Fast and Computationally efficient Continual Learning for NanoDet anchor-free Object Detector

A robust and efficient TinyML inference engine.

Posture-based Infant Action Recognition in the Wild with Very Limited Data (CVPRW2023)

SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

[ICCV 2023] MI-GAN: A Simple Baseline for Image Inpainting on Mobile Devices

[ICPR 2024] Official implementation of SuperSimpleNet: Unifying Unsupervised and Supervised Learning for Fast and Reliable Surface Defect Detection

Quantized Attention that achieves speedups of 2.1x and 2.7x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

MeDetection

Blazingly fast LLM inference.

source code of "LSNet: Extremely lightweight Siamese Network for Change Detection in Remote Sensing Images"

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Unofficial implementation of EfficientAD https://arxiv.org/abs/2303.14535

On-device Speech Recognition for Apple Silicon

Kokkos C++ Performance Portability Programming Ecosystem: The Programming Model - Parallel Execution and Memory Abstraction

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.

A retargetable MLIR-based machine learning compiler and runtime toolkit.

Official inference framework for 1-bit LLMs

SecLists is the security tester's companion. It's a collection of multiple types of lists used during security assessments, collected in one place. List types include usernames, passwords, URLs, se…

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

An open-source implementaion for fine-tuning Phi3-Vision and Phi3.5-Vision by Microsoft.

《MATHEMATICS FOR MACHINE LEARNING》 一书的部分翻译。

A curated list of awesome mathematics resources

Open-source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks

The Canny Edge Detection algorithm is implemented on an FPGA using only Verilog code and no Intellectual Property, making it convenient to replicate using any simulator and any of the available FPG…

Machine learning on FPGAs using HLS

Vitis Libraries

A multi-level tensor algebra superoptimizer

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[CVPR2024] Efficient Dataset Distillation via Minimax Diffusion