IEEE

Feature Space Quantization and Application of Metrics in Structural Methods of Image Recognition

Abstract: This research aims to simplify the decision-making rules and reduce computational load when using structural methods of image classification that employ a description in the form of a set of ...
GitHub

LQER: Low-Rank Quantization Error Reconstruction for LLMs

LQER runs a high-rank low-precision GEMM and a group of low-rank high-precision GEMMs in parallel to push the limitation of lossless LLM PTQ. The DeepWok Lab, is an ML research group led by Dr. Aaron ...
GitHub

Oaken: Fast and Efficient LLM Serving with Online-Offline Hybrid KV Cache Quantization

Oaken is an accleration solution that achieves high accuracy and high performance simultaneously through co-designing algorithm and hardware, leveraging online ...
IEEE

Diagnosing and Improving Vector-Quantization-Based Blind Image Restoration

Abstract: Vector-Quantization (VQ) based discrete generative models are widely used to learn powerful high-quality (HQ) priors for blind image restoration (BIR). In this paper, we diagnose the ...