arXiv subjects

Yuhan He

Publications and source records attributed to Yuhan He.

9 recordsLinked to original sources

arXiv2026

Consistent Feature Transport for Image Relighting

Image relighting modifies illumination while preserving non-lighting content such as identity and geometry. Existing diffusion-based methods often suffer from unstable illumination changes or inconsistent content preservation under complex lighting, as they lack an explicit mechanism to learn feature transformations between images. We reformulate relighting as an illumination feature transport problem and introduce Consistent Feature Transport (CFT), a training principle that explicitly enforces illumination-consistent transport between source and target image distributions. Built upon rectified flow, CFT jointly models noise-to-image generation and illumination-consistent source-to-target transport through trajectory-level supervision. This dual-transport formulation encourages isolation of illumination-specific variations while preserving content-aligned features. To support complex lighting scenarios, we construct a large-scale portrait relighting dataset with diverse relighting effects. Experiments show consistent improvements over existing state-of-the-art relighting approaches and demonstrate that CFT can generalize to other editing tasks, including style transfer. Code is available at https://github.com/Dixin-Lab/CFT.

cs.CV↗

arXiv2025

All-optical temporal integration mediated by subwavelength heat antennas

Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern artificial intelligence. We demonstrate an all-optical neuromorphic computing system based on time division multiplexing, capable of processing input vectors exceeding 250,000 elements within a unified framework. The platform harnesses optically driven thermo-optic modulation in standing wave optical fields, with titanium nano-antennas functioning as wavelength-selective absorbers. Counterintuitively, the thermal time dynamics of the system enable simultaneous time integration of ultra-fast (50GHz) signals and the application of programmable, non-linear activation functions, entirely within the optical domain. This unified framework constitutes a leap towards large-scale photonic computing that satisfies the dimensional requirements of AI workloads.

physics.optics↗

arXiv2025

The Impact of Employee Education and Health on Firm-Level TFP in China

This study examines the influence of employee education and health on firm-level Total Factor Productivity (TFP) in China, using panel data from A-share listed companies spanning from 2007 to 2022. The analysis shows that life expectancy and higher education have a significant impact on TFP. More optimal health conditions can result in increased productivity through decreased absenteeism and improved work efficiency. Similarly, higher levels of education can support technological adaptation, innovation, and managerial efficiency. Nevertheless, the correlation between health and higher education indicates that there may be a point where further improvements in health yield diminishing returns in terms of productivity for individuals with advanced education. These findings emphasise the importance of implementing comprehensive policies that improve both health and education, maximising their impact on productivity. This study adds to the current body of research by presenting empirical evidence at the firm-level in China. It also provides practical insights for policymakers and business leaders who want to improve economic growth and competitiveness. Future research should take into account wider datasets, more extensive health metrics, and delve into the mechanisms that contribute to the diminishing returns observed in the relationship between health and education.

econ.GN↗

arXiv2024

MPSI: Mamba enhancement model for pixel-wise sequential interaction Image Super-Resolution

Single image super-resolution (SR) has long posed a challenge in the field of computer vision. While the advent of deep learning has led to the emergence of numerous methods aimed at tackling this persistent issue, the current methodologies still encounter challenges in modeling long sequence information, leading to limitations in effectively capturing the global pixel interactions. To tackle this challenge and achieve superior SR outcomes, we propose the Mamba pixel-wise sequential interaction network (MPSI), aimed at enhancing the establishment of long-range connections of information, particularly focusing on pixel-wise sequential interaction. We propose the Channel-Mamba Block (CMB) to capture comprehensive pixel interaction information by effectively modeling long sequence information. Moreover, in the existing SR methodologies, there persists the issue of the neglect of features extracted by preceding layers, leading to the loss of valuable feature information. While certain existing models strive to preserve these features, they frequently encounter difficulty in establishing connections across all layers. To overcome this limitation, MPSI introduces the Mamba channel recursion module (MCRM), which maximizes the retention of valuable feature information from early layers, thereby facilitating the acquisition of pixel sequence interaction information from multiple-level layers. Through extensive experimentation, we demonstrate that MPSI outperforms existing super-resolution methods in terms of image reconstruction results, attaining state-of-the-art performance.

cs.CV↗

arXiv2024

EchoIR: Advancing Image Restoration with Echo Upsampling and Bi-Level Optimization

Image restoration represents a fundamental challenge in low-level vision, focusing on reconstructing high-quality images from their degraded counterparts. With the rapid advancement of deep learning technologies, transformer-based methods with pyramid structures have advanced the field by capturing long-range cross-scale spatial interaction. Despite its popularity, the degradation of essential features during the upsampling process notably compromised the restoration performance, resulting in suboptimal reconstruction outcomes. We introduce the EchoIR, an UNet-like image restoration network with a bilateral learnable upsampling mechanism to bridge this gap. Specifically, we proposed the Echo-Upsampler that optimizes the upsampling process by learning from the bilateral intermediate features of U-Net, the "Echo", aiming for a more refined restoration by minimizing the degradation during upsampling. In pursuit of modeling a hierarchical model of image restoration and upsampling tasks, we propose the Approximated Sequential Bi-level Optimization (AS-BLO), an advanced bi-level optimization model establishing a relationship between upsampling learning and image restoration tasks. Extensive experiments against the state-of-the-art (SOTA) methods demonstrate the proposed EchoIR surpasses the existing methods, achieving SOTA performance in image restoration tasks.

