Han Zhou

FlowTime proposes a novel Continuous Generative Regression framework using a Flow-based Personalized Prior to accurately model the multimodal and heterogeneous nature of user watch time prediction, significantly outperforming existing state-of-the-art methods.

FlowTime proposes a novel Continuous Generative Regression framework using a Flow-based Personalized Prior to accurately model the multimodal and heterogeneous nature of user watch time prediction, significantly outperforming existing state-of-the-art methods.

This paper uses deep learning and genetic algorithms to automate the design of microwave filters.

A new three-port Doherty combiner design methodology is proposed using CNNs, pixelated layout representations, and genetic algorithms to improve Doherty power amplifier performance.

AutoACSL is a framework that uses Code Property Graphs and large language models to generate formal specifications for C programs with improved success ratio and full proof ratio.

Introduce PerceptionRubrics, a rubric-based evaluation framework for addressing real-world brittleness of models using 1,038 images and over 12,000 instance-specific rubrics.

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.