arXiv subjects

Hongyu Zhao

Publications and source records attributed to Hongyu Zhao.

At least 37 records · Page 2Linked to original sources

arXiv2025

A Control Oriented Fractional-Order Model of Lithium-ion Batteries Based on Caputo Definition

This letter proposes a fractional-order battery model based on the Caputo definition. A closed-form time-domain solution is derived, enabling a simple recursive expression for discrete-time implementation. The model requires only the current and previous time-step states in each iteration, significantly reducing memory usage compared to the conventional Grünwald--Letnikov (G-L) method. This recursive structure is highly compatible with filter design and online parameter identification. Experimental validation on a 40.2~Ah NCM622 cell shows that the proposed first-order model achieves voltage prediction accuracy comparable to a second-order integer-order model. The results demonstrate that the Caputo-based model offers a practical balance between accuracy and computational efficiency, making it well suited for real-time battery management systems (BMS).

eess.SY↗

arXiv2025

Multiple Equilibria Enables Tunable Wetting of Droplets on Patterned Liquid Surfaces

Patterning solid surfaces with varying wettability is important to manage droplets in microfluidics, heat transfer and printing. Solid surface roughness poses fundamental limitations including contact-line pinning and solid friction. Here, we report an experimental strategy and theoretical design principles for Patterned Liquid Surfaces (PaLS) that combines the controlled wettability from patterning with the ultra-smoothness of a lubricant-infused surface. In contrast to a solid, on PaLS a droplet can be in 10 different wetting states. This richness arises from the adaptation of the liquid lubricants, and can be harnessed to control the apparent contact angle of the droplet over the full range of wettability whilst removing contact-line pinning effects induced by the solid surface. In the limit of thin liquid films, we derive surface-averaged laws for the apparent contact angle for each wetting state, which capture both experimental and simulation data. Our results provide a distinct approach to surface patterning that exploits the interaction of fluids with lubricant-impregnated surfaces.

physics.flu-dyn↗

arXiv2025

AARC: Automated Affinity-aware Resource Configuration for Serverless Workflows

Serverless computing is increasingly adopted for its ability to manage complex, event-driven workloads without the need for infrastructure provisioning. However, traditional resource allocation in serverless platforms couples CPU and memory, which may not be optimal for all functions. Existing decoupling approaches, while offering some flexibility, are not designed to handle the vast configuration space and complexity of serverless workflows. In this paper, we propose AARC, an innovative, automated framework that decouples CPU and memory resources to provide more flexible and efficient provisioning for serverless workloads. AARC is composed of two key components: Graph-Centric Scheduler, which identifies critical paths in workflows, and Priority Configurator, which applies priority scheduling techniques to optimize resource allocation. Our experimental evaluation demonstrates that AARC achieves substantial improvements over state-of-the-art methods, with total search time reductions of 85.8% and 89.6%, and cost savings of 49.6% and 61.7%, respectively, while maintaining SLO compliance.

cs.DC↗

arXiv2024

Accuracy and robust early detection of short-circuit faults in single-cell lithium battery

Effective early-stage detection of internal short circuit in lithium-ion batteries is crucial to preventing thermal runaway. This report proposes an effective approach to address this challenging issue, in which the current change, state of charge and resistance are considered simultaneously to depict the voltage differential envelope curve. The envelope naturally utilizes the inherent physical information of the battery and accounts for error interference, providing a high-precision range for battery voltage fluctuations under any operating conditions. This study validates the algorithm using data from 10 fault intervals under dynamic operating condition. The results demonstrate that the algorithm achieves 100% accuracy and responds rapidly, enabling timely detection of early-stage internal short circuit faults in batteries. Compared to signal processing-based and neural network methods, the proposed approach offers significant advantages in both accuracy and practicality, making it highly relevant for the safe application and widespread adoption of lithium-ion batteries.

eess.SY↗

arXiv2024

BenTo: Benchmark Task Reduction with In-Context Transferability

Evaluating large language models (LLMs) is costly: it requires the generation and examination of LLM outputs on a large-scale benchmark of various tasks. This paper investigates how to efficiently reduce the tasks used to benchmark LLMs without affecting the evaluation quality. Our study reveals that task transferability and relevance provide critical information to identify the most representative subset of tasks via optimizing a facility location function. We propose a practically efficient metric for estimating the transferability between two tasks via in-context learning (ICL). By analyzing the pairwise transferability, we can reduce tasks in a modern LLM benchmark (e.g., MMLU or FLAN) to 5% while inducing only a <4% difference to the evaluation on the original benchmark. Compared to prior works, our method is training-free, gradient-free, and highly efficient requiring ICL only.

