Scientific Software
Updated 6 months ago

Multi-view-AE — Peer-reviewed • Rank 5.5 • Science 100%

Multi-view-AE: A Python package for multi-view autoencoder models - Published in JOSS (2023)

Updated 6 months ago

uform • Rank 15.6 • Science 64%

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Updated 6 months ago

tyc-dataset • Rank 2.3 • Science 54%

Official and maintained implementation of the dataset paper "The TYC Dataset for Understanding Instance-Level Semantics and Motions of Cells in Microstructures" [ICCVW 2023].

Updated 6 months ago

player-compatibality-and-win-pred-in-dota2-using-graph-neural-networks • Rank 2.1 • Science 44%

A GNN based approach to model player compatibility in Multiplayer Online Battle Arena (MOBA) games like Dota2.

Updated 5 months ago

https://github.com/alleninstitute/coupledae-patchseq • Rank 2.4 • Science 36%

Multimodal data alignment and cell type analysis with coupled autoencoders.

Updated 5 months ago

https://github.com/araffin/robotics-rl-srl • Rank 8.4 • Science 23%

S-RL Toolbox: Reinforcement Learning (RL) and State Representation Learning (SRL) for Robotics

Updated 5 months ago

https://github.com/astrazeneca/subtab • Rank 5.0 • Science 10%

The official implementation of the paper, "SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning"

Updated 6 months ago

speech-utility-bioacoustics • Science 67%

On the utility of speech and audio foundation models for marmoset call analysis

Updated 6 months ago

tsde • Science 41%

TSDE is a novel SSL framework for TSRL, the first of its kind, effectively harnessing a diffusion process, conditioned on an innovative dual-orthogonal Transformer encoder architecture with a crossover mechanism, and employing a unique IIF mask strategy (KDD 2024, main research track).

Updated 6 months ago

mergevq • Science 54%

[CVPR] MergeVQ: A Unified Framework for Visual Generation and Representation with Token Merging and Quantization

Updated 6 months ago

ssl-caller-detection • Science 57%

Source code for the paper 'Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?' by E. Sarkar and M. Magimai Doss (2023).

Updated 5 months ago

https://github.com/aida-ugent/nrl4lp • Science 23%

Instructions for replicating the experiments in the paper "Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?" (DSAA2020)

Updated 5 months ago

https://github.com/aiot-mlsys-lab/cate • Science 10%

[ICML 2021 Oral] "CATE: Computation-aware Neural Architecture Encoding with Transformers" by Shen Yan, Kaiqiang Song, Fei Liu, Mi Zhang

Updated 5 months ago

https://github.com/aiot-mlsys-lab/arch2vec • Science 10%

[NeurIPS 2020] "Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?" by Shen Yan, Yu Zheng, Wei Ao, Xiao Zeng, Mi Zhang

Updated 6 months ago

viscy • Science 67%

computer vision models for single-cell phenotyping

Updated 6 months ago

syncx • Science 54%

Official code repository for NeurIPS 2024 paper "Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery"

Updated 6 months ago

maskedfacerepresentation • Science 39%

Masked face recognition focuses on identifying people using their facial features while they are wearing masks. We introduce benchmarks on face verification based on masked face images for the development of COVID-safe protocols in airports.

Updated 5 months ago

https://github.com/alfa-group/code-representations-ml-brain • Science 10%

[NeurIPS 2022] "Convergent Representations of Computer Programs in Human and Artificial Neural Networks" by Shashank Srikant*, Benjamin Lipkin*, Anna A. Ivanova, Evelina Fedorenko, Una-May O'Reilly.

Updated 5 months ago

https://github.com/berenslab/medical-t-simcne • Science 23%

This repository contains the codes to train a t-SimCNE model. This model has been shown to produce good representations on natural and medical images.

Updated 5 months ago

https://github.com/cardiokit/vecg • Science 36%

Representational Learning of Single-Lead Electrocardiogram Signals using Beta-TCVAE