arXiv subjects

Zirui Peng

Publications and source records attributed to Zirui Peng.

5 recordsLinked to original sources

arXiv2026

Phase-Interface Instance Segmentation as a Visual Sensor for Laboratory Process Monitoring

Reliable visual monitoring of chemical experiments remains challenging in transparent glassware, where weak phase boundaries and optical artifacts degrade conventional segmentation. We formulate laboratory phenomena as the time evolution of phase interfaces and introduce the Chemical Transparent Glasses dataset 2.0 (CTG 2.0), a vessel-aware benchmark with 3,668 images, 23 glassware categories, and five multiphase interface types for phase-interface instance segmentation. Building on YOLO11m-seg, we propose LGA-RCM-YOLO, which combines Local-Global Attention (LGA) for robust semantic representation and a Rectangular Self-Calibration Module (RCM) for boundary refinement of thin, elongated interfaces. On CTG 2.0, the proposed model achieves 84.4% AP@0.5 and 58.43% AP@0.5-0.95, improving over the YOLO11m baseline by 6.42 and 8.75 AP points, respectively, while maintaining near real-time inference (13.67 FPS, RTX 3060). An auxiliary color-attribute head further labels liquid instances as colored or colorless with 98.71% precision and 98.32% recall. Finally, we demonstrate continuous process monitoring in separatory-funnel phase separation and crystallization, showing that phase-interface instance segmentation can serve as a practical visual sensor for laboratory automation.

cs.CV↗

arXiv2025

Probabilistic Net Load Forecasting for High-Penetration RES Grids Utilizing Enhanced Conditional Diffusion Model

The proliferation of intermittent distributed renewable energy sources (RES) in modern power systems has fundamentally compromised the reliability and accuracy of deterministic net load forecasting. Generative models, particularly diffusion models, demonstrate exceptional potential in uncertainty quantification for scenario forecasting. Nevertheless, their probabilistic predictive capabilities and conditional bootstrapping mechanisms still remain underexplored. In this paper, a day-ahead probabilistic net load forecasting framework is developed by systematically quantifying epistemic uncertainty and aleatoric variability using the feature-informed enhanced conditional diffusion model (ECDM). The ECDM architecture implements the net load distribution generation process using an imputation-based conditional diffusion model, where multi-modal conditional inputs, such as weather and calendar data, are fused via cross-attention mechanisms. Specifically, historical net load profiles are utilized to guide the reverse diffusion trajectory through non-parametric imputation operators preserving spatial-temporal integrity. To capture periodic characteristics, a novel weekly arrangement method is also introduced, while an unconditional model is integrated to ensure diversity in the generated scenarios. Subsequently, the maximum probabilistic points and probability intervals of predicted net load are obtained by the adaptive kernel density estimation under RES intermittency. Moreover, ECDM is extented to multi-energy forecast framework, attempting to increase interpretability of the net load predictions. Numerical experiments on a publicly available dataset demonstrate the superior forecasting performance of the proposed method compared to existing state-of-the-art approaches.

eess.SY↗

arXiv2025

Universality of the complete-graph Potts model with $0< q \leq 2$

Universality is a fundamental concept in modern physics. For the $q$-state Potts model, the critical exponents are merely determined by the order-parameter symmetry $S_q$, spatial dimensionality and interaction range, independent of microscopic details. In a simplest and mean-field treatment--i.e., the Potts model on complete graph (CG), the phase transition is further established to be of percolation universality for the range of $0 < q <2$. By simulating the CG Potts model in the random-cluster representation, we numerically demonstrate such a hyper-universality that the critical exponents are the same for $0< q <2$ and, moreover, the Ising system ($q = 2$) exhibits a variety of critical geometric properties in percolation universality. On the other hand, many other universal properties in the finite-size scaling (FSS) theory, including Binder-like ratios and distribution function of the order parameter, are observed to be $q$-dependent. Our finding provides valuable insights for the study of critical phenomena in finite spatial dimensions, particularly when the FSS theory is utilized.

cond-mat.stat-mech↗

arXiv2023

Sweeny dynamics for the random-cluster model with small $Q$

The Sweeny algorithm for the $Q$-state random-cluster model in two dimensions is shown to exhibit a rich mixture of critical dynamical scaling behaviors. As $Q$ decreases, the so-called critical speeding-up for non-local quantities becomes more and more pronounced. However, for some quantity of specific local pattern -- e.g., the number of half faces on the square lattice, we observe that, as $Q \to 0$, the integrated autocorrelation time $\tau$ diverges as $Q^{-\zeta}$, with $\zeta \simeq 1/2$, leading to the non-ergodicity of the Sweeny method for $Q \to 0$. Such $Q$-dependent critical slowing-down, attributed to the peculiar form of the critical bond weight $v=\sqrt{Q}$, can be eliminated by a combination of the Sweeny and the Kawasaki algorithm. Moreover, by classifying the occupied bonds into bridge bonds and backbone bonds, and the empty bonds into internal-perimeter bonds and external-perimeter bonds, one can formulate an improved version of the Sweeny-Kawasaki method such that the autocorrelation time for any quantity is of order $O(1)$.

cond-mat.stat-mech↗

arXiv2022

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations

In this paper, we propose a novel and practical mechanism which enables the service provider to verify whether a suspect model is stolen from the victim model via model extraction attacks. Our key insight is that the profile of a DNN model's decision boundary can be uniquely characterized by its Universal Adversarial Perturbations (UAPs). UAPs belong to a low-dimensional subspace and piracy models' subspaces are more consistent with victim model's subspace compared with non-piracy model. Based on this, we propose a UAP fingerprinting method for DNN models and train an encoder via contrastive learning that takes fingerprint as inputs, outputs a similarity score. Extensive studies show that our framework can detect model IP breaches with confidence > 99.99 within only 20 fingerprints of the suspect model. It has good generalizability across different model architectures and is robust against post-modifications on stolen models.

cs.CR↗