Stars
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
Repository for CARTE: Context-Aware Representation of Table Entries
MAGI-1: Autoregressive Video Generation at Scale
An open source implementation of CLIP.
tulip-berkeley / open_clip
Forked from mlfoundations/open_clipAn open source implementation of CLIP (With TULIP Support)
A fast Lomb-Scargle periodogram. It's nifty, and uses a NUFFT!
Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
ORACLE - The first hierarchical deep-learning model for real-time, context-aware classification of the LSST alert stream
Astronomical Transformer for time series And Tabular data
A codebase dedicated to exploring multimodal learning approaches by integrating images of host galaxies of supernovae and their corresponding light-curves and spectra.
High accuracy RAG for answering questions from scientific documents with citations
Unified Training of Universal Time Series Forecasting Transformers
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the …
Code to reproduce results in the paper, deepCR: Cosmic Ray Rejection with Deep Learning (Zhang & Bloom (2019))
Deep Learning Based Cosmic Ray Removal for Astronomical Images
An extremely fast Python package and project manager, written in Rust.
A collaborative platform for reproducible research (web interface and CLI).
A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems", which is `dmls-book`
LaTeX Template with an example Statement of Purpose (SoP) for CS PhD and graduate school applicants.
Large-Scale Multimodal Dataset of Astronomical Data
AIHawk aims to easy job hunt process by automating the job application process. Utilizing artificial intelligence, it enables users to apply for multiple jobs in a tailored way.
Extensible, parallel implementations of t-SNE
The most impactful papers related to contrastive pretraining for multimodal models!
A playbook for systematically maximizing the performance of deep learning models.
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Source code for models described in the paper "AudioCLIP: Extending CLIP to Image, Text and Audio" (https://arxiv.org/abs/2106.13043)
The code of GaSNet-II. Arxiv: https://arxiv.org/abs/2311.04146
A Library for Advanced Deep Time Series Models for General Time Series Analysis.