Skip to content

@LaVi-Lab LaVi Lab

Change the repository type filter

All

    Repositories list

    14 repositories

    • EgoMask

      Public
      [ICCV 2025] "Fine-grained Spatiotemporal Grounding on Egocentric Videos"
      Python
      •0•7•0•0•Updated Aug 4, 2025Aug 4, 2025

    • VG-LLM

      Public
      The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'
      spatial-reasoning3d-scene-understandingmllm
      Jupyter Notebook
      •2•102•6•0•Updated Aug 3, 2025Aug 3, 2025

    • AIM

      Public
      [ICCV 2025] Official code for "AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning"
      Python
      •
      Apache License 2.0
      •2•37•1•0•Updated Jun 26, 2025Jun 26, 2025

    • Video-3D-LLM

      Public
      [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.
      Python
      •
      Apache License 2.0
      •10•143•5•0•Updated Jun 4, 2025Jun 4, 2025

    • LaVi-Lab.github.io

      Public
      JavaScript
      •
      BSD 3-Clause "New" or "Revised" License
      •0•0•0•0•Updated Jun 2, 2025Jun 2, 2025

    • C2LEVA

      Public
      [Findings of ACL 2025] "C2LEVA: Toward Comprehensive and Contamination-Free Language Model Evaluation"
      nlpbenchmarkcontamination
      Other
      •0•2•0•0•Updated May 27, 2025May 27, 2025

    • CLEVA

      Public
      [EMNLP 2023 Demo] "CLEVA: Chinese Language Models EVAluation Platform"
      nlpevaluationenglishchinesecontamination
      Shell
      •
      Other
      •3•63•1•0•Updated May 16, 2025May 16, 2025

    • FTTT

      Public
      [ACL 2025] Official code for ''Learning to Reason from Feedback at Test-Time''.
      Python
      •
      MIT License
      •0•11•0•0•Updated May 16, 2025May 16, 2025

    • Visual-Table

      Public
      [EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"
      Python
      •
      Apache License 2.0
      •1•20•0•0•Updated Oct 17, 2024Oct 17, 2024

    • TG-Vid

      Public
      [EMNLP 2024] Official code for "Enhancing Temporal Modeling of Video LLMs via Time Gating"
      Python
      •0•6•0•0•Updated Oct 10, 2024Oct 10, 2024

    • LongContextReasoner

      Public
      [ACL 2024] Making Long-Context Language Models Better Multi-Hop Reasoners
      Python
      •
      MIT License
      •0•16•0•0•Updated May 28, 2024May 28, 2024

    • Multimodal-Summit

      Public
      CSS
      •
      Creative Commons Zero v1.0 Universal
      •0•0•0•0•Updated Apr 11, 2024Apr 11, 2024

    • NaviLLM

      Public
      [CVPR 2024] The code for paper 'Towards Learning a Generalist Model for Embodied Navigation'
      Python
      •
      MIT License
      •14•46•0•0•Updated Apr 11, 2024Apr 11, 2024

    • MVT-3DVG

      Public
      [CVPR 2022] Multi-View Transformer for 3D Visual Grounding
      C++
      •5•1•0•0•Updated Nov 9, 2022Nov 9, 2022