https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成

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

Orchestrate multiple coding agents from desktop and mobile

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

[ICML 2026] Meta Context Engineering via Agentic Skill Evolution

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

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

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

Flow Map OPD for AnyStep Video Diffusion

[ECCV2026] ViBe: Ultra-High-Resolution Video Synthesis Born from Pure Images

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

Project Lyra: Open Generative 3D World Models

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

[ICCV'25 Best Paper Finalist] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"

Helios: Real Real-Time Long Video Generation Model

OpenSeeker: A search agent with open-source data and models

A Mechanistic View on Video Generation as World Models: State and Dynamics

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

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation (ECCV 2026)

Advancing Open-source World Models

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

[ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal Forcing++

Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and shaping the future!

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)