Yan Feng

SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

Zhenyu Lu, Liupeng Li, Jinpeng Wang, et al.

Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study

Danya Li, Yan Feng, Rico Krueger

PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment

Tianci Luo, Jinpeng Wang, Shiyu Qin, et al.

PromptHub is a framework that improves visual in-context learning (learning vision tasks from image examples) by better combining multiple demonstration examples through spatial awareness and smarter training objectives. Unlike previous methods that treat image patches independently, PromptHub uses location information to understand context better and employs multiple complementary training goals to help the model learn more effectively. The approach shows strong performance across multiple vision tasks and works reliably even with different types of images.