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

Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey

2014_IEEE Multimedia_PRVQ_Projected residual vector quantization for ANN search. [IEEE] 2015_arXiv_IRVQ_Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search. ...
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 ...