Autoregressive video generation enables efficient inference through streaming prediction. However, existing methods are typically restricted to fixed sampling steps, limiting the flexibility to balance generation quality and efficiency, while one-step generation suffers from degraded visual quality and error accumulati...
Jia-Hua Xu, Yi-Jie Fang, Nan-Nan Wang et al.· 0 citations
Low-rank Decomposition and Adaptation (LoDA) performs a task-driven decomposition to build general and truly task-specific LoRA subspaces by solving two energy-based objectives, decoupling directions for knowledge sharing and isolation.
Ling-Feng He, De Cheng, Huai-Jie Wang et al.· arXiv.org· 12 citations· ⚡2
Magnetic resonance imaging (MRI) plays an important role in clinical diagnosis, nevertheless, it suffers from motion artifacts in many real-world scenarios. Removing motion artifacts can alleviate this interference and thus facilitate precise diagnosis. However, recent works mainly rely on paired data and the artifactu...
Jia-Hua Xu, Dawei Zhou, Lei Hu et al.· Neural Networks· 0 citations
A Difficulty-aware Dynamic Routing (DDR) strategy that overcomes the rigid, one-size-fits-all processing paradigm for Real-ISR approaches, and builds a set of Real-ISR networks with varying model capacities by modulating the spatial downsampling ratio of the VAE in the SD backbone.
Xue Wu, Kang Zhao, Ka-Feng Wang et al.· arXiv.org· 0 citations
PAPT++ is introduced, a risk-aware adversarial generation-training framework for SDG that progressively exposes the classifier to challenging yet semantically consistent variations.
Zhi-Peng Xu, De Cheng, Xinyang Jiang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.