Thao M. Dang — accepted AI-conference papers

2026

Hyperbolic Gramian Volumes for Multimodal Alignment

Saiyang Na, Feng Jiang, Qifeng Zhou, Wenliang Zhong, Thao M. Dang, Yuzhi Guo +4

CVPR 2026

Multimodal contrastive learning typically relies on pairwise similarities for alignment, but recent work has shown that Gramian volumes can capture higher-order correlations across modalities. However, Euclidean Gramian volumes suffer from volume collapse under L2 normalization, concentrating near u

Cited by 0 Source ↗Scholar ↗

2026

Learning from Guidelines: Structured Prompt Optimization for Expert Annotation Tasks

Wenliang Zhong, Haiqing Li, Thao M. Dang, Feng Jiang, Hehuan Ma, Yuzhi Guo +2

AAAI 2026technical

Deep learning has significantly advanced numerous fields by training on extensive annotated datasets. However, this data-driven paradigm faces limitations such as limited adaptability and high annotation costs, particularly when precise adherence to detailed, domain-specific guidelines is required i

Cited by 0 Source ↗PDF ↗Scholar ↗