Lists (2)
Starred repositories
Infinite Worlds with Versatile Interactions
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Repository containing all necessary codes to get started on the SoccerNet Dense Video Captioning challenge.
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents -- All for Long running Agentized Workflows
A tutorial on modern GPU programming for machine learning systems
Archive any Zhihu creator (answers, articles, images) by URL — browser-driven (login once) or pure-HTTP with a cookie.
Scrape Xiaohongshu like a human, not a bot — persistent login, cover-click stealth, full-res media, and offline OCR.
YC (S26) | Open Computer History | Record your screen continuously locally and provide context to your agents (Claude, Codex, Openclaw, Hermes, Runner...)
robomimic: A Modular Framework for Robot Learning from Demonstration
The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)
Building General-Purpose Robots Based on Embodied Foundation Model
Official repo for "StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation"
[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.
A unified simulation platform that combines hardware and software, enabling pre-silicon, full-stack, closed-loop evaluation of your robotic system.
Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
[NeurIPS2025]VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
[RSS 2026] LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
World Model & VLA Survey - Interactive Research Page