Chenguo Lin

JoyAI-VL-Interaction. Python

lingbot-world-v2. Infinite Worlds with Versatile Interactions

lingbot-video. Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

mira. Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

lingbot-vla-v2. From Foundation to Application

lingbot-vision. Self-supervised learning for spatial perception

Hy3. Hy3 (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency.

RDM. Python

GenRecon. Python

GEAR. Python

diffusion-bench. Towards Holistic evaluation of Generative Diffusion Transformers!

ViQ. [ECCV2026] ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

Boogu-Image. Boogu-Image-0.1 is an Apache-2.0 open-source image generation and editing model family that delivers near-closed-source performance with an order of magnitude less data.

i1. Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

Surflo. Official implementation of Surflo: Consistent 3D Surface Flow Model with Global State.

minit2i-torch. Official PyTorch re-implementation of MiniT2I.

TripoSplat. TripoSplat converts a single 2D image into high-quality and variable number of 3D Gaussians, developed by TripoAI.

SynthVerse. [SIGGRAPH 2026] SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking

ResearchMathAgent. Research Math Agents, Official code release for our paper RMA

SpatialClaw. SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

meshflow. Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh Ranjan, Ping Tan and Andrea Vedaldi.

UniRL. UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

llm_wiki. LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratch every time), the LLM incrementally builds and maintains a persistent wiki from your sources。

RationalRewards. RationalRewards: a reasoning reward model for diffusion RL and test-time prompt tuning

html-video. Programmatic video for coding agents — HTML to video on your laptop. Turn HTML, CSS & data into real MP4s with pluggable render engines, 21 templates, AI soundtrack. Apache-2.0, no per-render fees. An official project by the Open Design team.

GordenSuperPPTSkills. AI PPT赛道终结者，史上最最最强 PPT Skill！！！ 使用GPT生成豪华的图片格式PPT，然后转换为完全可编辑的PPTX文件。

JoyAI-Echo. JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation

Bernini. Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.

flashdreams. high-performance inference and serving library for interactive autoregressive video and world models

maple-font. Maple Mono: Open source monospace font with round corner, ligatures and Nerd-Font icons for IDE and terminal, fine-grained customization options. 带连字和控制台图标的圆角等宽字体，中英文宽度完美2:1，细粒度的自定义选项

VLM3. Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

cosmos-framework. Our inference and training framework to run on the Cosmos Models

DiffusionOPD. DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models

ai-agent-deep-dive. AI Agent 源码深度研究报告

Open-d4rt. Python

OSP-Next. OSP-Next

Eagle. Eagle: Frontier Vision-Language Models with Data-Centric Strategies

orbit. Stable and Efficient Reinforcement Learning for Trillion-Parameter LLMs

Trellis. The best agent harness.

R3. Official implementation of R^3: 3D Reconstruction via Relative Regression.

Gamma-World. Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

MoneyPrinterTurbo. 利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

GenLIP. Official repo for "Let ViT Speak: Generative Language-Image Pre-training"

SpatialBench. SpatialBench: Is Your Spatial Foundation Model an All-Round Player?

html-anything. ✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.

RTDMD. [arXiv 2026] This is the official PyTorch implementation of "RTDMD: Reinforcing Few-step Generators via Reward-Tilted Distribution Matching".

WBench. WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation

TriSplat. TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

cambrian-p. Cambrian-P: Pose-Grounded Video Understanding

DeepSeek-Reasonix. DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

NoPo4D. Official implementation of No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos

SCOPE. SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models

Understand-Anything. Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.

PiD. PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion

Nova3D. Editable, part-aware 3D generation from text or reference images. Open-source client for nova3d.xyz.

