Yiyi Liu — accepted AI-conference papers

2025

CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan Reconstruction

Yiyi Liu, Chunyang Liu, Bohan Wang, Weiqin Jiao, Bojian Wu, Lubin Fan +3

NeurIPS 2025poster

We present CAGE (Continuity-Aware edGE) network, a robust framework for reconstructing vector floorplans directly from point-cloud density maps. Traditional corner-based polygon representations are highly sensitive to noise and incomplete observations, often resulting in fragmented or implausible la…

Cited by 0 Source ↗code ↗Scholar ↗

2022

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict

Yiyi Liu, Yequan Wang, Aixin Sun, Xuying Meng, Jing Li, Jiafeng Guo

NAACL 2022findings

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments expressed in one sentence. However, it is difficult to recogn…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