arXiv subjects

Guang Zhao

Publications and source records attributed to Guang Zhao.

15 recordsLinked to original sources

arXiv2026

Auditing Retrieval-Augmented LLM Hypotheses for Longitudinal Cell Painting Morphology

High-content morphological profiling (Cell Painting) yields sensitive, high-dimensional signatures of cellular state, but translating longitudinal morphology trajectories into interpretable biology remains difficult, especially for weak, chronic perturbations such as low-dose-rate ionizing radiation. Large language models (LLMs) can synthesize heterogeneous evidence into biological narratives, yet their scientific use requires quantitative auditing. We present an evaluation-first, retrieval-augmented interpretation framework for longitudinal Cell Painting morphology, applied to a 9-week RPE-1 time course across five dose rates (0.003--6.0 mGy/hr). Week-matched treated-control morphology deltas are combined with retrieved perturbation neighbors, pathway context, and literature evidence through stable evidence identifiers, enabling an LLM to generate structured, evidence-linked hypotheses that are hierarchically summarized while preserving provenance. We introduce two quantitative auditing tests: V1 citation validity, which verifies that cited evidence identifiers exist in the prompt, and V2 proxy-based morphology compatibility, which evaluates consistency between predicted biological processes and the most altered morphology features. In our experiments, V1 detected no invalid evidence references, while V2 showed meaningful morphology compatibility that increased with perturbation strength and was positively associated with an independent morphology drift summary. The framework produces auditable, falsifiable biological hypotheses, including an adaptive phenotype involving metabolic reprogramming and proteostatic stress at lower dose rates (0.003--0.3 mGy/hr). Current limitations include proxy-based evaluation and the lack of ground-truth mechanism labels.

q-bio.QM↗

arXiv2026

Integration and characterization of Readout Electronics System for dN/dx Measurement with Drift Chamber Prototype

To explore the feasibility of high-precision particle identification using the cluster counting technique for the drift chamber, a dedicated readout electronics system with low noise, high bandwidth, and high sampling rate is required. This paper presents the design and performance evaluation of a scalable readout prototype developed for this application. The system architecture integrates a custom front-end with a $1.3\ \text{GSps}$ waveform sampling backend, implemented within a modular 120-channel framework. Laboratory characterization of the 40-channel prototype demonstrates a $-3$ dB analog bandwidth of $460\ \text{MHz}$ and an Equivalent Noise Input current of $0.81\ \mu\text{A}_\text{rms}$. These specifications are essential for preserving the fast temporal features of ionization signals. Furthermore, the system achieves an intrinsic timing jitter of $0.87\ \text{ns}$, which satisfies the timing precision requirements for drift distance measurement. Joint experiments with a drift chamber prototype using cosmic rays verified the system's capability to resolve discrete ionization peaks within piled-up waveforms. These results confirm that the readout electronics provide the signal fidelity and temporal resolution necessary for future cluster counting algorithm development.

physics.ins-det↗

arXiv2025

dN/dx Reconstruction with Deep Learning for High-Granularity TPCs

Particle identification (PID) is essential for future particle physics experiments such as the Circular Electron-Positron Collider and the Future Circular Collider. A high-granularity Time Projection Chamber (TPC) not only provides precise tracking but also enables dN/dx measurements for PID. The dN/dx method estimates the number of primary ionization electrons, offering significant improvements in PID performance. However, accurate reconstruction remains a major challenge for this approach. In this paper, we introduce a deep learning model, the Graph Point Transformer (GraphPT), for dN/dx reconstruction. In our approach, TPC data are represented as point clouds. The network backbone adopts a U-Net architecture built upon graph neural networks, incorporating an attention mechanism for node aggregation specifically optimized for point cloud processing. The proposed GraphPT model surpasses the traditional truncated mean method in PID performance. In particular, the $K/\pi$ separation power improves by approximately 10% to 20% in the momentum interval from 5 to 20 GeV/c.

hep-ex↗

arXiv2025

SCENT: Robust Spatiotemporal Learning for Continuous Scientific Data via Scalable Conditioned Neural Fields

Spatiotemporal learning is challenging due to the intricate interplay between spatial and temporal dependencies, the high dimensionality of the data, and scalability constraints. These challenges are further amplified in scientific domains, where data is often irregularly distributed (e.g., missing values from sensor failures) and high-volume (e.g., high-fidelity simulations), posing additional computational and modeling difficulties. In this paper, we present SCENT, a novel framework for scalable and continuity-informed spatiotemporal representation learning. SCENT unifies interpolation, reconstruction, and forecasting within a single architecture. Built on a transformer-based encoder-processor-decoder backbone, SCENT introduces learnable queries to enhance generalization and a query-wise cross-attention mechanism to effectively capture multi-scale dependencies. To ensure scalability in both data size and model complexity, we incorporate a sparse attention mechanism, enabling flexible output representations and efficient evaluation at arbitrary resolutions. We validate SCENT through extensive simulations and real-world experiments, demonstrating state-of-the-art performance across multiple challenging tasks while achieving superior scalability.

