4 papers
Enhancing Zero-shot Personalized Image Aesthetics Assessment with Profile-aware Multimodal LLM
Chun Wang, Chenfeng Wei, Chenyang Liu +1
Personalized image aesthetics assessment (PIAA) aims to predict an individual user's subjective rating of an image, which requires modeling user-specific aesthetic preferences. Exi…
Optimal Transport Regularization for Speech Text Alignment in Spoken Language Models
Wenze Xu, Chun Wang, Jiazhen Yu +3
Spoken Language Models (SLMs), which extend Large Language Models (LLMs) to perceive speech inputs, have gained increasing attention for their potential to advance speech understan…
Dual Information Speech Language Models for Emotional Conversations
Chun Wang, Chenyang Liu, Wenze Xu +1
Conversational systems relying on text-based large language models (LLMs) often overlook paralinguistic cues, essential for understanding emotions and intentions. Speech-language m…
Seek and Solve Reasoning for Table Question Answering
Ruya Jiang, Chun Wang, Weihong Deng
The complexities of table structures and question logic make table-based question answering (TQA) tasks challenging for Large Language Models (LLMs), often requiring task simplific…