Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Multimodal LLMs under Pairwise Modalities
Yan Li, Yunlong Deng, Yuewen Sun +3
Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human…
cs.CV2026
Unsupervised Synthetic Image Attribution: Alignment and Disentanglement
Zongfang Liu, Guangyi Chen, Boyang Sun +2
As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring mo…
cs.CV2025
MixAR: Mixture Autoregressive Image Generation
Jinyuan Hu, Jiayou Zhang, Shaobo Cui +2
Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the qu…