Jocelyn Xu

Singer-Informed Vocal Source Separation for Multi-Singer Music Mixtures

Jocelyn Xu, Minje Kim

Music source separation systems typically extract a single vocal track and do not distinguish between multiple singers. We study singer-informed vocal source separation for multi-singer mixtures. Our framework introduces a short enrollment recording of a target singer to guide separation through a …

Distorting the witness: how digital mediation shapes contemporary understandings of wartime sexual violence in the Anti-Japanese War

Jocelyn Xu

This article examines the Shoah Foundation's New Dimensions in Testimony (NDT) project, which interviews and records the memories of Holocaust and other wartime survivors to create their interactive digital representations. Specifically, this article focuses on two Chinese women. One participant, Xia Shuqin, …

gb (code pays fourni par la source)

That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation

Jae‐Sung Bae, Cameron Churchwell, Mitchell Hermon, Tsun-An Hsieh et autres

This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we extend the investigation of knowledge conflicts to the realm of code …

D-CryptO: deep learning-based analysis of colon organoid morphology from brightfield images

Lyan Abdul, Jocelyn Xu, Alexander Sotra, Abbas Chaudary et autres

Stem cell-derived organoids are a promising tool to model native human tissues as they resemble human organs functionally and structurally compared to traditional monolayer cell-based assays. For instance, colon organoids can spontaneously develop crypt-like structures similar to those found in the native …

ca (code pays fourni par la source)