2 papers
cs.CV2026
Prefix-Adaptive Block Diffusion for Efficient Document Recognition
Mingxu Chai, Ziyu Shen, Chenyu Liu +9
Block Diffusion Models (BDMs) support parallel generation, flexible-length output, and KV caching, making them promising for efficient document parsing. However, existing BDMs bind…
cs.CV2026
ACD-CLIP: Decoupling Representation and Dynamic Fusion for Zero-Shot Anomaly Detection
Ke Ma, Jun Long, Hongxiao Fei +3
Pre-trained Vision-Language Models (VLMs) struggle with Zero-Shot Anomaly Detection (ZSAD) due to a critical adaptation gap: they lack the local inductive biases required for dense…