5 papers
AdaKerNet: Neural Kernel Decoding for Task-Adaptive Prediction with Multimodal Large Models
Konstantinos D. Polyzos, Eleni Oikonomou, Tara Javidi
Large foundation models have been introduced with the promise of efficient adaptation to downstream tasks. Yet, under limited supervision, MLLMs, an important class of large founda…
Enhancing Bayesian Optimization and Active Learning Through Kernel Diversity
Heng Zhang, Haotian Xiang, Konstantinos D. Polyzos +2
Hyperparameter selection remains a key challenge in Bayesian optimization (BO) and Bayesian active learning (AL), as model misspecification can lead to suboptimal performance, whil…
A Single Image and Multimodality Is All You Need for Novel View Synthesis
Amirhosein Javadi, Chi-Shiang Gau, Konstantinos D. Polyzos +1
Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular…
Consequences of Kernel Regularity for Bandit Optimization
Madison Lee, Tara Javidi
In this work we investigate the relationship between kernel regularity and algorithmic performance in the bandit optimization of RKHS functions. While reproducing kernel Hilbert sp…
Active Sampling and Gaussian Reconstruction for Radio Frequency Radiance Field
Chi-Shiang Gau, Xingyu Chen, Tara Javidi +1
Radio-frequency (RF) Radiance Field reconstruction is a challenging problem. The difficulty lies in the interactions between the propagating signal and objects, such as reflections…