IEEE

BAM-Net: Hardware Friendly Associative Memory Using Binary Dominant Weights and NAND Logic

Abstract: This paper presents BAM-Net, a hardware-efficient binarization algorithm designed for associative memory (AM) implementation. BAM-Net aims to reduce memory overhead, power consumption, and ...
IEEE

Document Binarization via Multi-resolutional Attention Model with DRD Loss

Abstract: Document binarization which separates text from background is a critical pre-processing step for many high level document analysis tasks. Conventional document binarization approaches tend ...
GitHub

A collection of simple python mini projects to enhance your Python skills.

Select an issue and ask to be assigned to it. Check existing scripts in the projects directory. Star this repository. On the python-mini-projects repo page, click the Fork button. Clone your forked ...
GitHub

for Accurate and Efficient LLMs

Train the model using Quantization-Aware Training (QAT) with the RaBiT approach. The codebase uses a generic RaBiTModel wrapper that works with any HuggingFace AutoModelForCausalLM architecture — no ...