Skip to content

@Visual-AI Visual AI Lab

Change the repository type filter

All

    Repositories list

    31 repositories

    • visual-ai.github.io

      Public
      JavaScript
      •16•0•0•0•Updated Jun 14, 2026Jun 14, 2026

    • SPoT

      Public
      Official code for paper "Surgical Post-Training: Cutting Errors, Keeping Knowledge"
      Python
      •1•18•1•0•Updated Jun 6, 2026Jun 6, 2026

    • v-CLR

      Public
      [CVPR 2025 Highlight] v-CLR: View-Consistent Learning for Open-World Instance Segmentation
      highlightdetropen-world-instance-segmentation
      highlightdetropen-world-instance-segmentationcvpr2025
      Python
      •
      MIT License
      •4•21•2•0•Updated May 31, 2026May 31, 2026

    • iVGR

      Public
      [ICML 2026] iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
      Python
      •
      Apache License 2.0
      •0•6•1•0•Updated May 26, 2026May 26, 2026

    • CodeBind

      Public
      [ACL 2026 Findings] CodeBind: Decoupled Representation Learning for Multimodal Alignment with Unified Compositional Codebook
      representation-learningmultimodal
      representation-learningmultimodal
      Python
      •
      MIT License
      •1•4•0•0•Updated May 19, 2026May 19, 2026

    • GAMEBoT

      Public
      [ACL 2025] GAMEBoT: Transparent Assessment of LLM Reasoning in Games
      benchmarkgamesatari
      benchmarkgamesatarievalllm
      Python
      •4•33•0•0•Updated May 15, 2026May 15, 2026

    • sculpt4d

      Public
      Sculpt4D: Generating 4D Shapes via Sparse-Attention Diffusion Transformers — Project Page
      0•2•0•0•Updated Apr 26, 2026Apr 26, 2026

    • speed3r

      Public
      [CVPR 2026 Findings] Speed3R: Sparse Feed-forward 3D Reconstruction Models
      Python
      •
      BSD 3-Clause "New" or "Revised" License
      •3•72•1•0•Updated Apr 7, 2026Apr 7, 2026

    • SEAL

      Public
      [NeurIPS 2025] SEAL: Semantic-Aware Hierarchical Learning for Generalized Category Discovery
      open-world-learninggeneralized-category-discoveryneurips-2025
      open-world-learninggeneralized-category-discoveryneurips-2025
      Python
      •3•16•0•0•Updated Apr 4, 2026Apr 4, 2026

    • Category-Discovery

      Public
      [ArXiv2025] Category Discovery: An Open-World Perspective
      surveygeneralized-category-discoverycategory-discovery
      surveygeneralized-category-discoverycategory-discovery
      1•15•0•0•Updated Mar 17, 2026Mar 17, 2026

    • Awesome-Category-Discovery

      Public
      novel-category-discoverygeneralized-category-discoverycategory-discovery
      novel-category-discoverygeneralized-category-discoverycategory-discovery
      1•4•0•0•Updated Mar 17, 2026Mar 17, 2026

    • ICE

      Public
      [CVPR2025 Highlight] ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models
      Python
      •0•19•0•0•Updated Mar 3, 2026Mar 3, 2026

    • Pancap

      Public
      [NeurIPS 2025] Panoptic Captioning: An Equivalence Bridge for Image and Text
      Python
      •
      MIT License
      •0•38•0•0•Updated Jan 31, 2026Jan 31, 2026

    • LooC

      Public
      LooC: Effective Low-Dimentional Codebook for Compositional Vector Quantization
      Python
      •
      MIT License
      •0•2•0•0•Updated Jan 7, 2026Jan 7, 2026

    • JoVA

      Public
      JoVA: Unified Multimodal Learning for Joint Video-Audio Generation
      0•33•1•0•Updated Dec 22, 2025Dec 22, 2025

    • Fin3R

      Public
      [NeurIPS 2025] Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation
      Python
      •
      Other
      •2•60•3•0•Updated Dec 18, 2025Dec 18, 2025

    • Semantic-Correspondence

      Public
      [TPAMI 2025] Semantic Correspondence: Unified Benchmarking and a Strong Baseline
      Python
      •0•20•0•0•Updated Dec 11, 2025Dec 11, 2025

    • Awesome-Semantic-Correspondence

      Public
      A collection of papers on semantic correspondence, organized by year.
      2•30•0•0•Updated Dec 10, 2025Dec 10, 2025

    • 3DRS

      Public
      [NeurIPS 2025] 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
      Python
      •
      Apache License 2.0
      •0•157•4•0•Updated Dec 9, 2025Dec 9, 2025

    • Inpaint4Drag

      Public
      [ICCV 2025] Inpaint4Drag: Repurposing Inpainting Models for Drag-Based Image Editing via Bidirectional Warping
      Python
      •
      Apache License 2.0
      •10•95•0•0•Updated Nov 30, 2025Nov 30, 2025

    • HypCD

      Public
      [CVPR 2025] Hyperbolic Category Discovery
      Python
      •
      MIT License
      •3•30•0•0•Updated Nov 7, 2025Nov 7, 2025

    • DebGCD

      Public
      [ICLR 2025] DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery
      Python
      •
      MIT License
      •1•16•0•0•Updated Sep 27, 2025Sep 27, 2025

    • Mr.DETR

      Public
      [CVPR 2025] Mr. DETR: Instructive Multi-Route Training for Detection Transformers
      detectiondetrcvpr2025
      detectiondetrcvpr2025
      Python
      •
      MIT License
      •12•174•7•0•Updated Sep 6, 2025Sep 6, 2025

    • HiLo

      Public
      [ICLR2025] HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts
      Python
      •2•21•3•0•Updated Aug 1, 2025Aug 1, 2025

    • PruneVid

      Public
      [ACL 2025] PruneVid: Visual Token Pruning for Efficient Video Large Language Models
      Python
      •1•71•2•0•Updated May 15, 2025May 15, 2025

    • SPTNet

      Public
      [ICLR2024] SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
      Python
      •
      Other
      •3•36•0•0•Updated Apr 9, 2025Apr 9, 2025

    • PromptCCD

      Public
      [ECCV2024] PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery
      Python
      •6•30•0•0•Updated Apr 3, 2025Apr 3, 2025

    • FROSTER

      Public
      [ICLR 2024] FROSTER: Frozen CLIP is a Strong Teacher for Open-Vocabulary Action Recognition
      Python
      •
      Other
      •7•101•1•0•Updated Jan 14, 2025Jan 14, 2025

    • RegionDrag

      Public
      [ECCV2024] RegionDrag: Fast Region-Based Image Editing with Diffusion Models
      Python
      •4•67•2•0•Updated Oct 9, 2024Oct 9, 2024

    • SCD

      Public
      [CVPRW2024] What’s in a Name? Beyond Class Indices for Image Recognition
      Python
      •1•17•0•0•Updated Aug 30, 2024Aug 30, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.