-
The Hong Kong University of Science and Technology
- Clear Water Bay, Hong Kong
- https://mobiuslqm.github.io
Lists (1)
Sort Name ascending (A-Z)
Stars
📄Score Centering Stabilizes Off-policy Reinforcement Learning
NVIDIA FastGen: Fast Generation from Diffusion Models
Qwen-Image-Layered: Layered Decomposition for Inherent Editablity
Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.
Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.
Offical repo for the paper "LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow"
GPT-6 Astra for embodied AI and robotics.
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…
Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.
A simple AI agent that turns prompts into articulated 3D objects.
高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
Qwen's most powerful open-source image generation model
The official implementation of 'SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation', SIGGRAPH Asia 2025
Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Agentic 3D Modeling with Procedural Control — turns a text prompt into an editable parametric program, with optional per-part materials and articulation.
[SIGGRAPH Asia 2026] 4DAnyone: Create Anyone in 4D from a Casual Monocular Video
Some simple Blender scripts for rendering paper figures
LiteReality-Agent: Turn the real world into simulation-ready environments.
DeepSeek Harness: Everything is a Plugin.