimed at Serving as a Comprehensive Resource for Researchers, Practitioners, a…
Awesome Unified Multimodal Models
NextFlow🚀: Unified Sequential Modeling Activates Multimodal Understanding and Generation
Official repo for vidar and vidarc: video foundation model for robotics.
Official code of Motus: A Unified Latent Action World Model
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
RoboChallenge Inference example code
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
[ICLR 2026] Trace Anything: Representing Any Video in 4D via Trajectory Fields
A unified inference and post-training framework for accelerated video generation.