Published multiple high-level academic papers covering topics like the response analysis of large vision-language models to visually absent tokens, a federated learning algorithm of diffusion models, zero-shot candidate selection for instruction-guided image editing, a region-aware vision language model for precise GUI grounding, and temporality-aware integrated gradients for time series explanation.
Research Experience
Published papers in top international conferences such as EMNLP, TPAMI, ICCV, ACL, and ICML; involved or led research projects on analyzing responses of large vision-language models to visually absent tokens, federated learning algorithm of diffusion models, early timestep zero-shot candidate selection for instruction-guided image editing, region-aware vision language model for precise GUI grounding, and temporality-aware integrated gradients for time series explanation.
Background
Research interests include machine learning algorithms, multi-modal learning, large language models, computer vision, and machine learning for healthcare.
Miscellany
Welcomes students interested in AI-based technology entrepreneurship; seeking military scholarship recipients; open positions for MS, PhD students, and postdocs.