Third-year Ph.D. directed by Prof. Huchuan Lu from Dalian University of Technology.
Research Interests:   Deep Learning, Machine Learning, Computer Vision Domains: Vision-and-Language, Parameter-efficient Transfer Learning, Large Multimodal Model. 1. Vision-Language Retrieval: SGRAF (AAAI'21), RCAR (TIP'23), DBL (TIP'24), GSSF (TIP'24)
2. Parameter-Efficient Tuning: UniPT (CVPR'24), SHERL (ECCV'24), KARST (2024)
3. Large Multi-Modality Model: EVE (NeurIPS'24), DenseFusion (NeurIPS'24), PathWeave (NeurIPS'24)
4. AI Generated Content: MoTrans (ACMMM'24), NOVA (2024)


Research Pursuits:   Develop an efficient and reliable mechanism that can proficiently recognize visual-semantic perception, contextualize fine-grained interaction across modalities, and mimick human-like judgement and decision-making capabilities.
Open Resources:   [Awesome_Matching_Pretraining_Transfering]
[Awesome_Image_Text_Retrieval_Benchmark]

Sep. 2023 -- Present:   Research intern at BAAI with Dr. Xinlong Wang on Large Multimodality Model for Understanding and Generation.
Jan. 2023 -- Aug. 2023:   Remote cooperation with Ph.D. Bo Wan from KU Leuven and Asst. Prof. Long Chen from HKUST on Parameter-efficient Transfer Learning.
Jun. 2020 -- Mar. 2021:   Research intern at Tencent AI Lab with Dr. Ying Zhang and Dr. Lin Ma on Image-Text Retrieval, Cross-modal Boosting and Metric Learning.