Eason (YICHENG XIAO)

penguin-harness. 🐧 Automated Agent Builder on Your Desktop: Create Self-Evolving Agents in One Click

LiveEdit. [ECCV 2026] LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing

Stable-Video-Infinity. [ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

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

LongLive-RAG. Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

drifting. Python

mammothmoda. Python

FastVideo. A unified inference and post-training framework for accelerated video generation.

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

Meta-CoT. [CVPR 2026] Official code of the paper "Meta-CoT: Enhancing Granularity and Generalization in Image Editing"

DuQuant-v2. DuQuant++: Fine-grained Rotation Enhances Microscaling FP4 Quantization

Awesome-Efficient-dLLMs. 📚 A curated list of Awesome Efficient dLLMs Papers with Codes

QDLM. Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs

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

OpenSpatial. Python

MotionLCM. [ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

triattention. TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

SpatialEdit. [Official Repo] SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing

JoyAI-Image. JoyAI-Image is the unified multimodal foundation model for image understanding, text-to-image generation, and instruction-guided image editing.

StreamDiffusionV2. StreamDiffusion, Live Stream APP

Helios. Helios: Real Real-Time Long Video Generation Model

Kiwi-Edit. A unified and fully open-source framework for instruction-guided and reference-guided video editing using natural language.

Utonia. [ICML'26] Official repository of Utonia: Toward One Encoder for All Point Clouds

Kimi-K2.5. Open Visual Agentic Intelligence

lingbot-world. Advancing Open-source World Models

Reasoning-Visual-World. Official repository for "Visual Generation Unlocks Human-Like Reasoning through Multimodal World Models", https://arxiv.org/abs/2601.19834

objaverse-xl. 🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

Omni-Video. Python

sam-3d-objects. SAM 3D Objects

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

DSR_Suite. Jupyter Notebook

Wan-Move. [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

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

VST. [ECCV2026] Visual Spatial Tuning

Emu3.5. Native Multimodal Models are World Learners

MindOmni.

QeRL. [ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

LongLive. Long Video Gen Infrastructure

HunyuanImage-3.0. HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

MRVS_SOC. Python

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

FollowYourShape. [ICLR 2026] Follow-Your-Shape: This repo is the official implementation of "Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control"

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

ARC-Hunyuan-Video-7B. Structured Video Comprehension of Real-World Shorts

Long-RL. Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

UniWorld. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

RISEBench. [NIPS 2025 DB Oral] Official Repository of paper: Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

OmniGen2. OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

Bagel. Open-source unified multimodal model

TokLIP. TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

edge-tts. Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

MindOmni. [NeurIPS2025] The official implementation of MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Step1X-Edit. A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.

VideoPainter. [SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

AnimeGamer. [ICCV 2025] AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction

awesome-deep-reasoning. Collect every awesome work about r1!

x-flux. Python

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

lmm-r1. Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

HaploVLM. ICML2025

MM-EUREKA. MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning

Megatron-LM. Ongoing research training transformer models at scale

VoCo-LLaMA. [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".

VLM-R1. Solve Visual Understanding with Reinforced VLMs

Image-Generation-CoT. [CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

RF-Solver-Edit. [🚀ICML 2025] "Taming Rectified Flow for Inversion and Editing" Using FLUX and HunyuanVideo for image and video editing!

lmms-eval. One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

OmniGen. OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

ECCV2022-RIFE. ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

DynamicCity. [ICLR 2025 Spotlight] Official implementation for "DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes"

1d-tokenizer. This repo contains the code for 1D tokenizer and generator

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

PhyGenBench. [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation

mar. PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Consistent123. [ACMMM 2024] Consistent123: One Image to Highly Consistent 3D Asset Using Case-Aware Diffusion Priors

WritingAIPaper. Writing AI Conference Papers: A Handbook for Beginners

Awesome-diffusion-model-for-image-processing. one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

HivisionIDPhotos. ⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

natural-instructions. Expanding natural instructions

Lumina-mGPT. Official Implementation of "Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining"

EditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

open-instruct. AllenAI's post-training codebase

COVE. [NeurIPS 2024] COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing

awesome-vlm-architectures. Famous Vision Language Models and Their Architectures

SpeculativeDecodingPapers. 📰 Must-read papers and blogs on Speculative Decoding ⚡️

Awesome-Efficient-LLM. A curated list for Efficient Large Language Models

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

MobileVLM. Strong and Open Vision Language Assistant for Mobile Devices

chainlit. Build Conversational AI in minutes ⚡️

Efficient-Multimodal-LLMs-Survey. Efficient Multimodal Large Language Models: A Survey

MambaTree. [NeurIPS2024 Spotlight] The official implementation of MambaTree: Tree Topology is All You Need in State Space Model

CoHD. The official implementation of A Counting-Aware Hierarchical Decoding Framework for Generalized Referring Expression Segmentation

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

LongLoRA. Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

LaVIT. LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

awesome-diffusion-models-in-low-level-vision. A Repository for Diffusion-Model-related Papers in Low-level Vision

awesome-concealed-object-segmentation.

Video-LLaVA. 【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

UniLSeg. [CVPR 2024] Official implementation of "Universal Segmentation at Arbitrary Granularity with Language Instruction"

VQA_to_multimodal_survey. Update 2020

FollowYourHandle. [WACV 2025] Follow-Your-Handle: This repo is the official implementation of "MagicStick: Controllable Video Editing via Control Handle Transformations"

UVCOM. [CVPR 2024] Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection

PKEF. [CIKM'23] Parallel Knowledge Enhancement based Framework for Multi-behavior Recommendation

EasonXiao-888.github.io. HTML

RKDNet.

NeurIPS2023_SOC. [NeurIPS 2023] The official implementation of SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

iccv2023_RVOS_Challenge. [ICCV 2023 Workshop] The Official Implementation of The First Prize Solution for RVOS Competition

EasonXiao-888.

SemanticAC. [ICASSP 2023] SEMANTICAC: SEMANTICS-ASSISTED FRAMEWORK FOR AUDIO CLASSIFICATION

UniVTG. [ICCV 2023] UniVTG: Towards Unified Video-Language Temporal Grounding

Awesome-Cross-Modal-Video-Moment-Retrieval. 前沿论文持续更新--视频时刻定位 or 时域语言定位 or 视频片段检索。

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

CVPR-2023-Papers.

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

FollowYourPose. [AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

cs-self-learning. 计算机自学指南

mmaction2. OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

CS-BAOYAN-2022. 计算机保研交流群（QQ群号：605176069）

xduts. Xidian University TeX Suite 西安电子科技大学LaTeX套装

Bilibili-WenDao. Algorithm & DataSet for Machine Learning