RiT. PyTorch implementation of RiT: Vanilla Diffusion Transformers Suffice in Representation Space

GenEvolve. Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation

PhysX-Omni. PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects

minWM. A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

StitchVM. Official code for "Stitched Value Model for Diffusion Alignment"

RAEv2. Official Implemenation for RAEv2: Improved Baselines with Representation Autoencoders

Lance. A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

advantage_weighted_matching. Official code for paper Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

FaithC. [CVPR 2026 (Oral)] Official Torch/CUDA Implementation of Faithful Contouring

ReactiveGWM. [Arxiv 2026] ReactiveGWM: Steering NPC in Reactive Game World Models

articraft. An Agentic System for Scalable Articulated 3D Asset Generation

academic-research-skills. Academic Research Skills for Claude Code: research → write → review → revise → finalize

V-Thinker. Python

HiAR. [ECCV 2026] sink-free, anti-drift causal AR Video Generation

SDAR. Official code for "Self-Distilled Agentic Reinforcement Learning"

Warp-as-History. Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

image-blaster. An image-to-world skillset for Claude.

vggt-omega. [CVPR 2026 Oral] VGGT Omega

Cola-DLM. The codebase of Cola DLM

Olaf-World. [ICML 2026] Orienting Latent Actions for Video World Modeling

G-OPD. Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"

ram. Python

ODE. Implementation for: Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents

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

AnyFlow. Flow Map OPD for AnyStep Video Diffusion

dmdr. [ECCV 2026] Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

ui-ux-pro-max-skill. An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

LeapAlign_Code. [CVPR2026] LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

AutoRubric-as-Reward. Auto-Rubric as Reward: From Implicit Preference to Explicit Generative Criteria

D-OPSD. Official Repo of "D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models"

ELF. Python

Pixal3D. [SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

narrator-ai-cli-skill. AI 解说大师 — Agent skill；封装 narrator-ai-cli 供 Claude/Codex 等工具调用

CDM. Continuous-Time Distribution Matching for Few-Step Diffusion Distillation👏

HiDream-O1-Image. Python

gpt-image2-ppt-skills. Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT：gpt-image-2 仿版式、你换内容，另含 10 套精选风格。Claude Code / OpenClaw skill.

Flow-OPD. Official Repo of "Flow-OPD: On-Policy Distillation for Flow Matching Models"

browser-agent. [browser-agent] Never send a human to do a machine's job.

verl-omni. Multimodal RL training framework for diffusion & omni models

Dispider. [CVPR 2025]Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction

AURA. Python

OpenSearch-VL. 🔍 OpenSearch-VL provides a fully open recipe for training strong multimodal deep search agents through high-quality data curation, diverse visual/search tools, and fatal-aware agentic reinforcement learning.

infinity-rope. [CVPR 2026] Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout

v-grpo. [CVPR 2026 Findings] V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think

agent-zero-to-hero. Build a Claude-Code-shaped agent harness from scratch. 7-week course, 20 chapters, ~5,000 lines of Python, 42 tests, 3 LLM providers, no frameworks.

Pixelle-Video. 🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

hands-on-modern-rl. 🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

recgen. Jupyter Notebook

awesome-ego-video-datasets. 🎥 [Awesome] Egocentric / First-Person Video Datasets 📚 Papers, Benchmarks & Resources for Ego Vision

Code2World. Code2World: A GUI World Model via Renderable Code Generation

OPD. Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

awesome-agentic-world-modeling. Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

open-codesign. Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.

PaperOrchestra. An automated AI research-paper writer based off Google's PaperOrchestra paper's implementation through a skills - benchmark + autoraters using any coding agent (Claude Code, Cursor, Antigravity, Cline, Aider). No API keys, no LLM SDKs.

PaperBanana. PaperBanana: Automating Academic Illustration For AI Scientists

papervizagent. Python

FD-Loss. Python

nano-world-model. A Minimalist, Batteries-included Repository for Advancing World Model Science.

Claw-Eval-Live. Python

tuna-2. Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation

World-R1. [ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

SenseNova-U1. SenseNova-U series: Native Unified Paradigm with NEO-unify from the First Principles

InfraTech. 分享AI Infra知识&代码练习：PyTorch、vLLM/SGLang、slime/vime框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等

Vista4D. Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)

4RC. [ICML 2026] 4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere

PAT3D. Python

MemFlow. Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

Pika-Skills. Python

sapiens2. 1K resolution vision transformers pretrained on 1B human images.

Hy3-preview. Hy3 preview (295B A21B), a leading reasoning and agent model in its size, with great cost efficiency

RISE. [RSS 2026] Code for RISE: Self-Improving Robot Policy with Compositional World Model

VANS. [CVPR 2026] Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO

diamond_maps. Python

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

AnyRecon. AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model

ShotStream. [ECCV 2026] ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling

OpenGame. OpenGame: Open Agentic Coding for Games

MultiWorld. Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

TokenGS. [CVPR'26] TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens

SelfEvo. Self-Improving 4D Perception via Self-Distillation

HY-SOAR. HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models

vla0. VLA-0: Building State-of-the-Art VLAs with Zero Modification

tigon. Official repository of Text-Image Conditioned 3D Generation (TIGON, CVPR 2026)

Boxer3D. AR 3D object detection for iPhone with LiDAR — YOLO 2D + BoxerNet 3D lifting

SteerViT. SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.

ERNIE-Image. ERNIE-Image is an open text-to-image generation model developed by the ERNIE-Image team at Baidu. It is built on a single-stream Diffusion Transformer (DiT), with only 8B DiT parameters, it reaches state-of-the-art performance among open-weight text-to-image models.

PixelDiT. [CVPR 2026 Best Paper Finalist] Pixel Diffusion Transformers for Image Generation

HY-World-2.0. HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

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

tips. TIPSv2 (CVPR'26) and TIPS (ICLR'25)

CRD. Python

VisionFoundry. VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images

SearchClaw. Harness for deep search agent

Auto-Resubmit. 🚀 Automated & lossless LaTeX paper migration tool. Instantly convert your Overleaf source between top-tier AI conference templates (NeurIPS, ICLR, ACL等). 一键无损转换顶会论文格式！解决转投时的排版折磨，完美保留公式、图表与引用，让科研人员专注研究而非排版。

SkillClaw. Let Skills Evolve Collectively with Agentic Evolver

hermes-agent. The agent that grows with you

HY-Embodied. HY-Embodied: Embodied Foundation Models for Real-World Agents

boxer. Code for the Boxer research paper

cli. Generate text, images, video, speech, and music by MiniMax.

vero. Vero: An Open RL Recipe for General Visual Reasoning

GLM-5. GLM-5: From Vibe Coding to Agentic Engineering

void-model. Python

GEMS. GEMS: Agent-Native Multimodal Generation with Memory and Skills

SkillZero. Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

AlayaRenderer. Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.

claude-code-book. 《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：

claude-reviews-claude. Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.

VCC. Compile agent conversations!

resplat. ReSplat: Learning Recurrent Gaussian Splatting

Unify-Agent. 🐧 Unify-Agent: An end-to-end unified multimodal agent for faithful, knowledge-grounded image generation.

scenetok. [CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes

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

Gen-Searcher. Gen-Searcher: Reinforcing Agentic Search for Image Generation

codex-plugin-cc. Use Codex from Claude Code to review code or delegate tasks.

colleague-skill. 将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

LiveWorld. [ECCV 2026] Official implementation of paper LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

reasoning-from-scratch. Implement a reasoning LLM in PyTorch from scratch, step by step

claude-howto. A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

cli. The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.

HyDRA. Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

megaflow. MegaFlow: Zero-Shot Large Displacement Optical Flow

UNITE-tokenization-generation. Single-stage End-to-End Training for Tokenization and Generation

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

AutoGaze. AutoGaze automatically removes redundant patches in a video, reducing #tokens in ViT/MLLM by 4x-100x.

seedance-prompt-skill. Seedance 2.0 prompt skill，使用该Skill生成Seedance 2.0 视频提示词

claude-prism. An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

sage. Official Code Release of SAGE: Scalable Agentic 3D Scene Generation for Embodied AI

MagiCompiler. A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.

FunCineForge. Python

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.

GLD. Official implementation of "Repurposing Geometric Foundation Models for Multi-view Diffusion"

InfiniDepth. [CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Astrolabe. Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

ReLi3D. Relightable multi-view 3D reconstruction with disentangled illumination and spatially varying PBR materials

lagernvs. Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

daVinci-MagiHuman. Python

zotero-mcp. Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

drifting. Python

frontend-slides. Create beautiful slides on the web using a coding agent's frontend skills

inspatio-world. Python

HOMIE-toolkit. Python

SegviGen. [SIGGRAPH 2026 Journal] SegviGen: Repurposing 3D Generative Model for Part Segmentation

Attention-Residuals.

AutoResearchClaw. Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