4 papers
Luminark: Training-free, Probabilistically-Certified Watermarking for General Vision Generative Models
Jiayi Xu, Zhang Zhang, Yuanrui Zhang +4
In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a…
Towards Infant Sleep-Optimized Driving: Synergizing Wearable and Vehicle Sensing in Intelligent Cruise Control
Ruitao Chen, Mozhang Guo, Jinge Li
Automated driving (AD) has substantially improved vehicle safety and driving comfort, but their impact on passenger well-being, particularly infant sleep, is not sufficiently studi…
New Sphere Packings from the Antipode Construction
Ruitao Chen, Jiachen Hu, Binghui Li +2
In this note, we construct non-lattice sphere packings in dimensions , , , , , , and , demonstrating record densities that surpass all previously docume…
Feedback-Driven Vision-Language Alignment with Minimal Human Supervision
Giorgio Giannone, Ruoteng Li, Qianli Feng +3
Vision-language models (VLMs) have demonstrated remarkable potential in integrating visual and linguistic information, but their performance is often constrained by the need for ex…