no code implementations • 1 Dec 2024 • Zilin Du, Haoxin Li, Jianfei Yu, Boyang Li
Visual grounding aims to localize the image regions based on a textual query.
no code implementations • 8 Oct 2024 • Xu Guo, Zilin Du, Boyang Li, Chunyan Miao
A major limitation of prompt tuning is its dependence on large labeled training datasets.
1 code implementation • 18 Jun 2024 • Miaoyu Li, Haoxin Li, Zilin Du, Boyang Li
Finally, in the ensemble stage, an LLM informed by the rationales selects one answer from the three candidates.
no code implementations • 5 Dec 2023 • Zilin Du, Haoxin Li, Xu Guo, Boyang Li
Comparing our method to direct training on synthetic data, we observed a significant improvement of 24. 06% F1 with synthetic text and 26. 42% F1 with synthetic images.
no code implementations • 15 Jun 2023 • Zilin Du, Yunxin Li, Xu Guo, Yidan Sun, Boyang Li
Contemporary news reporting increasingly features multimedia content, motivating research on multimedia event extraction.
1 code implementation • 29 Dec 2022 • Chunkai Zhang, Yuting Yang, Zilin Du, Wensheng Gan, Philip S. Yu
High-utility sequential pattern mining (HUSPM) has emerged as an important topic due to its wide application and considerable popularity.