arXiv subjects

Yi Zhuang

Publications and source records attributed to Yi Zhuang.

14 recordsLinked to original sources

arXiv2026

Discontinuous transition to shear flow turbulence

Depending on the type of flow, the transition to turbulence can take one of two forms: either turbulence arises from a sequence of instabilities or from the spatial proliferation of transiently chaotic domains, a process analogous to directed percolation. The former scenario is commonly referred to as a supercritical transition and frequently encountered in flows destabilized by body forces, whereas the latter subcritical transition is common in shear flows. Both cases are inherently continuous in a sense that the transformation from ordered laminar to fully turbulent fluid motion is only accomplished gradually with flow speed. Here we show that these established transition types do not account for the more general setting of shear flows subject to body forces. The combination of the two continuous scenarios leads to the attenuation of spatial coupling; with increasing forcing amplitude, the transition becomes increasingly sharp and eventually discontinuous. We argue that the suppression of laminar-turbulent coexistence and the approach towards a discontinuous phase transition potentially apply to a broad range of situations including flows subject to, for example, buoyancy, centrifugal or electromagnetic forces.

physics.flu-dyn↗

arXiv2026

Acceleration of Modelling with Physics Informed Learning: Frameworks and Perspectives for Real-Time Control of Electrochemical Devices

Electrochemical devices (batteries, fuel cells, and electrolyzers) are in full development, driven by the green energy transition. Their real-time control requires ms predictions in order to take critical decisions during fast transients or faults. The physics behind include coupled multi-physics phenomena that conventional finite element methods cannot solve so fast with the current CPU technology. This paper evaluates the potential of physics-informed machine learning represented by three frameworks: \ac{pinn}, \ac{pideeponet}, and \ac{pino} by evaluating their training effort, inference speed, and extrapolation capacity. Our analysis reveals valuable performance trade-offs. \acp{pinn} offer simplicity for fixed problem instances but require retraining for parameter changes. \ac{pideeponet} enables operator learning across varying conditions with mesh-free geometric flexibility. \ac{pino} delivers superior performance on regular grids, with the strongest extrapolation capabilities due to spectral derivative computation and resolution invariance. \ac{pideeponet} is particularly suited for irregular, unstructured geometries (e.g., porous electrodes or complex flow fields), while \ac{pino} works best for layered, structured-grid problems (e.g., transport across stacked electrochemical layers) requiring fast inference. Possible future applications include real-time lithium concentration prediction for safe fast-charging and micro short circuit detection, water management in fuel cells, and optimal power management in electrolyzers under intermittent renewable inputs. These findings establish physics-informed operator learning as a transformative approach for next-generation electrochemical device controller technology.

physics.app-ph↗

arXiv2026

Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits

We study a decentralized collaborative requesting problem that aims to optimize the information freshness of time-sensitive clients in edge networks consisting of multiple clients, access nodes (ANs), and servers. Clients request content through ANs acting as gateways, without observing AN states or the actions of other clients. We define the reward as the age of information reduction resulting from a client's selection of an AN, and formulate the problem as a non-stationary multi-armed bandit. In this decentralized and partially observable setting, the resulting reward process is history-dependent and coupled across clients, and exhibits both abrupt and gradual changes in expected rewards, rendering classical bandit-based approaches ineffective. To address these challenges, we propose the AGING BANDIT WITH ADAPTIVE RESET algorithm, which combines adaptive windowing with periodic monitoring to track evolving reward distributions. We establish theoretical performance guarantees showing that the proposed algorithm achieves near-optimal performance, and we validate the theoretical results through simulations.

cs.LG↗

arXiv2026

Physics-informed neural network surrogate modeling of single particle model for lithium-ion batteries

Physics-based models play a key role in battery management, yet face challenges in real-time applications due to the high computational cost of solving coupled algebraic-partial differential equations. To accelerate model simulation, this study benchmarks three physics-informed neural network (PINN) architectures for modeling the battery single particle model, including two conventional PINN architectures and a DeepONet-based architecture. Both the accuracy and the generalization of these PINNs have been evaluated and compared under various current conditions. Our results highlight the potential of PINNs in modeling battery physics but also reveal limitations of conventional PINN architectures under highly dynamic current conditions. Among them, the Fourier-enhanced DeepONet achieves superior generalization performance and offers nearly a 10 times speedup compared with numerical solvers. This work provides an example of integrating physics-based models

physics.app-ph↗

arXiv2025

A Note on Code Quality Score: LLMs for Maintainable Large Codebases

Maintaining code quality in large-scale software systems presents significant challenges, particularly in settings where a large numbers of engineers work concurrently on a codebase. This paper introduces Code Quality Score (CQS) system to automatically detect issues with a set of code changes and provide actionable insights. At its core, the CQS system is powered by two Llama3 models, fine-tuned (with SFT and offline RL approaches), to a) detect common code quality issues related to coding best practices and b) to provide good ``critiques'' for LLM-generated code review respectively. To maintain good user experience, we layer the system with hand-crafted rules to filter out incorrect responses/hallucinations. Offline evaluations show that our CQS system is able to achieve an impressive precision rate for identifying valid issues. This system has already been rolled out to developers in an industrial scale setting and has consistently achieved 60\% week over week user helpfulness rate, demonstrating its effectiveness in a real-world environment. In this paper, we present details of the CQS system along with some learnings on curating developer feedback to create training data for LLM fine-tuning.

