A deployed multimodal predictor may face missing modalities after its weights can no longer be changed. This raises a question that training-time repair does not answer: what part of the resulting error is still correctable from the information that remains? We show that this part is characterized by the Bayes gap, the difference between the model's prediction and the Bayes prediction given the observed modalities.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Ho Duc
Computer Science > Cryptography and Security
End-to-end autoencoder communication has emerged as a promising means of achieving efficient data transmission across various domains. Nevertheless, vulnerabilities have recently been revealed in these systems by adversarial attacks, wherein malevolent entities manipulate the transmitted signals to deceive the autoencoder.
Computer Science > Information Theory
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Computer Science > Machine Learning
[Submitted on 28 Sep 2026] Title:The Decision Value of Perception Compute View a PDF of the paper titled The Decision Value of Perception Compute, by Hoang Pham Cong and Ho Viet Duc Luong View PDF HTML (experimental) Abstract:Adaptive perception spends extra computation on inputs where perception is expected to improve. When perception feeds a downstream decision system, a better perception output need not produce a better decision.
Effects of bottom roughness on wave transmission across a submerged reef
Dinh Q. Cuong1*, Nguyen Q. Tao1, Ho D. Dat1 and Tri Mai1 1Hanoi University of Civil Engineering, Vietnam Provisionally accepted: The final, formatted version of the article will be published soon. This paper presents a laboratory study to investigate the effects of bottom roughness on wave transmiting across a submerged coral reef having a steep fore-reef slope. Experimented models were carried out in wave flume for four different bed roughness levels including a smooth and three roughness heights.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Ho
Contact Ho, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack