Popular repositories Loading

1. UnIVAL UnIVAL Public

   [TMLR23] Official implementation of UnIVAL: Unified Model for Image, Video, Audio and Language Tasks.

   Jupyter Notebook 224 22

2. ViCHA ViCHA Public

   [BMVC22] Official Implementation of ViCHA: "Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment"

   Jupyter Notebook 54 2

3. TFood TFood Public

   [CVPRW22] Official Implementation of T-Food: "Transformer Decoders with MultiModal Regularization for Cross-Modal Food Retrieval". Accepted at CVPR22 's MULA Workshop.

   HTML 29 7

4. eP-ALM eP-ALM Public

   [ICCV23] Official implementation of eP-ALM: Efficient Perceptual Augmentation of Language Models.

   Jupyter Notebook 27 1

5. EvALign-ICL EvALign-ICL Public

   [ICLR2024] (EvALign-ICL Benchmark) Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning

   Python 20

6. ima-lmms ima-lmms Public

   [NeurIPS2024] Official code for (IMA) Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs

   Python 14