cs.SE↗

arXiv2025

Age of Computing: A Metric of Computation Freshness in Communication and Computation Cooperative Networks

In communication and computation cooperative networks (3CNs), timely computation is crucial but not always guaranteed. There is a strong demand for a computational task to be completed within a given deadline. The time taken involves both processing time, communication time, and the impact of the deadline. However, a measure of such timeliness in 3CNs is lacking. In this paper, we introduce the novel concept, Age of Computing (AoC), to capture computation freshness in 3CNs. We analyze AoC in a line topology consisting of a source, a transmitter, a receiver, and a computational node. Tasks generated by the source are immediately available at the transmitter, where they enter a communication queue. These tasks then pass to the receiver and subsequently to a computation queue at the computational node for processing. Each task has a deadline, requiring completion within this timeframe. AoC is evaluated under two types of deadlines: (i) soft deadline, tasks can be fed back to the source if delayed beyond the deadline, but with additional latency; (ii) hard deadline, tasks delayed beyond the deadline are discarded. Under both deadlines, we derive the AoC formula and a general expression for the time-average AoC. For the first-come, first-serve discipline, we obtain a closed-form expression for the average AoC under the soft deadline and an approximation for the hard deadline. In addition to freshness, we define computation throughput, providing a general expression and an approximation. To explore the relationship between freshness and throughput, we construct an optimization problem and prove that the objective pair is a weakly Pareto-optimal point. Numerical results validate all the theoretical findings. Additionally, they reveal that under the hard deadline, the computation throughput serves as a reliable proxy for the average AoC.

eess.SY↗

arXiv2024

Prospects for measuring time variation of astrophysical neutrino sources at dark matter detectors

We study the prospects for measuring the time variation of solar and atmospheric neutrino fluxes at future large-scale Xenon and Argon dark matter detectors. For solar neutrinos, a yearly time variation arises from the eccentricity of the Earth's orbit, and, for charged current interactions, from a smaller energy-dependent day-night variation to due flavor regeneration as neutrinos travel through the Earth. For a 100-ton Xenon detector running for 10 years with a Xenon-136 fraction of $\lesssim 0.1\%$, in the electron recoil channel a time-variation amplitude of about 0.8\% is detectable with a power of 90\% and the level of significance of 10\%. This is sufficient to detect time variation due to eccentricity, which has amplitude of $\sim 3\%$. In the nuclear recoil channel, the detectable amplitude is about 10\% under current detector resolution and efficiency conditions, and this generally reduces to about 1\% for improved detector resolution and efficiency, the latter of which is sufficient to detect time variation due to eccentricity. Our analysis assumes both known and unknown periods. We provide scalings to determine the sensitivity to an arbitrary time-varying amplitude as a function of detector parameters. Identifying the time variation of the neutrino fluxes will be important for distinguishing neutrinos from dark matter signals and other detector-related backgrounds, and extracting properties of neutrinos that can be uniquely studied in dark matter experiments.

hep-ph↗

arXiv2024

Detection of astrophysical neutrinos at prospective locations of dark matter detectors

We study the prospects for detection of solar and atmospheric neutrino fluxes at future large-scale dark matter detectors through both electron and nuclear recoils. We specifically examine how the detection prospects change for several prospective detector locations (SURF, SNOlab, Gran Sasso, CJPL, and Kamioka), and improve upon the statistical methodologies used in previous studies. Due to its ability to measure lower neutrino energies than other locations, we find that the best prospects for the atmospheric neutrino flux are at the SURF location, while the prospects are weakest at CJPL because it is restricted to higher neutrino energies. On the contrary, the prospects for the diffuse supernova neutrino background (DSNB) are best at CJPL, due largely to the reduced atmospheric neutrino background at this location. Including full detector resolution and efficiency models, the CNO component of the solar flux is detectable via the electron recoil channel with exposures of $\sim 10^3$ ton-yr for all locations. These results highlight the benefits for employing two detector locations, one at high and one at low latitude.

hep-ph↗

arXiv2023

Superconducting Non-Reciprocity Based on Time-Modulated Coupled-Resonator Systems

