Searcharxiv⌕ Search

arXiv subjects

Yuchen Yin

Publications and source records attributed to Yuchen Yin.

10 recordsLinked to original sources
arXiv2026

Artificial Intelligence in a Photonic Temporal Processor

Optical neural networks (ONNs) promise high-throughput and energy-efficient artificial intelligence, yet essentially all implementations so far encode information across space either in free-space arrays or in integrated waveguide meshes, tying the number of neurons to the number of physical components and fixes the routing topology at fabrication. Here we show that moving the computation into time decouples computational dimension from hardware dimension. Exploiting space-time duality, we implement optical diffraction and interference entirely in time domain, using thin-film lithium niobate modulators as time lenses and temporal masks, with chromatic dispersion providing the coupling between successive temporal neurons. We experimentally verify high-order, complex-valued matrix-matrix multiplications using just a single optical input/output port, scaling the computational dimensions far beyond the channel count. By incorporating optical feedback, we extend this platform into versatile neural networks, where the network layers, neuron numbers, and synaptic connections are fully programmable and in-situ trainable. Our temporal diffractive neural networks are successfully validated on various classification benchmarks, alongside image and video generation tasks. Notably, using this platform we demonstrate an all-analogue generative pipeline in which the latent variable is drawn directly from amplified spontaneous emission, so that no digital sampling or electronic modulation appears anywhere in the generative path. Furthermore, high-resolution images and videos are generated at high frame rates, outperforming state-of-the-art modulator-refresh-limited optical generative systems. These results establish a unified photonic temporal computing framework, providing a scalable and deployable pathway toward next-generation machine intelligence.

physics.optics↗
arXiv2026

Nonexistence of blow-up solutions with smooth radiation for energy-critical equivariant wave maps

We study $k$-equivariant energy critical wave maps $\mathbb{R}^{1+2} \to \mathbb{S}^2$, for any equivariance degree $k\ge 2$. We prove that the radiation associated with any finite-energy blow-up solution cannot satisfy a certain regularity condition; in particular, it cannot be smooth. The assumption $k \geq 2$ is necessary, since for $k = 1$ such solutions are known to exist. The starting point of our analysis is the soliton resolution theorem. The key ingredient is a novel application of the modulation method, in which we compare the effects of the radiation and inner bubbles to study the dynamic behavior of the widest bubble.

math.AP↗
arXiv2026

Approaching physical limits of latent dimensionality in optical computing

The physical implementation of artificial intelligence requires mapping computational processes onto the dynamic physical processes of the underlying computing platform. The photonic processors offer an intrinsically parallel and low energy framework for this mapping, however, a mismatch between the potential computing capability of a bounded optical domain and the human accessible manipulation range sets a hard integration density ceiling on existing architectures. Here, we address this challenge by investigating the integration density limits in photonic processors through exploring the fundamental physical limits on the latent dimensionality for maximum expressivity of a bounded optical domain. These physical limits potentially serve as universal metrics for evaluating optical computing capacity. To validate these, we design and realize ultracompact multimode photonic processors approaching these limits: a 2.2 um by 8 um processor achieves 86.7 % accuracy in experiment for iris flower classification, and a 20.6 um by 44.8 um processor reaches 92.9% accuracy in handwritten digit recognition. Finally, we scale this architecture to highly complex tasks by implementing a generative diffusion model for image synthesis. By grounding photonic processor design in the wave physics origin of latent dimensionality, our results supply the missing theoretical reference point for optical computing architecture.

physics.optics↗
arXiv2026

On-chip Multimode Opto-electronic Neural Network

Opto-electronic computing combines the complementary strengths of photonics and electronics to deliver ultrahigh computational throughput with high energy efficiency. However, its practical deployment for real-world applications has been limited by architectures that rely on delicate wavelength management or phase-sensitive coherent detection. Here, we demonstrate the first multimode opto-electronic neural network (MOENN) on a silicon-on-insulator platform. By utilizing orthogonal waveguide eigenmodes as independent information carriers, our architecture achieves robust single-wavelength computation that is inherently immune to spectral crosstalk and phase noise. The fabricated MOENN chip monolithically integrates all functional components, including input encoders, programmable mode-division fan-in/-out units, and most importantly, the nonlinear multimode activation functions. We report the system's versatility through in-situ training via a genetic algorithm, successfully resolving the nonlinear decision boundaries of a two-class dataset and achieving 92.1% accuracy on the Iris classification benchmark. Furthermore, we reconfigure the MOENN into a one-dimensional convolutional neural network, attaining an accuracy of 90.7% on the electrocardiogram-based emotion recognition task. This work establishes a new opto-electronic computing paradigm of simple control and excellent robustness, providing a compelling path toward scalable, deployable photonic intelligence.

physics.optics↗
arXiv2025

Deep Photonic Reservoir Computing with On-chip Nonlinearity

Reservoir computing, renowned for its low training cost, has emerged as a promising lightweight paradigm for efficient spatiotemporal processing,it remains challenging to realize deep photonic reservoir computing (DPRC) systems, due to the lack of scalable on-chip nonlinearity. Here, we introduce a versatile time delayed DPRC framework that natively supports deep and concurrent spatiotemporal processing entirely in the optical domain. At its core, the system leverages free carrier dynamics in silicon microring resonators to provide the fundamental nonlinearity and short term memory, and these nonlinear nodes are interconnected through true time delay lines that establish shared long-term memory. Benefiting from intrinsic physical nonlinearity and multi-timescale fading memory, this simple yet effective architecture demonstrates remarkable high dimensional representation capabilities. On the NTU RGB D benchmark, the parameter efficient DPRC system achieves superior action recognition accuracies compared to mainstream deep learning models, while requiring only a single shot regression training procedure. We further verify a prototype DPRC chip that excels across diverse dataset classification and time series prediction tasks. It enables a streamlined all optical pipeline between hierarchical layers, delivering a consistent computational density of 334.25 TOPs/mm2, independent of the reservoir depth and three orders of magnitude higher than conventional approaches. Moreover, its performance scales with near-zero hardware overhead by utilizing additional wavelength channels. This DPRC network is highly scalable on a silicon photonic platform, with flexible extension to hundreds of deep reservoir layers and parallel channels, paving the way toward intelligent optoelectronic systems for advanced real time processing and parallel decision making.

