Jia-Hong Huang

for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models

MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understanding

MMArt is introduced, a large-scale dataset of 74,234 WikiArt paintings, each annotated with four independently annotated perspectives plus a harmonized unified caption, produced by specialized vision-language models or human annotation and validated through complementary quality evaluations.

Can We Read the Mind of an Audio LLM? A Verbalizable, Multilingual Middle-Layer Workspace

Reading a base Qwen3-Omni with a logit lens at the audio-token positions, it is found that the answer to a spoken question becomes legible - in words - in the model's middle layers, before it emits any token.