cs.CV↗

arXiv2023

In-memory photonic dot-product engine with electrically programmable weight banks

Electronically reprogrammable photonic circuits based on phase-change chalcogenides present an avenue to resolve the von-Neumann bottleneck; however, implementation of such hybrid photonic-electronic processing has not achieved computational success. Here, we achieve this milestone by demonstrating an in-memory photonic-electronic dot-product engine, one that decouples electronic programming of phase-change materials (PCMs) and photonic computation. Specifically, we develop non-volatile electronically reprogrammable PCM memory cells with a record-high 4-bit weight encoding, the lowest energy consumption per unit modulation depth (1.7 nJ per dB) for Erase operation (crystallization), and a high switching contrast (158.5%) using non-resonant silicon-on-insulator waveguide microheater devices. This enables us to perform parallel multiplications for image processing with a superior contrast-to-noise ratio (greater than 87.36) that leads to an enhanced computing accuracy (standard deviation less than 0.007). An in-memory hybrid computing system is developed in hardware for convolutional processing for recognizing images from the MNIST database with inferencing accuracies of 86% and 87%.

physics.app-ph↗

arXiv2020

Dynamic brain spectrum acquired by a real-time ultra-spectral imaging chip with reconfigurable metasurfaces

Spectral imaging paves way for various fields and particular in biomedical research. However, spectral imaging mainly depending on spatial or temporal scanning, cannot achieve high temporal, spatial and spectral resolution simultaneously. In this study, we demonstrated a silicon real-time ultra-spectral imaging chip based on reconfigurable metasurfaces, comprising of 155,216 (356$\times$436) image-adaptive micro-spectrometers with ultra-high center-wavelength accuracy of 0.04 nm and spectral resolution of 0.8 nm. It is employed for imaging brain hemodynamics, and the dynamic spectral absorption properties of deoxyhemoglobin and oxyhemoglobin in a rat barrel cortex were obtained, which enlighten the spectroscopy in vivo studies and other real-time applications.

physics.optics↗

arXiv2018

Truly concomitant and independently expressed short- and long-term plasticity in Bi2O2Se-based three-terminal memristor

Orchestration of diverse synaptic plasticity mechanisms across different timescales produces complex cognitive processes. To achieve comparable cognitive complexity in memristive neuromorphic systems, devices that are capable to emulate short- and long-term plasticity (STP and LTP, respectively) concomitantly are essential. However, this fundamental bionic trait has not been reported in any existing memristors where STP and LTP can only be induced selectively because of the inability to be decoupled using different loci and mechanisms. In this work, we report the first demonstration of truly concomitant STP and LTP in a three-terminal memristor that uses independent physical phenomena to represent each form of plasticity. The emerging layered material Bi2O2Se is used in memristor for the first time, opening up the prospects for ultra-thin, high-speed and low-power neuromorphic devices. The concerted action of STP and LTP in our memristor allows full-range modulation of the transient synaptic efficacy, from depression to facilitation, by stimulus frequency or intensity, providing a versatile device platform for neuromorphic function implementation. A recurrent neural circuitry model is developed to simulate the intricate "sleep-wake cycle autoregulation" process, in which the concomitance of STP and LTP is posited as a key factor in enabling this neural homeostasis. This work sheds new light on the highly sophisticated computational capabilities of memristors and their prospects for realization of advanced neuromorphic functions.

physics.app-ph↗

arXiv2018

Fractional powers of monotone operators in Hilbert spaces

In this article, we show that if $A$ is a maximal monotone operator on a Hilbert space $H$ with $0$ in the range $\textrm{Rg}(A)$ of $A$, then for every $0<s<1$, the Dirichlet problem associated with the Bessel-type equation $$ A_{1-2s}u:=-\frac{1-2s}{t}u_{t}-u_{tt}+Au\ni 0 $$ is well-posed for boundary values $φ\in \overline{D(A)}^{\mbox{}_{H}}$. This allows us to define the Dirichlet-to-Neumann (DtN) operator $Λ_{s}$ associated with $A_{1-2s}$ as $$ φ\mapsto Λ_{s}φ:=-\lim_{t\to 0+}t^{1-2s}u_{t}(t)\qquad\text{in H.} $$ The existence of the DtN operator $Λ_{s}$ associated with $A_{1-2s}$ is the first step to define fractional powers $A^α$ of monotone (possibly, nonlinear and multivalued) operators $A$ on $H$. We prove that $Λ_{s}$ is monotone on $H$ and if $\overlineΛ_{s}$ is the closure of $Λ_{s}$ in $H\times H_{w}$ then we provide sufficient conditions implying that $-\overlineΛ_{s}$ generates a strongly continuous semigroup on $\overline{D(A)}^{\mbox{}_{H}}$. In addition, we show that if $A$ is completely accretive on $L^{2}(Σ,μ)$ for a $σ$-finite measure space $(Σ,μ)$, then $Λ_{s}$ inherits this property from $A$.

math.AP↗