physics.optics↗
arXiv2025

A modified RIME algorithm with covariance learning and diversity enhancement for numerical optimization

Metaheuristics are widely applied for their ability to provide more efficient solutions. The RIME algorithm is a recently proposed physical-based metaheuristic algorithm with certain advantages. However, it suffers from rapid loss of population diversity during optimization and is prone to fall into local optima, leading to unbalanced exploitation and exploration. To address the shortcomings of RIME, this paper proposes a modified RIME with covariance learning and diversity enhancement (MRIME-CD). The algorithm applies three strategies to improve the optimization capability. First, a covariance learning strategy is introduced in the soft-rime search stage to increase the population diversity and balance the over-exploitation ability of RIME through the bootstrapping effect of dominant populations. Second, in order to moderate the tendency of RIME population to approach the optimal individual in the early search stage, an average bootstrapping strategy is introduced into the hard-rime puncture mechanism, which guides the population search through the weighted position of the dominant populations, thus enhancing the global search ability of RIME in the early stage. Finally, a new stagnation indicator is proposed, and a stochastic covariance learning strategy is used to update the stagnant individuals in the population when the algorithm gets stagnant, thus enhancing the ability to jump out of the local optimal solution. The proposed MRIME-CD algorithm is subjected to a series of validations on the CEC2017 test set, the CEC2022 test set, and the experimental results are analyzed using the Friedman test, the Wilcoxon rank sum test, and the Kruskal Wallis test. The results show that MRIME-CD can effectively improve the performance of basic RIME and has obvious superiorities in terms of solution accuracy, convergence speed and stability.

cs.NE↗
arXiv2025

A multi-strategy improved gazelle optimization algorithm for solving numerical optimization and engineering applications

Aiming at the shortcomings of the gazelle optimization algorithm, such as the imbalance between exploration and exploitation and the insufficient information exchange within the population, this paper proposes a multi-strategy improved gazelle optimization algorithm (MSIGOA). To address these issues, MSIGOA proposes an iteration-based updating framework that switches between exploitation and exploration according to the optimization process, which effectively enhances the balance between local exploitation and global exploration in the optimization process and improves the convergence speed. Two adaptive parameter tuning strategies improve the applicability of the algorithm and promote a smoother optimization process. The dominant population-based restart strategy enhances the algorithms ability to escape from local optima and avoid its premature convergence. These enhancements significantly improve the exploration and exploitation capabilities of MSIGOA, bringing superior convergence and efficiency in dealing with complex problems. In this paper, the parameter sensitivity, strategy effectiveness, convergence and stability of the proposed method are evaluated on two benchmark test sets including CEC2017 and CEC2022. Test results and statistical tests show that MSIGOA outperforms basic GOA and other advanced algorithms. On the CEC2017 and CEC2022 test sets, the proportion of functions where MSIGOA is not worse than GOA is 92.2% and 83.3%, respectively, and the proportion of functions where MSIGOA is not worse than other algorithms is 88.57% and 87.5%, respectively. Finally, the extensibility of MSIGAO is further verified by several engineering design optimization problems.

cs.NE↗
arXiv2025

Regression and Forecasting of U.S. Stock Returns Based on LSTM

This paper analyses the investment returns of three stock sectors, Manuf, Hitec, and Other, in the U.S. stock market, based on the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model, in order to test the validity of the Fama-French three-factor model, the Carhart four-factor model, and the Fama-French five-factor model for the three sectors of the market. French five-factor model for the three sectors of the market. Also, the LSTM model is used to explore the additional factors affecting stock returns. The empirical results show that the Fama-French five-factor model has better validity for the three segments of the market under study, and the LSTM model has the ability to capture the factors affecting the returns of certain industries, and can better regress and predict the stock returns of the relevant industries. Keywords- Fama-French model; Carhart model; Factor model; LSTM model.

q-fin.ST↗
arXiv2024

Tail Risk Alert Based on Conditional Autoregressive VaR by Regression Quantiles and Machine Learning Algorithms

As the increasing application of AI in finance, this paper will leverage AI algorithms to examine tail risk and develop a model to alter tail risk to promote the stability of US financial markets, and enhance the resilience of the US economy. Specifically, the paper constructs a multivariate multilevel CAViaR model, optimized by gradient descent and genetic algorithm, to study the tail risk spillover between the US stock market, foreign exchange market and credit market. The model is used to provide early warning of related risks in US stocks, US credit bonds, etc. The results show that, by analyzing the direction, magnitude, and pseudo-impulse response of the risk spillover, it is found that the credit market's spillover effect on the stock market and its duration are both greater than the spillover effect of the stock market and the other two markets on credit market, placing credit market in a central position for warning of extreme risks. Its historical information on extreme risks can serve as a predictor of the VaR of other markets.

q-fin.RM↗