This article delves into the realm of model editing in Large Language Models (LLMs). The authors seek to understand its strengths and limitations, thus facilitating robust, realistic applications of communicative…
Continue readingThe article centers on a new decoding method named Permute-and-Flip (PF) decoder. This decoder exhibits robustness features akin to the standard sampling decoder, but it is provably up to 2x…
Continue readingThe paper discusses the challenges in evaluating large language models, including data contamination, prompt sensitivity, and benchmark creation cost. To address these, the authors propose a lossless data compression-based evaluation…
Continue readingThis study investigates adversarial attacks through the lens of diffusion models, but not for enhancing the adversarial robustness of image classifiers. The focus is on utilizing the diffusion model to…
Continue readingThe research explores the use of models such as BERT and HuBERT in dimensional speech emotion recognition. Despite their large dimensionality, these models are frequently used for emotion recognition tasks,…
Continue readingThe article presents a novel adversarial defense method leveraging sample distribution shifts and pretrained diffusion models. The proposed method exploits the discrepancy between normal and adversarial sample distributions to counter…
Continue readingResearchers developed a framework, ADV3D, to test the safety of self-driving vehicles (SDVs). The industry typically uses closed-loop simulation to test how SDVs interact in synthetic and real scenarios. However,…
Continue readingThe article presents STYLIST, a new method for novelty detection, which is the identification of meaningful deviations from established data distributions. It separates semantic changes, which are relevant to the…
Continue readingThe article discusses the development of VIC-KD, a technique for enhancing the robustness of keyword spotting (KWS) systems against adversarial attacks. KWS is a process of identifying predetermined words in…
Continue readingThe paper addresses the problem of estimating multi-label noise transition matrices in noisy multi-label learning. Given the challenges of collecting large-scale accurate labels, the authors propose using transition matrices to…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
