Yilong Yang — accepted AI-conference papers

2026

Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation

Yilong Yang, Jianxin Tian, Shengchuan Zhang, Liujuan Cao

CVPR 2026

Current zero-shot camouflaged object segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segmentation. However, relying solely on MLLMs for camouflaged object discovery often leads to inaccurate localization, false

Cited by 0 Source ↗code ↗Scholar ↗

2026

Improving Sustainability of Adversarial Examples in Class-Incremental Learning

Taifeng Liu, Xinjing Liu, Liangqiu Dong, Yang Liu, Yilong Yang, Zhuo Ma

AAAI 2026technical

Current adversarial examples (AEs) are typically designed for static models. However, with the wide application of Class-Incremental Learning (CIL), models are no longer static and need to be updated with new data distributed and labeled differently from the old ones. As a result, existing AEs often

Cited by 0 Source ↗PDF ↗Scholar ↗