cs.CL↗

arXiv2024

False Discovery Rate Control via Data Splitting for Testing-after-Clustering

Testing for differences in features between clusters in various applications often leads to inflated false positives when practitioners use the same dataset to identify clusters and then test features, an issue commonly known as ``double dipping''. To address this challenge, inspired by data-splitting strategies for controlling the false discovery rate (FDR) in regressions \parencite{daiFalseDiscoveryRate2023}, we present a novel method that applies data-splitting to control FDR while maintaining high power in unsupervised clustering. We first divide the dataset into two halves, then apply the conventional testing-after-clustering procedure to each half separately and combine the resulting test statistics to form a new statistic for each feature. The new statistic can help control the FDR due to its property of having a sampling distribution that is symmetric around zero for any null feature. To further enhance stability and power, we suggest multiple data splitting, which involves repeatedly splitting the data and combining results. Our proposed data-splitting methods are mathematically proven to asymptotically control FDR in Gaussian settings. Through extensive simulations and analyses of single-cell RNA sequencing (scRNA-seq) datasets, we demonstrate that the data-splitting methods are easy to implement, adaptable to existing single-cell data analysis pipelines, and often outperform other approaches when dealing with weak signals and high correlations among features.

stat.ME↗

arXiv2024

Degrees of Freedom: Search Cost and Self-consistency

Model degrees of freedom ($\df$) is a fundamental concept in statistics because it quantifies the flexibility of a fitting procedure and is indispensable in model selection. To investigate the gap between $\df$ and the number of independent variables in the fitting procedure, \textcite{tibshiraniDegreesFreedomModel2015} introduced the \emph{search degrees of freedom} ($\sdf$) concept to account for the search cost during model selection. However, this definition has two limitations: it does not consider fitting procedures in augmented spaces and does not use the same fitting procedure for $\sdf$ and $\df$. We propose a \emph{modified search degrees of freedom} ($\msdf$) to directly account for the cost of searching in either original or augmented spaces. We check this definition for various fitting procedures, including classical linear regressions, spline methods, adaptive regressions (the best subset and the lasso), regression trees, and multivariate adaptive regression splines (MARS). In many scenarios when $\sdf$ is applicable, $\msdf$ reduces to $\sdf$. However, for certain procedures like the lasso, $\msdf$ offers a fresh perspective on search costs. For some complex procedures like MARS, the $\df$ has been pre-determined during model fitting, but the $\df$ of the final fitted procedure might differ from the pre-determined one. To investigate this discrepancy, we introduce the concepts of \emph{nominal} $\df$ and \emph{actual} $\df$, and define the property of \emph{self-consistency}, which occurs when there is no gap between these two $\df$'s. We propose a correction procedure for MARS to align these two $\df$'s, demonstrating improved fitting performance through extensive simulations and two real data applications.

stat.ME↗

arXiv2024

Geneverse: A collection of Open-source Multimodal Large Language Models for Genomic and Proteomic Research

The applications of large language models (LLMs) are promising for biomedical and healthcare research. Despite the availability of open-source LLMs trained using a wide range of biomedical data, current research on the applications of LLMs to genomics and proteomics is still limited. To fill this gap, we propose a collection of finetuned LLMs and multimodal LLMs (MLLMs), known as Geneverse, for three novel tasks in genomic and proteomic research. The models in Geneverse are trained and evaluated based on domain-specific datasets, and we use advanced parameter-efficient finetuning techniques to achieve the model adaptation for tasks including the generation of descriptions for gene functions, protein function inference from its structure, and marker gene selection from spatial transcriptomic data. We demonstrate that adapted LLMs and MLLMs perform well for these tasks and may outperform closed-source large-scale models based on our evaluations focusing on both truthfulness and structural correctness. All of the training strategies and base models we used are freely accessible.

cs.LG↗

arXiv2024

Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But it also leads to extra cost and computation due to the involvement of LLMs in this process. To reduce the filtering cost, we study Superfiltering: Can we use a smaller and weaker model to select data for finetuning a larger and stronger model? Despite the performance gap between weak and strong language models, we find their highly consistent capability to perceive instruction difficulty and data selection results. This enables us to use a much smaller and more efficient model to filter the instruction data used to train a larger language model. Not only does it largely speed up the data filtering, but the filtered-data-finetuned LLM achieves even better performance on standard benchmarks. Extensive experiments validate the efficacy and efficiency of our approach.

