Yizhou Wang

A Large-scale Attribute Dataset for Zero-shot Learning

2018 · arXiv (Cornell University)

Zero-Shot Learning (ZSL) has attracted huge research attention over the past few years; it aims to learn the new concepts that have never been seen before. In classical ZSL algorithms, attributes are introduced as the …

SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation

2021 · arXiv (Cornell University)

Anomaly detection is a fundamental yet challenging problem in machine learning due to the lack of label information. In this work, we propose a novel and powerful framework, dubbed as SLA$^2$P, for unsupervised anomaly detection. …

Which Invariance Should We Transfer? A Causal Minimax Learning Approach

2021 · arXiv (Cornell University)

A major barrier to deploying current machine learning models lies in their non-reliability to dataset shifts. To resolve this problem, most existing studies attempted to transfer stable information to unseen environments. Particularly, independent causal mechanisms-based …

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

2023 · arXiv (Cornell University)

In this paper, we introduce the BeaverTails dataset, aimed at fostering research on safety alignment in large language models (LLMs). This dataset uniquely separates annotations of helpfulness and harmlessness for question-answering pairs, thus offering distinct …