3 papers
cs.CL2025
English K_Quantization of LLMs Does Not Disproportionately Diminish Multilingual Performance
Karl Audun Borgersen, Morten Goodwin
For consumer usage of locally deployed LLMs, the GGUF format and k\_quantization are invaluable tools for maintaining the performance of the original model while reducing it to siz…
cs.CV2023
CorrEmbed: Evaluating Pre-trained Model Image Similarity Efficacy with a Novel Metric
Karl Audun Kagnes Borgersen, Morten Goodwin, Jivitesh Sharma +3
Detecting visually similar images is a particularly useful attribute to look to when calculating product recommendations. Embedding similarity, which utilizes pre-trained computer…
cs.AI2022
A Comparison Between Tsetlin Machines and Deep Neural Networks in the Context of Recommendation Systems
Karl Audun Borgersen, Morten Goodwin, Jivitesh Sharma
Recommendation Systems (RSs) are ubiquitous in modern society and are one of the largest points of interaction between humans and AI. Modern RSs are often implemented using deep le…