cs.CL↗

arXiv2024

Decomposition with Monotone B-splines: Fitting and Testing

A univariate continuous function can always be decomposed as the sum of a non-increasing function and a non-decreasing one. Based on this property, we propose a non-parametric regression method that combines two spline-fitted monotone curves. We demonstrate by extensive simulations that, compared to standard spline-fitting methods, the proposed approach is particularly advantageous in high-noise scenarios. Several theoretical guarantees are established for the proposed approach. Additionally, we present statistics to test the monotonicity of a function based on monotone decomposition, which can better control Type I error and achieve comparable (if not always higher) power compared to existing methods. Finally, we apply the proposed fitting and testing approaches to analyze the single-cell pseudotime trajectory datasets, identifying significant biological insights for non-monotonically expressed genes through Gene Ontology enrichment analysis. The source code implementing the methodology and producing all results is accessible at https://github.com/szcf-weiya/MonotoneDecomposition.jl.

stat.ME↗

arXiv2024

WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine

We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain. Our system harnesses a large language model of GPT architecture that has been tuned using extensive corpora of finance-related text. As a result, our system possesses the capability to understand complex financial queries, such as "How should I manage my investments during inflation?", and provide informed responses. Furthermore, our system incorporates a local knowledge base and a search engine to retrieve relevant information. The final responses are conditioned on the search results and include proper citations to the sources, thus enjoying an enhanced credibility. Through a range of finance-related questions, we have demonstrated the superior performance of our system compared to other models. To experience our system firsthand, users can interact with our live demo at https://weaverbird.ttic.edu, as well as watch our 2-min video illustration at https://www.youtube.com/watch?v=yofgeqnlrMc.

cs.CL↗

arXiv2024

Application of Deep Learning Methods for Distinguishing Gamma-Ray Bursts from Fermi/GBM TTE Data

To investigate GRBs in depth, it is crucial to develop an effective method for identifying GRBs accurately. Current criteria, e.g., onboard blind search, ground blind search, and target search, are limited by manually set thresholds and perhaps miss GRBs, especially for sub-threshold events. We propose a novel approach that utilizes convolutional neural networks (CNNs) to distinguish GRBs and non-GRBs directly. We structured three CNN models, plain-CNN, ResNet, and ResNet-CBAM, and endeavored to exercise fusing strategy models. Count maps of NaI detectors onboard Fermi/GBM were employed as the input samples of datasets and models were implemented to evaluate their performance on different time scale data. The ResNet-CBAM model trained on 64 ms dataset achieves high accuracy overall, which includes residual and attention mechanism modules. The visualization methods of Grad-CAM and t-SNE explicitly displayed that the optimal model focuses on the key features of GRBs precisely. The model was applied to analyze one-year data, accurately identifying approximately 98% of GRBs listed in the Fermi burst catalog, 8 out of 9 sub-threshold GRBs, and 5 GRBs triggered by other satellites, which demonstrated the deep learning methods could effectively distinguish GRBs from observational data. Besides, thousands of unknown candidates were retrieved and compared with the bursts of SGR J1935+2154 for instance, which exemplified the potential scientific value of these candidates indeed. Detailed studies on integrating our model into real-time analysis pipelines thus may improve their accuracy of inspection, and provide valuable guidance for rapid follow-up observations of multi-band telescopes.

astro-ph.HE↗

arXiv2024

Real-time object detection and robotic manipulation for agriculture using a YOLO-based learning approach

The optimisation of crop harvesting processes for commonly cultivated crops is of great importance in the aim of agricultural industrialisation. Nowadays, the utilisation of machine vision has enabled the automated identification of crops, leading to the enhancement of harvesting efficiency, but challenges still exist. This study presents a new framework that combines two separate architectures of convolutional neural networks (CNNs) in order to simultaneously accomplish the tasks of crop detection and harvesting (robotic manipulation) inside a simulated environment. Crop images in the simulated environment are subjected to random rotations, cropping, brightness, and contrast adjustments to create augmented images for dataset generation. The you only look once algorithmic framework is employed with traditional rectangular bounding boxes for crop localization. The proposed method subsequently utilises the acquired image data via a visual geometry group model in order to reveal the grasping positions for the robotic manipulation.

cs.CV↗

arXiv2023

Explicit Planning Helps Language Models in Logical Reasoning

Language models have been shown to perform remarkably well on a wide range of natural language processing tasks. In this paper, we propose LEAP, a novel system that uses language models to perform multi-step logical reasoning and incorporates explicit planning into the inference procedure. Explicit planning enables the system to make more informed reasoning decisions at each step by looking ahead into their future effects. Moreover, we propose a training strategy that safeguards the planning process from being led astray by spurious features. Our full system significantly outperforms other competing methods on multiple standard datasets. When using small T5 models as its core selection and deduction components, our system performs competitively compared to GPT-3 despite having only about 1B parameters (i.e., 175 times smaller than GPT-3). When using GPT-3.5, it significantly outperforms chain-of-thought prompting on the challenging PrOntoQA dataset. We have conducted extensive empirical studies to demonstrate that explicit planning plays a crucial role in the system's performance.

