Shiyu Xuan

Associate Professor@Nanjing University of Science and Technology·中国·OpenReview

研究方向

multi-modal large language model · domain generalization · visual prompt · person ReID · domain adaptation · incremental learning · contrastive learning · long-tailed visual recognition · object tracking

5.0

Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition

ICLR 2026Poster

一作

4.5

Textual and Temporal-Guided Feature Decoupling for Video Temporal Grounding

ICLR 2026Rejected

二作

4.5

Evoking Generalized Cognition for Exemplar Free Continual Learning via Granular Ball Representation

合作者 (6)