Skip to content
@dvlab-research

DV Lab

Deep Vision Lab

Popular repositories Loading

  1. MGM MGM Public

    Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

    Python 3.3k 279

  2. LongLoRA LongLoRA Public

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

    Python 2.7k 294

  3. LISA LISA Public

    Project Page for "LISA: Reasoning Segmentation via Large Language Model"

    Python 2.5k 191

  4. DreamOmni2 DreamOmni2 Public

    This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

    Python 2.4k 203

  5. ControlNeXt ControlNeXt Public

    Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

    Python 1.6k 80

  6. SNR-Aware-Low-Light-Enhance SNR-Aware-Low-Light-Enhance Public

    This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022

    Python 940 97

Repositories

Showing 10 of 88 repositories
  • UnityVideo Public

    This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"

    dvlab-research/UnityVideo’s past year of commit activity
    25 MIT 0 0 0 Updated Dec 9, 2025
  • MGM-Omni Public

    MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech

    dvlab-research/MGM-Omni’s past year of commit activity
    Python 263 Apache-2.0 17 3 0 Updated Nov 17, 2025
  • Scaf-GRPO Public

    Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning

    dvlab-research/Scaf-GRPO’s past year of commit activity
    Python 9 0 1 0 Updated Oct 25, 2025
  • SmartSwitch Public

    SmartSwitch: Advancing LLM Reasoning by Overcoming Underthinking via Promoting Deeper Thought Exploration

    dvlab-research/SmartSwitch’s past year of commit activity
    Python 6 0 0 0 Updated Oct 23, 2025
  • DreamOmni2 Public

    This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''

    dvlab-research/DreamOmni2’s past year of commit activity
    Python 2,428 Apache-2.0 203 23 0 Updated Oct 20, 2025
  • VisionReasoner Public

    Vision Manus: Your versatile Visual AI assistant

    dvlab-research/VisionReasoner’s past year of commit activity
    Python 302 Apache-2.0 15 0 0 Updated Oct 12, 2025
  • VisionThink Public

    [NeurIPS 2025] Efficient Reasoning Vision Language Models

    dvlab-research/VisionThink’s past year of commit activity
    Python 425 Apache-2.0 29 12 0 Updated Sep 18, 2025
  • LSDBench Public

    A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency of long-video VLMs. (ICCV2025)

    dvlab-research/LSDBench’s past year of commit activity
    Python 24 Apache-2.0 0 0 0 Updated Aug 7, 2025
  • Jenga Public

    [NeurIPS 2025] Training-Free Efficient Video Generation via Dynamic Token Carving

    dvlab-research/Jenga’s past year of commit activity
    Python 258 12 9 0 Updated Aug 4, 2025
  • Seg-Zero Public

    Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

    dvlab-research/Seg-Zero’s past year of commit activity
    Python 574 Apache-2.0 26 5 0 Updated Jul 30, 2025
View all repositories