Show Lab ORG

A curated list of recent diffusion models for video generation, editing, and various other applications.

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Automatic Video Generation from Scientific Papers

[ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

[CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

[ICML 2026] Video generation via code

💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents.

[IJCV] Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation

[ECCV 2024 Oral] MotionDirector: Motion Customization of Text-to-Video Diffusion Models.

📖 A curated list of resources dedicated to hallucination of multimodal large language models (MLLM).

📖 This is a repository for organizing papers, codes and other resources related to unified multimodal models.

[Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.

[CVPR 2024] X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)

[CVPR 2025] Video Narration as Vocabulary & Video as Long Document

[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025)

[ICCV 2025] Code Implementation of "ArtEditor: Learning Customized Instructional Image Editor from Few-Shot Examples"

The official code implementation of the paper "OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data."

Code for [CVPR 2024] VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence

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

MovieAgent: Automated Movie Generation via Multi-Agent CoT Planning

A curated list of recent robot learning papers incorporating diffusion models for robotics tasks.

[NeurIPS2023] DatasetDM:Synthesizing Data with Perception Annotations Using Diffusion Models

Human-taught Computer-use Agent Designed for Real Windows and MacOS Desktops.

Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

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

[CVPR2023] All in One: Exploring Unified Video-Language Pre-training

[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion

[NeurIPS 2022] Egocentric Video-Language Pretraining

Official code of "MakeAnything: Harnessing Diffusion Transformers for Multi-Domain Procedural Sequence Generation"

The Pytorch implementation of "DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes"

[NeurlPS 2024] One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos

Find out who said what in the video.

the official repo for "D-AR: Diffusion via Autoregressive Models"

[NeurIPS 2023] Customize spatial layouts for conditional image synthesis models, e.g., ControlNet, using GPT

[CVPR 2026] ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands

Enable AI to control your PC. This repo includes the WorldGUI Benchmark and GUI-Thinker Agent Framework.

Official code implementation of "OmniPSD: Layered PSD Generation with Diffusion Transformer"

Code for [CVPR 2025] ROICtrl: Boosting Instance Control for Visual Generation

[ICML 2026] Orienting Latent Actions for Video World Modeling

The official code implementation of the paper “Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration“.

[CVPR 2025] A Hierarchical Movie Level Dataset for Long Video Generation

Official code of "LayerTracer: Cognitive-Aligned Layered SVG Synthesis via Diffusion Transformer"

(NeurIPS 2024) Official PyTorch implementation of LOVA3

EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models

[CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.

No description.

ICML 2025 - Impossible Videos

T2VScore: Towards A Better Metric for Text-to-Video Generation

Official GitHub repository for the Text-Guided Video Editing (TGVE) competition of LOVEU Workshop @ CVPR'23.

No description.

(ICLR 2024, CVPR 2024) SparseFormer

Muti-human Interactive Talking Dataset

[CVPR 2026 Oral] RobotSeg

[ICCV 2025] Balanced Image Stylization with Style Matching Score

No description.

No description.

FQGAN: Factorized Visual Tokenization and Generation

Compress conventional Vision-Language Pre-training data

[NeurIPS 2024 D&B] VideoGUI: A Benchmark for GUI Automation from Instructional Videos

The code repository of UniRL

[NeurIPS 2024] EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models.

Affordance Grounding from Demonstration Video to Target Image (CVPR 2023)

No description.

Computer-Use Agents as Judges for Generative UI

[CVPR 2026] Official Implementation of Edit2Perceive

[ECCV 2024] Learning Video Context as Interleaved Multimodal Sequences

The Pytorch implementation for "Video-Text Pre-training with Learned Regions"

[AAAI2023] Symbolic Replay: Scene Graph as Prompt for Continual Learning on VQA Task (Oral)

No description.

[CVPR 2025] SAM-I2V

No description.

[CVPR 2026] FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection

No description.

Official Pytorch Code of the Paper "WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation"

[NeurIPS 2025] PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

[IEEE-VR 2024] Bring Your Own Character: A Holistic Solution for Automatic Facial Animation Generation of Customized Characters

DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles

A curated list of resources about long-context in large-language models and video understanding.

No description.

[ICCV 2025] Official repository of DiffSim: Taming Diffusion Models for Evaluating Visual Similarity

No description.

Github repository for World-VLA-Loop.

[ICLR 2026] Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing

Official implementation of Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning

Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?

This is the project page of ShowRoom3D

TPDiff: Temporal Pyramid Video Diffusion Model

A V2V framework that translates human interaction videos into robot manipulation videos.

[ECCV 2022] AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant

[ICCV 2023] Label-Efficient Online Continual Object Detection in Streaming Video

The code implementation of **IDProtector: An Adversarial Noise Encoder to Protect Against ID-Preserving Image Generation**.

[Arxiv2022] Revitalize Region Feature for Democratizing Video-Language Pre-training

No description.

Official code implementation of "Mitty: Diffusion-based Human-to-Robot Video Generation"

[ECCV 2022] GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval

This is the project page for the HOSNeRF

[CVPR 2024] Tune-An-Ellipse: CLIP Has Potential to Find What You Want

No description.

Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance

No description.

Edit and Generate Anything in 3D world!

ACM MM 2025 Can I Trust You? Advancing GUI Task Automation with Action Trust Score

Repository of GUI Action Narrator

Implementation of StreamingEffect: Real-Time Human-Centric Video Effect Generation

[IJCV2023] Offical implementation of "SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels"

The code repository of UniMoD

No description.

The Pytorch implementation of "Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization"

Implementation of OmniHumanoid: Streaming Cross-Embodiment Video Generation with Paired-Free Adaptation

[ArXiv 2025] Personalized Vision via Visual In-Context Learning

The official code implementation of the paper “VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers“.

No description.

A comprehensive benchmark for evaluating text-to-film generation performance.

[TPAMI 2026] SAM-I2V++

This is the project page for ColonNeRF.

No description.

No description.

This is the project page for DynVideo-E.

Official Code of SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution

No description.

World-VLA-Loop Project Github Pages

P-Flow: Prompting Visual Effects Generation

A watermark plugin for latent diffusion models.

No description.

No description.

Revisit Parameter-Efficient Transfer Learning: A Two-Stage Paradigm

No description.

No description.

The website for aloha introduction

Open Multimodal Gathering workshop @ NUS

No description.

No description.

No description.

No description.