cs.LG↗

arXiv2025

Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting

Mesoscale ocean dynamics play a critical role in climate systems, governing heat transport, hurricane genesis, and drought patterns. However, simulating these processes at high resolution remains computationally prohibitive due to their nonlinear, multiscale nature and vast spatiotemporal domains. Implicit neural representations (INRs) reduce the computational costs as resolution-independent surrogates but fail in many-query scenarios (inverse modeling) requiring rapid evaluations across diverse parameters. We present PINROD, a novel framework combining dynamics-aware implicit neural representations with parameterized neural ordinary differential equations to address these limitations. By integrating parametric dependencies into latent dynamics, our method efficiently captures nonlinear oceanic behavior across varying boundary conditions and physical parameters. Experiments on ocean mesoscale activity data show superior accuracy over existing baselines and improved computational efficiency compared to standard numerical simulations.

cs.LG↗

arXiv2024

Conceptual Design of the Muonium-to-Antimuonium Conversion Experiment (MACE)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. The Muonium-to-Antimuonium Conversion Experiment (MACE) is designed to utilize a high-intensity muon beam, a Michel electron magnetic spectrometer, a positron transport system, and a positron detection system, to either discover or constrain this rare process with a conversion probability of $\mathcal{O}(10^{-13})$. This article presents an overview of the theoretical framework as well as a detailed description of the experimental design for the search for muonium-to-antimuonium conversion.

hep-ex↗

arXiv2024

Cluster Counting Algorithm for the CEPC Drift Chamber using LSTM and DGCNN

The particle identification (PID) of hadrons plays a crucial role in particle physics experiments, especially in flavor physics and jet tagging. The cluster-counting method, which measures the number of primary ionizations in gaseous detectors, is a promising breakthrough in PID. However, developing an effective reconstruction algorithm for cluster counting remains challenging. To address this challenge, we propose a cluster-counting algorithm based on long short-term memory and dynamic graph convolutional neural networks for the CEPC drift chamber. Experiments on Monte Carlo simulated samples demonstrate that our machine-learning-based algorithm surpasses traditional methods. It improves the $K/\pi$ separation of PID by 10\%, meeting the PID requirements of CEPC.

hep-ex↗

arXiv2024

Peak finding algorithm for cluster counting with domain adaptation

Cluster counting in drift chamber is the most promising breakthrough in particle identification (PID) technique in particle physics experiment. Reconstruction algorithm is one of the key challenges in cluster counting. In this paper, a semi-supervised domain adaptation (DA) algorithm is developed and applied on the peak finding problem in cluster counting. The algorithm uses optimal transport (OT), which provides geometric metric between distributions, to align the samples between the source (simulation) and target (data) samples, and performs semi-supervised learning with the samples in target domain that are partially labeled with the continuous wavelet transform (CWT) algorithm. The model is validated by the pseudo data with labels, which achieves performance close to the fully supervised model. When applying the algorithm on real experimental data, taken at CERN with a 180 GeV/c muon beam, it shows better classification power than the traditional derivative-based algorithm, and the performance is stable for experimental data samples across varying track lengths.

physics.ins-det↗

arXiv2023

Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale

Neural Architecture Search (NAS) has demonstrated its efficacy in computer vision and potential for ranking systems. However, prior work focused on academic problems, which are evaluated at small scale under well-controlled fixed baselines. In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle. In this paper, we present Rankitect, a NAS software framework for ranking systems at Meta. Rankitect seeks to build brand new architectures by composing low level building blocks from scratch. Rankitect implements and improves state-of-the-art (SOTA) NAS methods for comprehensive and fair comparison under the same search space, including sampling-based NAS, one-shot NAS, and Differentiable NAS (DNAS). We evaluate Rankitect by comparing to multiple production ranking models at Meta. We find that Rankitect can discover new models from scratch achieving competitive tradeoff between Normalized Entropy loss and FLOPs. When utilizing search space designed by engineers, Rankitect can generate better models than engineers, achieving positive offline evaluation and online A/B test at Meta scale.

cs.LG↗

arXiv2022

Simulation study of particle identification using cluster counting technique for the BESIII drift chamber

The particle identification of charged hadrons, especially for the separation of $K$ and $π$, is crucial for the flavour physics study. Ionization measurement with the cluster counting technique, which has much less fluctuation than traditional $dE/dx$ measurement, is expected to provide better particle identification for the BESIII experiment. Simulation studies, including a Garfield++ based waveform analysis and a performance study of K/πidentification in the BESIII, offline software system have been performed. The results show that $K/π$ separation power and PID efficiency would be improved significantly in the momentum range above 1.2 GeV/c using cluster counting technique even with conservative resolution assumption.

