Yuquan Lu — accepted AI-conference papers

2026

Decoupling Continual Semantic Segmentation

Yifu Guo, Yuquan Lu, Wentao Zhang, Zishan Xu, Dexia Chen, Siyu Zhang +2

AAAI 2026technical

Continual Semantic Segmentation (CSS) requires learning new classes without forgetting previously acquired knowledge, addressing the fundamental challenge of catastrophic forgetting in dense prediction tasks. However, existing CSS methods typically employ single-stage encoder-decoder architectures w

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

VideoSeg-R1:Reasoning Video Object Segmentation via Reinforcement Learning

Zishan Xu, Yifu Guo, Yuquan Lu, Fengyu Yang, Junxin Li, Lihua Cai

AAAI 2026technical

Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose VideoSeg-R1, the first framework to introduce reinforcement learning into video reasoning segmentati

Cited by 0 Source ↗PDF ↗Scholar ↗