Must-read Papers on Knowledge Editing for Large Language Models.

A faithful benchmark for vision-language compositionality

An open source implementation of CLIP.

MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions

Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning with LLMs

Meta-prompt: a simple self-improving language agent

Toolkit for Elevater Benchmark

NF-Layers as described in this paper: https://arxiv.org/abs/2302.14040

Code for Finetune like you pretrain: Improved finetuning of zero-shot vision models

The KiloGram Tangrams dataset

A Diagnostic Benchmark for Evaluating Logical Robustness of Deductive Reasoners

A simple script to extract scores of publicly available ICLR submissions from OpenReview.

Python 3.6+ toolbox for submitting jobs to Slurm

Small Python library to automatically set CUDA_VISIBLE_DEVICES to the least loaded device on multi-GPU systems.

Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction"

Oscar and VinVL

Robust fine-tuning of zero-shot models

This is the official implementation of NeurIPS 2021 "One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval".

Scripts to generate the CoDraw and i-CLEVR datasets used for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic i…

Code for the ICML 2021 (long talk) paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

Pytorch lightning + hydra + neptune template for LM finetuning

Discretized Integrated Gradients for Explaining Language Models (EMNLP 2021)