2 papers
cs.CV2025
ResDynUNet++: A nested U-Net with residual dynamic convolution blocks for dual-spectral CT
Ze Yuan, Wenbin Li, Shusen Zhao
We propose a hybrid reconstruction framework for dual-spectral CT (DSCT) that integrates iterative methods with deep learning models. The reconstruction process consists of two com…
cs.SD2024
Continuous Speech Tokens Makes LLMs Robust Multi-Modality Learners
Ze Yuan, Yanqing Liu, Shujie Liu +1
Recent advances in GPT-4o like multi-modality models have demonstrated remarkable progress for direct speech-to-speech conversation, with real-time speech interaction experience an…