K
Kai-Wei Chang
Researcher at University of California, Los Angeles
Publications - 262
Citations - 23031
Kai-Wei Chang is an academic researcher from University of California, Los Angeles. The author has contributed to research in topics: Computer science & Word embedding. The author has an hindex of 42, co-authored 183 publications receiving 17271 citations. Previous affiliations of Kai-Wei Chang include Boston University & Amazon.com.
Papers
More filters
Training and Testing Low-degree Polynomial Data Mappings via
Linear Svm,Yin-Wen Chang,Cho-Jui Hsieh,Kai-Wei Chang,Michael Ringgaard,Amphitheatre Parkway,Chih-Jen Lin +6 more
TL;DR: In this article, the authors apply fast linear-SVM methods to the explicit form of polynomially mapped data and investigate implementation issues, which may sometimes achieve accuracy close to that of using highly nonlinear kernels.
Journal Article
Generating universal language adversarial examples by understanding and enhancing the transferability across neural models
TL;DR: This paper systematically study the transferability of adversarial attacks for text classification models and proposes universal black-box attack algorithms that can induce adversarial examples to attack almost all existing models.
Journal ArticleDOI
DesCo: Learning Object Recognition with Rich Language Descriptions
TL;DR: Zhang et al. as discussed by the authors proposed a new description-conditioned (DesCo) paradigm of learning object recognition models with rich language descriptions consisting of two major innovations: 1) employ a large language model as a commonsense knowledge engine to generate rich language description of objects based on object names and the raw image-text caption; 2) design context-sensitive queries to improve the model's ability in deciphering intricate nuances embedded within descriptions and enforce the model to focus on context rather than object names alone.
Journal ArticleDOI
SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts
TL;DR: SpeechGen as discussed by the authors explores the application of prompt tuning to stimulate speech LMs for various generation tasks, within a unified framework called SpeechGen, with around 10M trainable parameters.
Posted Content
LOGAN: Local Group Bias Detection by Clustering
Jieyu Zhao,Kai-Wei Chang +1 more
TL;DR: This paper proposed a new bias detection technique based on clustering, called LOGAN, which identifies bias in a local region and allows them to better analyze the biases in model predictions and detect such local bias.