6 papers
FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation
Muyu Liu, Mingming Liu, Hong Gu +2
In autoregressive video generation, retaining all historical key-value (KV) states increases memory usage and per-step attention costs as videos grow longer. A fixed cache budget b…
PAPEL: A Collaborative System for Parental Guidance during Preschool Play-Based English Learning
Xutong Wang, Yu Mei, Qinwei Li +7
Play-based parent-child interaction offers preschoolers rich opportunities for everyday foreign language learning, yet many parents struggle to turn open-ended play into effective…
Zero-shot Low-Field MRI Enhancement via Diffusion-Based Adaptive Contrast Transport
Muyu Liu, Chenhe Du, Xuanyu Tian +5
Low-field (LF) magnetic resonance imaging (MRI) democratizes access to diagnostic imaging but is fundamentally limited by low signal-to-noise ratio and significant tissue contrast…
Resolving Blind Inverse Problems under Dynamic Range Compression via Structured Forward Operator Modeling
Muyu Liu, Xuanyu Tian, Chenhe Du +3
Recovering radiometric fidelity from unknown dynamic range compression (UDRC), such as low-light enhancement and HDR reconstruction, is a challenging blind inverse problem, due to…
Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction
Chenhe Du, Xuanyu Tian, Qing Wu +4
Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors…
Embedding Compression for Text Classification Using Dictionary Screening
Jing Zhou, Xinru Jing, Muyu Liu +1
In this paper, we propose a dictionary screening method for embedding compression in text classification tasks. The key purpose of this method is to evaluate the importance of each…