-
Institute for AI Industry Research (AIR), Tsinghua University
- Beijing, China
-
07:14
(UTC +08:00) - https://xxxxyu.github.io
Highlights
- Pro
Lists (14)
Sort Name ascending (A-Z)
Stars
Use Codex from Claude Code to review code or delegate tasks.
Best academic CV Polish Guide: Academic & PhD CV Checklist.
[MobiSys 2026] On-device parallel ultra-low-bit (ternary) LLM inference with LUT-based mpGeMM kernel.
A LaTeX resume template designed for optimal information density and aesthetic appeal.
ding113 / ccline-packycc
Forked from Haleclipse/CCometixLineClaude Code statusline tool written in Rust - for PackyCode
A simple Astro theme. Use it to create your blog or website.
A minimal, accessible and SEO-friendly Astro blog theme
austere - A minimal theme for Zola with a focus on writing.
🛠️ Coding, creating, and occasionally breaking things—welcome to my digital playground.
omo; the best agent harness - previously oh-my-opencode
Try X-Dub to sync any character in a video with any audio you like | Official repository for "From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping"
😼 优雅地使用基于 clash/mihomo 的代理环境
A modern GUI client based on Tauri, designed to run in Windows, macOS and Linux for tailored proxy experience
StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.
Machine Learning Engineering Open Book
🔥 A curated roadmap to the Efficient VLA landscape. We’re keeping this list live—contribute your latest work!
A comprehensive list of excellent research papers, models, datasets, and other resources on Vision-Language-Action (VLA) models in robotics.
Processed / Cleaned Data for Paper Copilot
Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch
Make beautiful isometric infrastructure diagrams
RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉
Anthropic's Interactive Prompt Engineering Tutorial
[NeurIPS 2024] PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation