arXiv subjects

Zheng Miao

Publications and source records attributed to Zheng Miao.

6 recordsLinked to original sources

arXiv2026

A neuromorphic vision system for open-world visual intelligence

Time-efficient and robust visual intelligence remains a critical challenge in unstructured open-world environments, yet current approaches often rely on computationally intensive neural architectures or task-specific sensors with limited versatility. Inspired by biological vision and information bottleneck theory, we report a neuromorphic vision system that performs task-oriented visual intelligence through an information distillation strategy (named as task traction mechanism) implemented on hardware. The system integrates a polarization-sensitive imager with a resistive random-access memory (RRAM) array to progressively distill task-relevant information via light field selection, region of interest extraction, and target anticipation. The neuromorphic vision system conducts visual tasks within an execution time of 193 μs. Evaluation across eight challenging open-world scenarios shows accuracy improvements of 25.54%, 37.73%, and 36.10% for object tracking, object segmentation, and trajectory prediction, respectively, together with an average 30.6-fold reduction in latency relative to state-of-the-art solutions.

eess.IV↗

arXiv2026

$G_2$ flux compactifications

We derive the three-dimensional $\mathcal{N}=1$ effective theories obtained by compactifying all five ten-dimensional string theories on generic seven-dimensional manifolds with $G_2$ structure. The resulting flux compactifications are worked out explicitly, including the full moduli dependence of the scalar potential, kinetic terms, axionic sectors, gauge fields, Stückelberg couplings, and the allowed geometric and form-flux data. Our results extend previous analyses by incorporating fields and fluxes that are generically present in $G_2$ reductions, and provide a unified framework for comparing type IIA, type IIB, type I and heterotic compactifications to three dimensions. In particular, the effective theories organize naturally in terms of the real superpotential formulation of three-dimensional $\mathcal{N}=1$ supergravity, making the relation between fluxes, torsion, Chern--Simons data, and moduli potentials manifest.

hep-th↗

arXiv2026

An interpretable framework using foundation models for fish sex identification

Accurate sex identification in fish is vital for optimizing breeding and management strategies in aquaculture, particularly for species at the risk of extinction. However, most existing methods are invasive or stressful and may cause additional mortality, posing severe risks to threatened or endangered fish populations. To address these challenges, we propose FishProtoNet, a robust, non-invasive computer vision-based framework for sex identification of delta smelt (Hypomesus transpacificus), an endangered fish species native to California, across its full life cycle. Unlike the traditional deep learning methods, FishProtoNet provides interpretability through learned prototype representations while improving robustness by leveraging foundation models to reduce the influence of background noise. Specifically, the FishProtoNet framework consists of three key components: fish regions of interest (ROIs) extraction using visual foundation model, feature extraction from fish ROIs and fish sex identification based on an interpretable prototype network. FishProtoNet demonstrates strong performance in delta smelt sex identification during early spawning and post-spawning stages, achieving the accuracies of 74.40% and 81.16% and corresponding F1 scores of 74.27% and 79.43% respectively. In contrast, delta smelt sex identification at the subadult stage remains challenging for current computer vision methods, likely due to less pronounced morphological differences in immature fish. The source code of FishProtoNet is publicly available at: https://github.com/zhengmiao1/Fish_sex_identification

cs.CV↗

arXiv2025

First Demonstration of Second-order Training of Deep Neural Networks with In-memory Analog Matrix Computing

Second-order optimization methods, which leverage curvature information, offer faster and more stable convergence than first-order methods such as stochastic gradient descent (SGD) and Adam. However, their practical adoption is hindered by the prohibitively high cost of inverting the second-order information matrix, particularly in large-scale neural network training. Here, we present the first demonstration of a second-order optimizer powered by in-memory analog matrix computing (AMC) using resistive random-access memory (RRAM), which performs matrix inversion (INV) in a single step. We validate the optimizer by training a two-layer convolutional neural network (CNN) for handwritten letter classification, achieving 26% and 61% fewer training epochs than SGD with momentum and Adam, respectively. On a larger task using the same second-order method, our system delivers a 5.88x improvement in throughput and a 6.9x gain in energy efficiency compared to state-of-the-art digital processors. These results demonstrate the feasibility and effectiveness of AMC circuits for second-order neural network training, opening a new path toward energy-efficient AI acceleration.

cs.ET↗

arXiv2025

T-dualities and scale-separated AdS$_3$ in type I

We perform three T-dualities on previously found, classical $\mathcal{N}=1$ scale-separated AdS$_3$ solutions of massive type IIA supergravity. These solutions arose from a compactification on a toroidal $G_2$-holonomy space with smeared O2/D2 and O6/D6 sources. The T-dual backgrounds are classical $\mathcal{N}=1$ AdS$_3$ solutions of type IIB supergravity with O5/D5 and O9/D9 sources (type I) compactified on a space with $G_2$-structure and non-vanishing Ricci scalar. We generalize the original solutions in IIA in the T-dual picture and present on the type IIB side fully classical solutions with parametric control, scale separation, and integer conformal dimensions for the dual operators in the corresponding CFT. We also obtain strongly coupled solutions with the same properties. These are S-dual to parametrically controlled classical solutions of the heterotic SO(32) string theory.

hep-th↗

arXiv2024

Clustering-based Multitasking Deep Neural Network for Solar Photovoltaics Power Generation Prediction

The increasing installation of Photovoltaics (PV) cells leads to more generation of renewable energy sources (RES), but results in increased uncertainties of energy scheduling. Predicting PV power generation is important for energy management and dispatch optimization in smart grid. However, the PV power generation data is often collected across different types of customers (e.g., residential, agricultural, industrial, and commercial) while the customer information is always de-identified. This often results in a forecasting model trained with all PV power generation data, allowing the predictor to learn various patterns through intra-model self-learning, instead of constructing a separate predictor for each customer type. In this paper, we propose a clustering-based multitasking deep neural network (CM-DNN) framework for PV power generation prediction. K-means is applied to cluster the data into different customer types. For each type, a deep neural network (DNN) is employed and trained until the accuracy cannot be improved. Subsequently, for a specified customer type (i.e., the target task), inter-model knowledge transfer is conducted to enhance its training accuracy. During this process, source task selection is designed to choose the optimal subset of tasks (excluding the target customer), and each selected source task uses a coefficient to determine the amount of DNN model knowledge (weights and biases) transferred to the aimed prediction task. The proposed CM-DNN is tested on a real-world PV power generation dataset and its superiority is demonstrated by comparing the prediction performance on training the dataset with a single model without clustering.

cs.LG↗