cs.CL↗

arXiv2023

Multi-Ship Tracking by Robust Similarity metric

Multi-ship tracking (MST) as a core technology has been proven to be applied to situational awareness at sea and the development of a navigational system for autonomous ships. Despite impressive tracking outcomes achieved by multi-object tracking (MOT) algorithms for pedestrian and vehicle datasets, these models and techniques exhibit poor performance when applied to ship datasets. Intersection of Union (IoU) is the most popular metric for computing similarity used in object tracking. The low frame rates and severe image shake caused by wave turbulence in ship datasets often result in minimal, or even zero, Intersection of Union (IoU) between the predicted and detected bounding boxes. This issue contributes to frequent identity switches of tracked objects, undermining the tracking performance. In this paper, we address the weaknesses of IoU by incorporating the smallest convex shapes that enclose both the predicted and detected bounding boxes. The calculation of the tracking version of IoU (TIoU) metric considers not only the size of the overlapping area between the detection bounding box and the prediction box, but also the similarity of their shapes. Through the integration of the TIoU into state-of-the-art object tracking frameworks, such as DeepSort and ByteTrack, we consistently achieve improvements in the tracking performance of these frameworks.

cs.AI↗

arXiv2023

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Discovering genes with similar functions across diverse biomedical contexts poses a significant challenge in gene representation learning due to data heterogeneity. In this study, we resolve this problem by introducing a novel model called Multimodal Similarity Learning Graph Neural Network, which combines Multimodal Machine Learning and Deep Graph Neural Networks to learn gene representations from single-cell sequencing and spatial transcriptomic data. Leveraging 82 training datasets from 10 tissues, three sequencing techniques, and three species, we create informative graph structures for model training and gene representations generation, while incorporating regularization with weighted similarity learning and contrastive learning to learn cross-data gene-gene relationships. This novel design ensures that we can offer gene representations containing functional similarity across different contexts in a joint space. Comprehensive benchmarking analysis shows our model's capacity to effectively capture gene function similarity across multiple modalities, outperforming state-of-the-art methods in gene representation learning by up to 97.5%. Moreover, we employ bioinformatics tools in conjunction with gene representations to uncover pathway enrichment, regulation causal networks, and functions of disease-associated or dosage-sensitive genes. Therefore, our model efficiently produces unified gene representations for the analysis of gene functions, tissue functions, diseases, and species evolution.

cs.LG↗

arXiv2023

Robustness of Learning from Task Instructions

Traditional supervised learning mostly works on individual tasks and requires training on a large set of task-specific examples. This paradigm seriously hinders the development of task generalization since preparing a task-specific example set is costly. To build a system that can quickly and easily generalize to new tasks, task instructions have been adopted as an emerging trend of supervision recently. These instructions give the model the definition of the task and allow the model to output the appropriate answer based on the instructions and inputs. However, task instructions are often expressed in different forms, which can be interpreted from two threads: first, some instructions are short sentences and are pretrained language model (PLM) oriented, such as prompts, while other instructions are paragraphs and are human-oriented, such as those in Amazon MTurk; second, different end-users very likely explain the same task with instructions of different textual expressions. A robust system for task generalization should be able to handle any new tasks regardless of the variability of instructions. However, the system robustness in dealing with instruction-driven task generalization is still unexplored. This work investigates the system robustness when the instructions of new tasks are (i) manipulated, (ii) paraphrased, or (iii) from different levels of conciseness. To our knowledge, this is the first work that systematically studies how robust a PLM is when it is supervised by instructions with different factors of variability.

cs.CL↗

arXiv2023

Learning Brain Connectivity in Social Cognition with Dynamic Network Regression

Dynamic networks have been increasingly used to characterize brain connectivity that varies during resting and task states. In such characterizations, a connectivity network is typically measured at each time point for a subject over a common set of nodes representing brain regions, together with rich subject-level information. A common approach to analyzing such data is an edge-based method that models the connectivity between each pair of nodes separately. However, such approach may have limited performance when the noise level is high and the number of subjects is limited, as it does not take advantage of the inherent network structure. To better understand if and how the subject-level covariates affect the dynamic brain connectivity, we introduce a semi-parametric dynamic network response regression that relates a dynamic brain connectivity network to a vector of subject-level covariates. A key advantage of our method is to exploit the structure of dynamic imaging coefficients in the form of high-order tensors. We develop an efficient estimation algorithm and evaluate the efficacy of our approach through simulation studies. Finally, we present our results on the analysis of a task-related study on social cognition in the Human Connectome Project, where we identify known sex-specific effects on brain connectivity that cannot be inferred using alternative methods.

stat.ME↗