The Harmonix Set: Beats, Downbeats, and Structural Annotations for Pop Music

A concise but complete full-attention transformer with a set of promising experimental features from various papers

Vector (and Scalar) Quantization, in Pytorch

Curated papers on Large Language Models in Healthcare and Medical domain

[ICASSP'25] Larger Language Models Don't Care How You Think: Why Chain-of-Thought Prompting Fails in Subjective Tasks

Toward Fully-End-to-End Listened Speech Decoding from EEG Signals (Interspeech 2024)

Code for the paper titled "Knowledge-guided EEG Representation Learning"

This repository implements time series diffusion in the frequency domain.

MONAI Generative Models makes it easy to train, evaluate, and deploy generative models and related applications

[official] PyTorch implementation of TimeVQVAE from the paper ["Vector Quantized Time Series Generation with a Bidirectional Prior Model", AISTATS 2023]

Codebase for EA Modeling (for Transactions on Affective Computing paper)

[NeurIPS 2023, ICMI 2023] Quantifying & Modeling Multimodal Interactions

[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification

Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

This repository contains research code for the paper "Generating realistic neurophysiological time series with denoising diffusion probabilistic models". @jsvetter

Vision Foundation Models for Medical AI, including RETFound, DINOv2, DINOv3

Companion repository for the EUSIPCO-24 accepted paper "Pre-Training Music Classification Models via Music Source Separation"

A list of all public EEG-datasets

Code for reproducing the experiments and results of "Multi-Source Contrastive Learning from Musical Audio", accepted for publication in SMC2023

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.