Popular GitHub Repositories for Minimum Description Length

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

Human: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris Analysis, Age & Gender & Emotion Prediction, Gaze Tracking, Gesture Recognition

? Must-read papers and blogs on LLM based Long Context Modeling ?

High-fidelity performance metrics for generative models in PyTorch

A collection of anomaly detection methods (iid/point-based, graph and time series) including active learning for anomaly detection/discovery, bayesian rule-mining, description for diversity/explanation/interpretability. Analysis of incorporating label feedback with ensemble and tree-based detectors. Includes adversarial attacks with Graph Convolutional Network.

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features

Transformer based on a variant of attention that is linear complexity in respect to sequence length

Implementation of Phenaki Video, which uses Mask GIT to produce text guided videos of up to 2 minutes in length, in Pytorch

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025)

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

Minimum-distortion embedding with PyTorch

Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.

Implementation of a Tensor Processing Unit for embedded systems and the IoT.

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.

A minimum unofficial implementation of the "A Convolutional Recurrent Neural Network for Real-Time Speech Enhancement" (CRN) using PyTorch