← Search

Hangyu Liu

3 accepted papers

2026

Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach

AAAI 2026technical

Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches for multi-target attacks primarily encode target labels into

Cited by 0SourcePDFScholar
2024

SongCreator: Lyrics-based Universal Song Generation

NeurIPS 2024poster

Music is an integral part of human culture, embodying human intelligence and creativity, of which songs compose an essential part. While various aspects of song generation have been explored by previous works, such as singing voice, vocal composition and instrumental arrangement, etc., generating so…

2022

To Smooth or Not? When Label Smoothing Meets Noisy Labels

ICML 2022oral

Label smoothing (LS) is an arising learning paradigm that uses the positively weighted average of both the hard training labels and uniformly distributed soft labels. It was shown that LS serves as a regularizer for training data with hard labels and therefore improves the generalization of the mode…