We present a unified approach for designing a diverse range of superconducting non-reciprocal components, including circulators, isolators, and uni-directional amplifiers, based on temporally-modulated coupled resonator networks. Our method leverages standard SQUID-based resonators as building blocks, arranged in various configurations such as series-coupled, wye-connected, and lattice-coupled resonators, to realize a wide range of on-chip non-reciprocal devices. Our theoretical studies demonstrated the effectiveness of the proposed approach, achieving circulators and isolators with near-zero insertion losses and isolation greater than 20 dB, and directional amplifiers with forward gain exceeding 10 dB and reverse isolation greater than 20 dB. To validate our findings, we implemented and measured a series-coupled three-resonator superconducting isolator using a single-layer superconducting process. At a base temperature of 20 mK, our device exhibited insertion loss of 1.3 dB in the forward direction, and isolation of up to 25 dB at the center frequency and greater than 15 dB across a bandwidth of 250 MHz in the reverse direction. Our approach promises to enable the design of a broad range of high-performance non-reciprocal devices for superconducting circuits.

quant-ph↗

arXiv2023

There and back again: Solar cycle effects in future measurements of low-energy atmospheric neutrinos

We study the impact of time-dependent solar cycles in the atmospheric neutrino rate at DUNE and Hyper-Kamiokande (HK), focusing in particular on the flux below 1 GeV. Including the effect of neutrino oscillations for the upward-going component that travels through the Earth, we find that across the solar cycle the amplitude of time variation is about $\pm5\%$ at DUNE, and $\pm 1\%$ at HK. At DUNE, the ratio of up/down-going events ranges from 0.45 to 0.85, while at HK, it ranges from 0.75 to 1.5. Over the 11-year solar cycle, we find that the estimated statistical significance for observing time modulation of atmospheric neutrinos is $4.8σ$ for DUNE and $2.0σ$ for HK. Flux measurements at both DUNE and HK will be important for understanding systematics in the low-energy atmospheric flux as well as for understanding the effect of oscillations in low-energy atmospheric neutrinos.

hep-ph↗

arXiv2022

TransLog: A Unified Transformer-based Framework for Log Anomaly Detection

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios especially for low-resource domains. However, previous deep models merely focused on extracting the semantics of log sequence in the same domain, leading to poor generalization on multi-domain logs. Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage. Our model is first pretrained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer the pretrained model to the target domain via the adapter-based tuning. The proposed method is evaluated on three public datasets including one source domain and two target domains. The experimental results demonstrate that our simple yet efficient approach, with fewer trainable parameters and lower training costs in the target domain, achieves state-of-the-art performance on three benchmarks.

cs.LG↗

arXiv2021

Time variation of the atmospheric neutrino flux at dark matter detectors

The cosmic ray flux at the lowest energies, $\lesssim 10$ GeV, is modulated by the solar cycle, inducing a time variation that is expected to carry over into the atmospheric neutrino flux at these energies. Here we estimate this time variation of the atmospheric neutrino flux at five prospective underground locations for multi-tonne scale dark matter detectors (CJPL, Kamioka, LNGS, SNOlab and SURF). We find that between solar minimum and solar maximum, the normalization of the flux changes by $\sim 30\%$ at a high-latitude location such as SURF, while it changes by a smaller amount, $\lesssim 10\%$, at LNGS. A dark matter detector that runs for a period extending through solar cycles will be most effective at identifying this time variation. This opens the possibility to distinguish such neutrino-induced nuclear recoils from dark matter-induced nuclear recoils, thus allowing for the possibility of using timing information to break through the "neutrino floor."

hep-ph↗

arXiv2017

Non-zero sum differential games of forward-backward stochastic differential delayed equations under partial information and application

This paper is concerned with a non-zero sum differential game problem of an anticipated forward-backward stochastic differential delayed equation under partial information. We establish a necessary maximum principle and sufficient verification theorem of the game system by virtue of the duality and convex variational method. We apply the theoretical results and stochastic filtering theory to study a linear-quadratic game system and derive the explicit form of the Nash equilibrium point and discuss the existence and uniqueness in particular cases. As an application, we consider a time-delayed pension fund manage problem with nonlinear expectation and obtain the Nash equilibrium point.

math.OC↗

arXiv2016

A partially observed non-zero sum differential game of forward-backward stochastic differential equations and its application in finance

In this article, we concern a kind of partially observed non-zero sum stochastic differential game based on forward and backward stochastic differential equations (FBSDEs). It is required that each player has his own observation equation, and the corresponding open-loop Nash equilibrium control is required to adapted to the filtration that the observation process generated. To find this open-loop Nash equilibrium point, we prove the maximum principle as a necessary condition of the existence of this point, and give a verification theorem as a sufficient condition to verify it is the real open-loop Nash equilibrium point. Combined this with reality, a financial investment problem is raised. We can obtain the explicit observable investment strategy by using stochastic filtering theory and the results above.

math.OC↗