Downloads
NNspectra
July 2019
This repo is a companion to the paper “A Fine-Grained Spectral Perspective on Neural Networks”.
Gaussian Process for Any Neural Architecture
February 2020
Gaussian Process for Any Neural Architecture: Reference Implementations This repo is a companion to the paper linked below, which shows that the Gaussian process behavior arises in wide, randomly initialized, neural networks regardless of architecture. Tensor Programs I: Wide Feedforward…
RaCT
April 2020
This repository implements Ranking-Critical Training (RaCT) for Collaborative Filtering, accepted in International Conference on Learning Representations (ICLR), 2020. By using an actor-critic architecture to fine-tune a differentiable collaborative filtering model, we can improve the performance of a variety of MLE-based…
imodelsX
November 2022
Scikit-learn friendly library to interpret, and prompt-engineer text datasets using large language models.
Admin-Torch
April 2022
Here, we provide a plug-in-and-play implementation of Admin, which stabilizes previously-diverged Transformer training and achieves better performance, without introducing additional hyper-parameters. The design of Admin is half-precision friendly and can be reparameterized into the original Transformer.
Microsoft KaggleDBQA Dataset: Realistic Evaluation of Text-to-SQL Parsers
July 2021
Microsoft KaggleDBQA is a cross-domain and complex evaluation dataset of real Web databases, with domain-specific data types, original formatting, and unrestricted questions. It also provides database documentation, which contain rich in-domain knowledge. The nature of obscure and abbreviated column/table names…
Focal Transformer
August 2021
This is a codebase for our recently released paper “Focal Self-attention for Local-Global Interactions in Vision Transformers”. It developed a new sparse self-attention mechanism called focal self-attention towards more effective and efficient vision transformers. The goal is the release the…
Visual Question Generation dataset
October 2016
We introduce this dataset in order to support the novel task of Visual Question Generation (VQG), where, given an image, the system should ‘ask a natural and engaging question’. This dataset can be used to support research on common sense…
SOLOIST
June 2021
This repository showcases building task-oriented bot at scale with handful examples via fine-tuning a pretrained model using SOLOIST framework, and contains the dataset, source code and pre-trained model for the following paper: SOLOIST: Building Task Bots at Scale with Transfer…