Skip to content
@LaVi-Lab

LaVi Lab

We are the Language and Vision (LaVi) Lab in CSE@CUHK led by Prof. Liwei Wang.

Popular repositories Loading

  1. VG-LLM VG-LLM Public

    The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'

    Jupyter Notebook 258 10

  2. Video-3D-LLM Video-3D-LLM Public

    [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.

    Python 223 15

  3. AIM AIM Public

    [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"

    Python 65 4

  4. CLEVA CLEVA Public

    [EMNLP 2023 Demo] "CLEVA: Chinese Language Models EVAluation Platform"

    Shell 64 3

  5. NaviLLM NaviLLM Public

    Forked from zd11024/NaviLLM

    [CVPR 2024] The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'

    Python 62 4

  6. EgoMask EgoMask Public

    [ICCV 2025] "Fine-grained Spatiotemporal Grounding on Egocentric Videos"

    Python 27 1

Repositories

Showing 10 of 16 repositories
  • EgoMask Public

    [ICCV 2025] "Fine-grained Spatiotemporal Grounding on Egocentric Videos"

    LaVi-Lab/EgoMask's past year of commit activity
    Python 27 1 2 0 Updated Aug 26, 2026
  • LaVi-Lab/LaVi-Lab.github.io's past year of commit activity
    JavaScript 1 BSD-3-Clause 1 0 0 Updated Aug 15, 2026
  • IntentEdit Public

    Implementation of "IntentEdit: Multi-Agent Reasoning for Intent-Driven Complex Image Editing"

    LaVi-Lab/IntentEdit's past year of commit activity
    Python 3 0 0 0 Updated Apr 8, 2026
  • Rethink_CoT_Video Public

    Official code for "Rethinking Chain-of-Thought Reasoning for Videos"

    LaVi-Lab/Rethink_CoT_Video's past year of commit activity
    21 0 1 0 Updated Dec 14, 2025
  • VG-LLM Public

    The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'

    LaVi-Lab/VG-LLM's past year of commit activity
    Jupyter Notebook 258 10 18 0 Updated Nov 28, 2025
  • AIM Public

    [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"

    LaVi-Lab/AIM's past year of commit activity
    Python 65 Apache-2.0 4 0 0 Updated Oct 9, 2025
  • Video-3D-LLM Public

    [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.

    LaVi-Lab/Video-3D-LLM's past year of commit activity
    Python 223 Apache-2.0 15 10 0 Updated Jun 4, 2025
  • C2LEVA Public

    [Findings of ACL 2025] "C2LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation"

    LaVi-Lab/C2LEVA's past year of commit activity
    2 0 0 0 Updated May 27, 2025
  • CLEVA Public

    [EMNLP 2023 Demo] "CLEVA: Chinese Language Models EVAluation Platform"

    LaVi-Lab/CLEVA's past year of commit activity
    Shell 64 3 1 0 Updated May 16, 2025
  • FTTT Public

    [ACL 2025] Official code for ''Learning to Reason from Feedback at Test-Time''.

    LaVi-Lab/FTTT's past year of commit activity
    Python 13 MIT 0 0 0 Updated May 16, 2025

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Most used topics