Skip to content

@showlab Show Lab

Change the repository type filter

All

    Repositories list

    124 repositories

    • Adv-GRPO

      Public
      [CVPR 2026] An official implementation of Adv-GRPO. The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation.
      Python
      •
      MIT License
      •1•72•1•0•Updated Feb 26, 2026Feb 26, 2026

    • World-VLA-Loop

      Public
      Github repository for World-VLA-Loop.
      JavaScript
      •1•3•0•0•Updated Feb 25, 2026Feb 25, 2026

    • Awesome-Video-Diffusion

      Public
      A curated list of recent diffusion models for video generation, editing, and various other applications.
      awesomevideo-editingvideo-generationdiffusion-modelsmotion-customizationvideo-generation-evaluation
      340•5.5k•0•0•Updated Feb 23, 2026Feb 23, 2026

    • videogui

      Public
      [NeurIPS 2024 D&B] VideoGUI: A Benchmark for GUI Automation from Instructional Videos
      guivideo-languagellm-agent
      JavaScript
      •3•51•2•0•Updated Feb 22, 2026Feb 22, 2026

    • Edit2Perceive

      Public
      [CVPR 2026] Official Implementation of Edit2Perceive
      Python
      •0•30•1•0•Updated Feb 21, 2026Feb 21, 2026

    • Olaf-World

      Public
      Orienting Latent Actions for Video World Modeling
      genievideo-generationinteractive-videoworld-modellatent-action
      MIT License
      •0•78•1•0•Updated Feb 11, 2026Feb 11, 2026

    • FocusUI

      Public
      [CVPR 2026] FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
      Python
      •1•25•0•0•Updated Feb 10, 2026Feb 10, 2026

    • World-VLA-Loop-Pages

      Public
      World-VLA-Loop Project Github Pages
      JavaScript
      •0•3•0•0•Updated Feb 9, 2026Feb 9, 2026

    • showui-pi

      Public
      ShowUI-π: Flow-based Generative Models as GUI Dexterous Hands
      agentgui
      Python
      •
      Apache License 2.0
      •13•94•3•0•Updated Feb 6, 2026Feb 6, 2026

    • Q2A

      Public
      [ECCV 2022] AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
      Python
      •5•23•1•0•Updated Jan 30, 2026Jan 30, 2026

    • D-AR

      Public
      the official repo for "D-AR: Diffusion via Autoregressive Models"
      diffusion-modelsautoregressive-modelsllms
      Python
      •
      MIT License
      •2•135•2•0•Updated Jan 29, 2026Jan 29, 2026

    • macosworld

      Public
      Python
      •
      Other
      •1•25•0•0•Updated Jan 28, 2026Jan 28, 2026

    • DIM

      Public
      [ICLR 2026] Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
      Python
      •
      Other
      •0•25•0•0•Updated Jan 27, 2026Jan 27, 2026

    • T2F-Bench

      Public
      A comprehensive benchmark for evaluating text-to-film generation performance.
      0•5•0•0•Updated Jan 22, 2026Jan 22, 2026

    • whisperVideo

      Public
      Find out who said what in the video.
      videospeech-recognitionface-detectionspeech-to-textwhisperasr
      Jupyter Notebook
      •16•135•1•0•Updated Jan 22, 2026Jan 22, 2026

    • ShowUI

      Public
      [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.
      agentvision-language-modelvision-language-actioncomputer-usegui-agent
      Python
      •
      Apache License 2.0
      •131•1.7k•15•0•Updated Jan 20, 2026Jan 20, 2026

    • ShowUI-Aloha

      Public
      Human-taught Computer-use Agent Designed for Real Windows and MacOS Desktops.
      Python
      •
      Apache License 2.0
      •31•240•4•0•Updated Jan 20, 2026Jan 20, 2026

    • Mitty

      Public
      Official code implementation of "Mitty: Diffusion-based Human-to-Robot Video Generation"
      Python
      •2•16•2•0•Updated Jan 14, 2026Jan 14, 2026

    • Aloha_Page

      Public
      The website for aloha introduction
      HTML
      •0•0•0•0•Updated Jan 13, 2026Jan 13, 2026

    • Show-o

      Public
      [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.
      multimodaldiffusion-modelslarge-language-models
      Python
      •
      Apache License 2.0
      •88•1.9k•64•4•Updated Jan 8, 2026Jan 8, 2026

    • SAM-I2VPP

      Public
      [TPAMI 2026] SAM-I2V++
      Jupyter Notebook
      •
      Apache License 2.0
      •0•3•0•0•Updated Jan 7, 2026Jan 7, 2026

    • SAM-I2V

      Public
      [CVPR 2025] SAM-I2V
      Jupyter Notebook
      •
      Apache License 2.0
      •1•35•0•0•Updated Jan 2, 2026Jan 2, 2026

    • X-Humanoid

      Public
      Other
      •2•41•2•0•Updated Dec 20, 2025Dec 20, 2025

    • RobotSeg

      Public
      Apache License 2.0
      •0•37•2•0•Updated Dec 18, 2025Dec 18, 2025

    • TrustScorer

      Public
      ACM MM 2025 Can I Trust You? Advancing GUI Task Automation with Action Trust Score
      Python
      •
      MIT License
      •0•12•0•0•Updated Dec 17, 2025Dec 17, 2025

    • EVOLVE-VLA

      Public
      EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
      HTML
      •1•73•1•0•Updated Dec 17, 2025Dec 17, 2025

    • OmniPSD

      Public
      Official code implementation of "OmniPSD: Layered PSD Generation with Diffusion Transformer"
      Other
      •5•87•3•0•Updated Dec 13, 2025Dec 13, 2025

    • H2R-Grounder

      Public
      A V2V framework that translates human interaction videos into robot manipulation videos.
      1•22•1•0•Updated Dec 12, 2025Dec 12, 2025

    • WorldWander

      Public
      Official Pytorch Code of the Paper "WorldWander: Bridging Egocentric and Exocentric Worlds in Video Generation"
      virtual-realityperspective-transformationvideo-translationworld-modelvideo-genrationegocentric-exocentriccross-view-generation
      Python
      •2•22•3•1•Updated Dec 6, 2025Dec 6, 2025

    • AUI

      Public
      Computer-Use Agents as Judges for Generative UI
      Python
      •
      MIT License
      •5•43•1•0•Updated Nov 27, 2025Nov 27, 2025