LaVi Lab

AIM

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

CLEVA

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

LaVi-Lab.github.io

LongContextReasoner

[ACL 2024] Making Long-Context Language Models Better Multi-Hop Reasoners

Multimodal-Summit

NaviLLM

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

TG-Vid

[EMNLP 2024] Official code for "Enhancing Temporal Modeling of Video LLMs via Time Gating"

Video-3D-LLM

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

Visual-Table

[EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"

LaVi-Lab/Video-3D-LLM

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

LaVi-Lab/CLEVA

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

LaVi-Lab/AIM

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

LaVi-Lab/NaviLLM

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

LaVi-Lab/Visual-Table

[EMNLP 2024] Official code for "Beyond Embeddings: The Promise of Visual Table in Multi-Modal Models"

LaVi-Lab/LongContextReasoner

[ACL 2024] Making Long-Context Language Models Better Multi-Hop Reasoners

LaVi-Lab/TG-Vid

[EMNLP 2024] Official code for "Enhancing Temporal Modeling of Video LLMs via Time Gating"

LaVi-Lab/LaVi-Lab.github.io

LaVi-Lab/Multimodal-Summit