Official implementation of OneDiffusion paper (CVPR 2025)

Code for the Molmo Vision-Language Model

The source code of ExFunTube

Refine high-quality datasets and visual AI models

MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.

Code for EMNLP 2018 paper "Commonsense for Generative Multi-Hop Question Answering Tasks"

Pytorch implementation of the Graph Attention Network model by Veličković et. al (2017, https://arxiv.org/abs/1710.10903)

Evaluation code for various unsupervised automated metrics for Natural Language Generation.

OpenGL 360° Video projector for A Memory Network Approach for Story-based Temporal Summarization of 360° Videos

🎥 Repository for our ICCV 2017 paper: A Read Write Network for Movie Story Understanding