3 papers
cs.CV2024
Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model
Huan Ma, Yan Zhu, Changqing Zhang +5
Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, th…
cs.LG2023
Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Huan Ma, Changqing Zhang, Huazhu Fu +2
Nowadays, billions of people engage in communication and express their opinions on the internet daily. Unfortunately, not all of these expressions are friendly or compliant, making…
cs.CV2023
Semantic Equivariant Mixup
Zongbo Han, Tianchi Xie, Bingzhe Wu +2
Mixup is a well-established data augmentation technique, which can extend the training distribution and regularize the neural networks by creating ''mixed'' samples based on the la…