Peng Xu

Three.js-Object-Sculptor-Codex-Plugin. Codex plugin that turns attached object images into code-only, animation-ready procedural Three.js models.

CLIProxyAPIPlus. CCS-maintained fork of CLIProxyAPIPlus (MIT snapshot, Apr 2026) with daily auto-sync from router-for-me/CLIProxyAPI. See plans for context.

Research-Paper-Writing-Skills. Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.

paper-framework-figure-studio-pro. A multi-round co-design skill for publication-ready paper framework diagrams and method overview figures.

Auto-claude-code-research-in-sleep. 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 with Claude Code, Codex, OpenClaw, or any LLM agent.

lingbot-map. A feed-forward 3D foundation model for reconstructing scenes from streaming data

lingbot-world-v2. Infinite Worlds with Versatile Interactions

sjh-skills. Shell

lingbot-vision. Self-supervised learning for spatial perception

FlashVDM. Unleashing Vecset Diffusion Model for Fast Shape Generation / within 1 Second (ICCV'25 Highlight)

laion-3d. Collect large 3d dataset and build models

DreamX-World. DreamX-World: A General-Purpose Interactive World Model

SOMA-X. SOMA: Unifying Parametric Human Body Models

github-readme-stats. :zap: Dynamically generated stats for your github readmes

Sana. SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

ABot-Earth-0.5. Generative 3D Earth Model by AMap-cvlab

VisionReward. [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation

ImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

DeepPaperNote. DeepPaperNote is an agent skill for deep-reading a single paper and generating high-quality Obsidian-style research notes. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

vipe. ViPE: Video Pose Engine for Geometric 3D Perception

Matrix-Game. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

zjuthesis. Zhejiang University Graduation Thesis LaTeX Template

superpowers. An agentic skills framework & software development methodology that works.

zju-connect. ZJU RVPN 客户端的 Go 语言实现

how-to-use-claude-the-smart-way.

IndustryBench. A multi-lingual benchmark for evaluating industrial domain knowledge of LLMs.

talkie. talkie is a vintage language model from 1930

CarlaAir. CarlaAir: Fly Drones Inside a CARLA World!! A Unified Infrastructure for Air-Ground Embodied Intelligence

VeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

MLFocalLengths. Estimating the Focal Length of a Monocular Image

GeoCalib. GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

TeleBoost. A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation.

StereoWorld. [CVPR 2026] Stereo World Model

claw-code. An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

learn-coding-agent. Research on Coding Agents

PhyGenesis. JavaScript

cosmos-predict2.5. Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

fantasy-world. [ICLR 2026] FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction

cosmos-predict1. Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

seoul-world-model. Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis

OpenEMMA. OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

font.

RAD. [NeurIPS 2025] RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

ReconDreamer-RL. Python

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

awesome-openclaw-skills. The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

lingbot-depth. Masked Depth Modeling for Spatial Perception

lingbot-vla. A Pragmatic VLA Foundation Model

learning_research. 本人的科研经验

Awesome-Foundation-Model-Based-Depth. A curated list of papers & resources on depth estimation & depth completion with foundation models.

lingbot-world. Advancing Open-source World Models

Awesome-Foundation-Models. A curated list of foundation models for vision and language tasks

Awesome-CV-Foundational-Models.

S3-Stereo.

Awesome-World-Models. A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.

Awesome-World-Model. Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

GANet. GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

iREPA. [ICLR 2026] Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

scared_toolkit. Unofficial SCARED Dataset Toolkit

sam-3d-body. The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the model.

sam-3d-objects. SAM 3D Objects

ZeroStereo. [ICCV 2025] ZeroStereo: Zero-Shot Stereo Matching from Single Images

SVP. Python

gemini-cli. An open-source AI agent that brings the power of Gemini directly into your terminal.

awesome-dust3r. 🌟A curated list of DUSt3R-related papers and resources, tracking recent advancements using this geometric foundation model.

xxxupeng.github.io. CSS

flowseek. Source code for ICCV 2025 paper "FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"

llm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

tiny-llm-zh. 从零实现一个小参数量中文大语言模型。

FastVGGT. [ICLR 2026] FastVGGT: Fast Visual Geometry Transformer

DMS. Using Stable Diffusion Model for generating multi-baseline images for autonomous driving scenes like KITTI.

stereo_toolbox. 🔧 A comprehensive stereo matching toolbox for efficient development and research.

BridgeDepth. [ICCV 2025 Highlight] BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment

Amodal-Depth-Anything. [ICCV 2025] Amodal Depth Anything: Amodal Depth Estimation in the Wild

Geo4D. [ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

unimatch. [TPAMI'23] Unifying Flow, Stereo and Depth Estimation

SMoE-Stereo. [ICCV 2025 Highlight] 🌟🌟🌟 Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Experts

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

dynamic-3dgs-papers. Dynamic Scene Representation Gaussian Splatting

Resume-Matcher. The #1 AI Harness for Building Resumes, PDFs, Cover Letters & more, locally with 100+ LLMs support.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

GwcNet. Group-wise Correlation Stereo Network, CVPR 2019

SeeingThroughFog. Python

read-frog. 🐸 Read Frog - Language Learning & Translate | 🐸 陪读蛙 - 语言学习与翻译

aanet. [CVPR'20] AANet: Adaptive Aggregation Network for Efficient Stereo Matching

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

fluentui-system-icons. Fluent System Icons are a collection of familiar, friendly and modern icons from Microsoft.

Hunyuan3D-2.1. From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

FoundationStereo. [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

LLaNA. Official code repository of LLaNA: Large Language and NeRF Assistant

MonSter. 【CVPR 2025 Highlight】MonSter: Marry Monodepth to Stereo Unleashes Power

DEFOM-Stereo. [CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching

MaterialMVP. MaterialMVP: Illumination-Invariant Material Generation via Multi-view PBR Diffusion

MIDAS. [ICCV 2025] MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching

REFRAME. This repository is the official implementation for the paper “REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices”.

Task-Conditional-Adapter. [MM 2024] Task-Conditional Adapter for Multi-Task Dense Prediction

stereoanywhere. [CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

holopix50k. Holopix50k: A Large-Scale In-the-wild Stereo Image Dataset

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

ADL. [CVPR 2024] Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching

AlchemyCat. Alchemy Cat —— 🔥Config System for SOTA

Awesome-Deep-Stereo-Matching. A curated list of awesome Deep Stereo Matching resources

awesome-4d-generation. List of papers on 4D Generation.

awesome-3d-diffusion. A collection of papers on diffusion models for 3D generation.

GeoWizard. [ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

cs-self-learning. 计算机自学指南

BrachioGraph. BrachioGraph is an ultra-cheap (total cost of materials: €14) plotter that can be built with minimal skills.