Yingqi Gao — accepted AI-conference papers

2026

A Novel SAM Coupling Mechanism for SAR Image Segmentation

Yang Liu, Miao Fu, Yingqi Gao, Lin Lin, Jiarui Li, Rui Liu

IJCAI 2026

The Segment Anything Model (SAM) provides a new paradigm for visual perception tasks through large-scale pre-training and interactive prompts. However, the quality of mask generation is limited by the difficulty of aligning the optimization direction between the backbone and the prompt, which is esp

Cited by 0 Scholar ↗

2023

Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System

Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, Wei Bi

EMNLP 2023long main

Developing an efficient retriever to retrieve knowledge from a large-scale knowledge base (KB) is critical for task-oriented dialogue systems to effectively handle localized and specialized tasks. However, widely used generative models such as T5 and ChatGPT often struggle to differentiate subtle di…

Cited by 0 Source ↗code ↗Scholar ↗