Skip to content
@GeWu-Lab

GeWu-Lab

Hi there 👋

This is the official account of GeWu-Lab. GeWu-Lab is a research group focusing on multimodal perception, interaction, and learning, we will post/release the source code/resources of most of our research projects here. Expecting your star ⭐

Nice To Meet You!

Pinned Loading

  1. MokA MokA Public

    MokA: Multimodal Low-Rank Adaptation for MLLMs

    Python 81 6

  2. OGM-GE_CVPR2022 OGM-GE_CVPR2022 Public

    The repo for "Balanced Multimodal Learning via On-the-fly Gradient Modulation", CVPR 2022 (ORAL)

    Python 311 23

  3. Crab Crab Public

    [CVPR 2025] Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation

    Python 80 3

  4. MUSIC-AVQA MUSIC-AVQA Public

    MUSIC-AVQA, CVPR2022 (ORAL)

    Python 96 9

  5. AnyTouch AnyTouch Public

    The repo for "AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors", ICLR 2025

    Python 84 8

  6. Action-Preference-Optimization Action-Preference-Optimization Public

    Python 13 3

Repositories

Showing 10 of 54 repositories
  • GeWu-Lab/gewu-lab.github.io’s past year of commit activity
    HTML 1 1 0 0 Updated Mar 3, 2026
  • APPO Public

    The official repository for CVPR'26 Paper "APPO: Attention-guided Perception Policy Optimization for Video Reasoning"

    GeWu-Lab/APPO’s past year of commit activity
    4 Apache-2.0 0 0 0 Updated Mar 3, 2026
  • awesome-balanced-multimodal-learning Public

    A curated list of balanced multimodal learning methods.

    GeWu-Lab/awesome-balanced-multimodal-learning’s past year of commit activity
    160 5 2 0 Updated Mar 2, 2026
  • AnyTouch2 Public

    [ICLR 2026] AnyTouch 2: General Optical Tactile Representation Learning For Dynamic Tactile Perception

    GeWu-Lab/AnyTouch2’s past year of commit activity
    Python 20 MIT 2 0 0 Updated Feb 27, 2026
  • GAP Public

    [ICLR 2026] When would Vision-Proprioception Policies Fail in Robotic Manipulation?

    GeWu-Lab/GAP’s past year of commit activity
    Python 1 0 0 0 Updated Feb 11, 2026
  • MIBench Public
    GeWu-Lab/MIBench’s past year of commit activity
    0 0 0 0 Updated Jan 25, 2026
  • LFAV Public

    Towards Long Form Audio-visual Video Understanding

    GeWu-Lab/LFAV’s past year of commit activity
    Python 15 MIT 0 1 0 Updated Jan 16, 2026
  • AnyTouch Public

    The repo for "AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors", ICLR 2025

    GeWu-Lab/AnyTouch’s past year of commit activity
    Python 84 MIT 8 2 0 Updated Jan 13, 2026
  • MokA Public

    MokA: Multimodal Low-Rank Adaptation for MLLMs

    GeWu-Lab/MokA’s past year of commit activity
    Python 81 6 13 0 Updated Dec 30, 2025
  • Crab Public

    [CVPR 2025] Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation

    GeWu-Lab/Crab’s past year of commit activity
    Python 80 3 4 0 Updated Dec 24, 2025

Most used topics

Loading…