activity
20242026
collaborators

13 papers

cs.CV2026

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion

Yongji Long, Shijun Liang, Jintao Li +1

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range informa…

eess.IV2025

Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction

Evan Bell, Shijun Liang, Ismail Alkhouri +1

Deep Image Prior (DIP) has recently emerged as a promising one-shot neural-network based image reconstruction method. However, DIP has seen limited application to 3D image reconstr…

eess.IV2025

Understanding Untrained Deep Models for Inverse Problems: Algorithms and Theory

Ismail Alkhouri, Evan Bell, Avrajit Ghosh +3

In recent years, deep learning methods have been extensively developed for inverse imaging problems (IIPs), encompassing supervised, self-supervised, and generative approaches. Mos…

eess.IV2025

Robust Physics-based Deep MRI Reconstruction Via Diffusion Purification

Ismail Alkhouri, Shijun Liang, Rongrong Wang +2

Deep learning (DL) techniques have been extensively employed in magnetic resonance imaging (MRI) reconstruction, delivering notable performance enhancements over traditional non-DL…

eess.IV2025

NERD: Network-Regularized Diffusion Sampling For 3D Computed Tomography

Shijun Liang, Ismail Alkhouri, Qing Qu +2

Numerous diffusion model (DM)-based methods have been proposed for solving inverse imaging problems. Among these, a recent line of work has demonstrated strong performance by formu…

cs.CV2025

LongCat-Video Technical Report

Meituan LongCat Team, Xunliang Cai, Qilong Huang +8

Video generation is a critical pathway toward world models, with efficient long video inference as a key capability. Toward this end, we introduce LongCat-Video, a foundational vid…