Area of research
Artificial Intelligence · Computer Vision and Pattern Recognition
Research interest
Research interests include Topic Modeling, Natural Language Processing Techniques, Music and Audio Processing, and Music Technology and Sound Studies.
MusicLDM: Enhancing Novelty in text-to-music Generation Using Beat-Synchronous mixup Strategies
Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation
Multitrack Music Transformer
CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained Language-Vision Models
HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models
Mix and Match: Learning-free Controllable Text Generationusing Energy Language Models
Prompt Consistency for Zero-Shot Task Generalization
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
Lagging Inference Networks and Posterior Collapse in Variational Autoencoders
Rare & Special e-Zone (The Hong Kong University of Science and Technology) 2019cited by 119position: last
A Surprisingly Effective Fix for Deep Latent Variable Modeling of Text
Simple and Effective Paraphrastic Similarity from Parallel Translations
Speaker-Follower Models for Vision-and-Language Navigation
Neural Information Processing Systems 2018cited by 155position: middle
Tools for Automated Analysis of Cybercriminal Markets
CAREER: Modeling Language Evolution via Deep Probabilistic Factorization
Collaborative Research: RI: Small: Unsupervised Islamicate Manuscript Transcription via Lacunae Reconstruction
RI: Small: Print and Probability - A Statistical Approach to Analysis of Clandestine Publication
RI: Small: Print and Probability - A Statistical Approach to Analysis of Clandestine Publication
RI: Small: Collaborative Research: Unsupervised Transcription of Early Modern Documents