AIConfPaper
← Search

Bingce Wang

2 accepted papers

2025

Adaptive Spatiotemporal Augmentation for Improving Dynamic Graph Learning

Xu Chu, Hanlin Xue, Bingce Wang, Xiaoyang Liu, Weiping Li, Tong Mo +2
ICASSP 2025accepted

Dynamic graph augmentation is used to improve the performance of dynamic GNNs. Most methods assume temporal locality, meaning that recent edges are more influential than earlier edges. However, for temporal changes in edges caused by random noise, overemphasizing recent edges while neglecting earlie…

Cited by 0Source ↗Scholar ↗
2025

Mitigating Hallucinations on Object Attributes using Multiview Images and Negative Instructions

Zhijie Tan, Yuzhi Li, Shengwei Meng, Xiang Yuan, Weiping Li, Tong Mo +2
ICASSP 2025accepted

Current popular Large Vision-Language Models (LVLMs) are suffering from Hallucinations on Object Attributes (HoOA), leading to incorrect determination of fine-grained attributes in the input images. Leveraging significant advancements in 3D generation from a single image, this paper proposes a novel…

Cited by 0Source ↗Scholar ↗