hep-ex↗

arXiv2022

Snowmass2021 Whitepaper: Muonium to antimuonium conversion

The spontaneous muonium to antimuonium conversion is one of the interesting charged lepton flavor violation processes. It serves as a clear indication of new physics and plays an important role in constraining the parameter space beyond Standard Model. MACE is a proposed experiment to probe such a phenomenon and expected to enhance the sensitivity to the conversion probability by more than two orders of magnitude from the current best upper constraint obtained by the PSI experiment two decades ago. Recent developments in the theoretical and experimental aspects to search for such a rare process are summarized.

hep-ph↗

arXiv2019

Fast Exact Computation of Expected HyperVolume Improvement

In multi-objective Bayesian optimization and surrogate-based evolutionary algorithms, Expected HyperVolume Improvement (EHVI) is widely used as the acquisition function to guide the search approaching the Pareto front. This paper focuses on the exact calculation of EHVI given a nondominated set, for which the existing exact algorithms are complex and can be inefficient for problems with more than three objectives. Integrating with different decomposition algorithms, we propose a new method for calculating the integral in each decomposed high-dimensional box in constant time. We develop three new exact EHVI calculation algorithms based on three region decomposition methods. The first grid-based algorithm has a complexity of $O(m\cdot n^m)$ with $n$ denoting the size of the nondominated set and $m$ the number of objectives. The Walking Fish Group (WFG)-based algorithm has a worst-case complexity of $O(m\cdot 2^n)$ but has a better average performance. These two can be applied for problems with any $m$. The third CLM-based algorithm is only for $m=3$ and asymptotically optimal with complexity $Θ(n\log{n})$. Performance comparison results show that all our three algorithms are at least twice faster than the state-of-the-art algorithms with the same decomposition methods. When $m>3$, our WFG-based algorithm can be over $10^2$ faster than the corresponding existing algorithms. Our algorithm is demonstrated in an example involving efficient multi-objective material design with Bayesian optimization.

stat.ML↗

arXiv2019

Adaptive Activity Monitoring with Uncertainty Quantification in Switching Gaussian Process Models

Emerging wearable sensors have enabled the unprecedented ability to continuously monitor human activities for healthcare purposes. However, with so many ambient sensors collecting different measurements, it becomes important not only to maintain good monitoring accuracy, but also low power consumption to ensure sustainable monitoring. This power-efficient sensing scheme can be achieved by deciding which group of sensors to use at a given time, requiring an accurate characterization of the trade-off between sensor energy usage and the uncertainty in ignoring certain sensor signals while monitoring. To address this challenge in the context of activity monitoring, we have designed an adaptive activity monitoring framework. We first propose a switching Gaussian process to model the observed sensor signals emitting from the underlying activity states. To efficiently compute the Gaussian process model likelihood and quantify the context prediction uncertainty, we propose a block circulant embedding technique and use Fast Fourier Transforms (FFT) for inference. By computing the Bayesian loss function tailored to switching Gaussian processes, an adaptive monitoring procedure is developed to select features from available sensors that optimize the trade-off between sensor power consumption and the prediction performance quantified by state prediction entropy. We demonstrate the effectiveness of our framework on the popular benchmark of UCI Human Activity Recognition using Smartphones.

cs.LG↗

arXiv2018

Multi-Objective Bayesian Materials Discovery: Application on the Discovery of Precipitation Strengthened NiTi Shape Memory Alloys through Micromechanical Modeling

In this study, a framework for the multi-objective materials discovery based on Bayesian approaches is developed. The capabilities of the framework are demonstrated on an example case related to the discovery of precipitation strengthened NiTi shape memory alloys with up to three desired properties. In the presented case the framework is used to carry out an efficient search of the shape memory alloys with desired properties while minimizing the required number of computational experiments. The developed scheme features a Bayesian optimal experimental design process that operates in a closed loop. A Gaussian process regression model is utilized in the framework to emulate the response and uncertainty of the physical/computational data while the sequential exploration of the materials design space is carried out by using an optimal policy based on the expected hyper-volume improvement acquisition function. This scalar metric provides a measure of the utility of querying the materials design space at different locations, irrespective of the number of objectives in the performed task. The framework is deployed for the determination of the composition and microstructure of precipitation-strengthened NiTi shape memory alloys with desired properties, while the materials response as a function of microstructure is determined through a thermodynamically-consistent micromechanical model.

cond-mat.mtrl-sci↗

arXiv2016

Radiation Studies for the Target Station of the MOMENT

The discovery of the neutrino mixing angle $θ_{13}$ opens new opportunities for the discovery of the leptonic CP violation for high intensity neutrino beams. MOMENT a future neutrino facility with a high-power proton beam of 15 MW from a continuous-wave linac is focused on that discovery. The high power of the proton beam causes extreme radiation conditions for the facility and especially for the target station where the pion capture system of five superconducting solenoids is located. In this paper initial studies are performed for the effects of the radiation on the solenoid structure and the area surrounding it. A concept cooling system is also proposed.

physics.ins-det↗