3 papers
cs.CL2025
Mitigating Knowledge Conflicts in Language Model-Driven Question Answering
Han Cao, Zhaoyang Zhang, Xiangtian Li +3
In the context of knowledge-driven seq-to-seq generation tasks, such as document-based question answering and document summarization systems, two fundamental knowledge sources play…
cs.CV2024
DTSGAN: Learning Dynamic Textures via Spatiotemporal Generative Adversarial Network
Xiangtian Li, Xiaobo Wang, Zhen Qi +3
Dynamic texture synthesis aims to generate sequences that are visually similar to a reference video texture and exhibit specific stationary properties in time. In this paper, we in…
cs.CV2024
Artistic Neural Style Transfer Algorithms with Activation Smoothing
Xiangtian Li, Han Cao, Zhaoyang Zhang +3
The works of Gatys et al. demonstrated the capability of Convolutional Neural Networks (CNNs) in creating artistic style images. This process of transferring content images in diff…