2 papers
cs.CV2025
Dual Codebook VQ: Enhanced Image Reconstruction with Reduced Codebook Size
Parisa Boodaghi Malidarreh, Jillur Rahman Saurav, Thuong Le Hoai Pham +5
Vector Quantization (VQ) techniques face significant challenges in codebook utilization, limiting reconstruction fidelity in image modeling. We introduce a Dual Codebook mechanism…
cs.CL2024
Evaluating Text Classification Robustness to Part-of-Speech Adversarial Examples
Anahita Samadi, Allison Sullivan
As machine learning systems become more widely used, especially for safety critical applications, there is a growing need to ensure that these systems behave as intended, even in t…