Hell-Mood

dino-tracker

Official Pytorch Implementation for “DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video”

Seg-LSTM

anole

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

SOFTS

Official implement for "SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion" in PyTorch.

diffusion-forcing

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

NetTrack

Official code for NetTrack [CVPR 2024]

UnSAM

Code release for "Segment Anything without Supervision"

ml-4m

4M: Massively Multimodal Masked Modeling

LLM101n

LLM101n: Let's build a Storyteller

BIRD

This is the official implementation of "Blind Image Restoration via Fast Diffusion Inversion"

vision-lstm

xLSTM as Generic Vision Backbone

llama-zip

LLM-powered lossless compression tool

tree-diffusion

Diffusion on syntax trees for program synthesis

nif_website

hailo_model_zoo

The Hailo Model Zoo includes pre-trained models and a full building and evaluation environment

mamba.np

A pure NumPy implementation of Mamba.

SFOD-RS

[IGARSS2024] Code for "CLIP-Guided Source-Free Object Detection in Aerial Images"

xlstm-resources

Resources about xLSTM by Sepp Hochreiter

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

mi_detection

An official PyTorch implementation of 'Deep Learning for Cardiologist-level Myocardial Infarction Detection in Electrocardiograms'

res_ae

Residual Auto Encoder...

resautonet

sort

Simple, online, and realtime tracking of multiple objects in a video sequence.

methcomp

Python package providing functionality and plotting for chemistry method comparison

TimeSeries-GAN

Generation of Time Series data using generatuve adversarial networks (GANs) for biological purposes.

ecgGAN

LSTM-GAN for generate plausible ECG signals

SE-ECGNet

conditional-flow-matching

TorchCFM: a Conditional Flow Matching library

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

DiffMOT

code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction