5 papers
Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark
Seng Nam Chen, Hao Chen, Chenglam Ho +4
Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly…
Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation
Hao Chen, Rui Yin, Yifan Chen +2
Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment. While recent generative approaches have a…
CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
Zhitong Dong, Chao Li, Jie Yu +1
Aesthetic image cropping aims to enhance the aesthetic quality of an image by improving its composition through spatial cropping. Previous methods often rely on saliency prediction…
Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
Yifan Chen, Fei Yin, Hao Chen +2
Contrast-enhanced imaging is central to oncologic diagnosis, but contrast agents can be contraindicated for many of the patients who need them most. Synthesizing contrast scans fro…
Generalized Spherical Neural Operators: Green's Function Formulation
Hao Tang, Hao Chen, Chao Li
Neural operators offer powerful approaches for solving parametric partial differential equations, but extending them to spherical domains remains challenging due to the need to pre…