Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

Official implementation of our EMNLP 2022 paper "CPL: Counterfactual Prompt Learning for Vision and Language Models"

Refine high-quality datasets and visual AI models

Code for EmBERT, a transformer model for embodied, language-guided visual task completion.

Official code for the ACL 2021 Findings paper "Yichi Zhang and Joyce Chai. Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring"

Official code for the ACL 2021 Findings paper "Yichi Zhang and Joyce Chai. Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring"

Code release for Fried et al., Speaker-Follower Models for Vision-and-Language Navigation. in NeurIPS, 2018.

An open-source platform for Visual AI.

An open-source platform for Visual AI.

Episodic Transformer (E.T.) is a novel attention-based architecture for vision-and-language navigation. E.T. is based on a multimodal transformer that encodes language inputs and the full episode h…

Accepted by CVPR 2020.

Website that hosts the open-source explainable AI toolkit (XAITK). Built with Minimal Mistakes in Jekyll

NLP implementations like information-theoretic measures of distributional similarity, text preprocessing using shell commands, Naive Bayes text categorization model, Cocke-Younger-Kasami parsing.

Coin collector game in Microsoft TextWorld, and a simple RL agent solving it.

FiLM: Visual Reasoning with a General Conditioning Layer

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Evaluating and improving the faithfulness of the interpretations offered by Neural Module Networks

Cornell NLVR and NLVR2 are natural language grounding datasets. Each example shows a visual input and a sentence describing it, and is annotated with the truth-value of the sentence.

Cornell NLVR and NLVR2 are natural language grounding datasets. Each example shows a visual input and a sentence describing it, and is annotated with the truth-value of the sentence.

Lightweight visualization tool for neural attention mechanisms

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Cracking the Coding Interview 6th Ed. Python Solutions

Gaining Trust in AI through Explanations

Discourse Processing in Videos https://arxiv.org/abs/1903.02252