Chuan Lin

2 accepted papers

2026

A Reasoning Paradigm for Named Entity Recognition

Hui Huang, Yanping Chen, Ruizhang Huang, Chuan Lin, Yongbin Qin

AAAI 2026technical

Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive shortcutting" leads to suboptimal performance and weak general

Cited by 0 Source ↗PDF ↗Scholar ↗

2026

BDNet:Bio-Inspired Dual-Backbone Small Object Detection Network

Wenchao Guan, Chuan Lin, Sihan Huang, Xiongzhen Wang, Xintao Pang

CVPR 2026

In remote sensing images, small objects often exhibit low color contrast and blurred edges, leading to suboptimal feature extraction. Physiological studies indicate that the LGN/V1-V2-V4 pathway provides color-opponent sensitivity and hierarchical enhancement for color information extraction, wherea

Cited by 0 Source ↗Scholar ↗