Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Rethinking Multi-Image Re-Representation in Multi-Image Understanding
Gengyuan Zhang, Xiao Han, Xinyu Xie +2
Multi-image understanding requires MLLMs not only to recognise the content of individual images, but also to organise visual evidence distributed across them. We study this problem…
cs.CV2025
DIFFUMA: High-Fidelity Spatio-Temporal Video Prediction via Dual-Path Mamba and Diffusion Enhancement
Xinyu Xie, Weifeng Cao, Jun Shi +4
Spatio-temporal video prediction plays a pivotal role in critical domains, ranging from weather forecasting to industrial automation. However, in high-precision industrial scenario…
cs.CV2025
AViLA: Asynchronous Vision-Language Agent for Streaming Multimodal Data Interaction
Gengyuan Zhang, Tanveer Hannan, Hermine Kleiner +6
An ideal vision-language agent serves as a bridge between the human users and their surrounding physical world in real-world applications like autonomous driving and embodied agent…