arXiv subjects

Yunlong Bai

Publications and source records attributed to Yunlong Bai.

3 recordsLinked to original sources

arXiv2026

LSTN: A Linear Model of Industrial Production Process for Demand Response

Industrial production modeling provides operational constraints for industrial users participating in demand response (DR) programs. Conventional modeling of the production process introduces binary variables to model the discrete operating points of industrial equipment, which can be computationally infeasible in large-scale DR applications. To reasonably model industrial users' operational constraints while balancing computational complexity and modeling accuracy, we developed a linear model of the industrial production process for evaluating DR applications. Numerical results verify the accuracy of the proposed model and its great improvement in computational efficiency over competing approaches.

eess.SY↗

arXiv2026

SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer

Recent breakthroughs in video diffusion models have significantly accelerated the development of video editing techniques. However, existing methods often rely on inpainting video frames based on masked input, which requires extracting the target video mask in advance, and the precision of the segmentation directly affects the quality of the completion. In this paper, we present SEDiT, a novel one-stage video Subtitle Erasure approach via One-step Diffusion Transformer. We introduce a mask-free inference approach that enables direct erasure of the targeted subtitle. The proposed one-stage framework mitigates the sub-optimality inherent in the two-stage processing of prior models. Since subtitle removal is a localized editing task in which most pixels remain unchanged, the underlying distribution shift is minimal, making it well-suited to one-step generation under rectified flow. We empirically validate the reliability of one-step denoising and further provide a formal theoretical justification. Under the localized-editing structure of subtitle removal, the conditional optimal transport (OT) map and its induced rectified flow velocity field are Lipschitz continuous with respect to the latent variable, which underpins the theoretical feasibility of one-step sampling. To address the challenge of long-term temporal consistency, we adopt a hybrid training strategy by occasionally conditioning the model with a clean first-frame latent. This facilitates temporal continuity, allowing each segment during inference to leverage the output of its predecessor. To avoid visible seams caused by cropping and reinserting processed targets, particularly in scenarios involving substantial motion, we feed the original video directly into SEDiT. Thanks to one-step and chunk-wise streaming inference, our method can efficiently handle native 1440p video with infinite length.

cs.CV↗

arXiv2025

Biomimetic Liquid Metal Cell

Gallium-based liquid metals, as a broad category of emerging functional materials with unique physical, chemical, and biological properties, offer numerous possibilities for advancing intelligent systems. However, a basic query persistently remains for the complex liquid metal system: Is there a minimal functional unit that can fully capture its diversity of morphology and function? Cells, as the most basic structural and functional units of life, are small in scale but have complex structures, functions, and life activities. Analogous to nature, this article proposes the concept of liquid metal cells, and systematically explores their construction routes, sensing capabilities, motion behaviors, and potential applications. We first construct a multi-phase composite structure with liquid metal as the nucleus, ionic solution as the cytoplasm, and polymer as the cell membrane by developing a layered cryogenic molding method. Furthermore, we reveal that liquid metal cells exhibit inherently versatile responsive characteristics and self-adaptive behaviors to thermal, pressure, chemical, electrical, and magnetic fields, indicating "small world, vast potential". Based on these fundamental findings, we finally demonstrate the feasibility of utilizing liquid metal cells as sensors, fluidic valves, and material transport carriers in flow channels through dynamic control.

physics.app-ph↗