arXiv subjects

Yang Zhong

Publications and source records attributed to Yang Zhong.

At least 37 records · Page 2Linked to original sources

arXiv2025

Unsupervised deep learning model for fast energy layer pre-selection of delivery-efficient proton arc therapy plan optimization of nasopharyngeal carcinoma

Proton arc therapy (PAT) is an emerging and promising modality in radiotherapy, offering improved dose distribution and treatment robustness over intensity-modulated proton therapy. Yet, identifying the optimal energy layer (EL) sequence remains challenging due to the intensive computational demand and prolonged treatment delivery time. This study proposes an unsupervised deep learning model for fast EL pre-selection that minimizes EL switch (ELS) time while maintaining high plan quality. We introduce a novel data representation method, spot-count representation, which encodes the number of proton spots intersecting the target and organs at risk (OAR) in a matrix structured by sorted gantry angles and energy layers. This representation serves as the input of an U-Net style architecture, SPArc_dl, which is trained using a tri-objective function: maximizing spot-counts on target, minimizing spot-counts on OAR, and reducing ELS time. The model is evaluated on 35 nasopharyngeal cancer cases, and its performance is compared to SPArc_particle_swarm (SPArc_ps). SPArc_dl produces EL pre-selection that significantly improves both plan quality and delivery efficiency. Compared to SPArc_ps, it enhances the conformity index by 0.1 (p<0.01), reduces the homogeneity index by 0.71 (p<0.01), lowers the brainstem mean dose by 0.25 (p<0.01), and shortens the ELS time by 37.2% (p < 0.01). The results unintentionally reveal employing unchanged ELS is more time-wise efficient than descended ELS. SPArc_dl's inference time is within 1 second. However, SPArc_dl plan demonstrates limitation in robustness. The proposed spot-count representation lays a foundation for incorporating unsupervised deep learning approaches into EL pre-selection task. SPArc_dl is a fast tool for generating high-quality PAT plans by strategically pre-selecting EL to reduce delivery time while maintaining excellent dosimetric performance.

physics.med-ph↗

arXiv2025

A Survey on Vision-Language-Action Models for Autonomous Driving

The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.

cs.CV↗

arXiv2025

A Universal Spin-Orbit-Coupled Hamiltonian Model for Accelerated Quantum Material Discovery

The accurate modeling of spin-orbit coupling (SOC) effects in diverse complex systems remains a significant challenge due to the high computational demands of density functional theory (DFT) and the limited transferability of existing machine-learning frameworks. This study addresses these limitations by introducing Uni-HamGNN, a universal SOC Hamiltonian graph neural network that is applicable across the periodic table. By decomposing the SOC Hamiltonian into spin-independent and SOC correction terms, our approach preserves SU(2) symmetry while significantly reducing parameter requirements. Based on this decomposition, we propose a delta-learning strategy to separately fit the two components, thereby addressing the training difficulties caused by magnitude discrepancies between them and enabling efficient training. The model achieves remarkable accuracy (mean absolute error of 0.0025 meV for the SOC-related component) and demonstrates broad applicability through high-throughput screening of the GNoME dataset for topological insulators, as well as precise predictions for 2D valleytronic materials and transition metal dichalcogenide (TMD) heterostructures. This breakthrough eliminates the need for system-specific retraining and costly SOC-DFT calculations, paving the way for rapid discovery of quantum materials.

cond-mat.mtrl-sci↗

arXiv2025

ODverse33: Is the New YOLO Version Always Better? A Multi Domain benchmark from YOLO v5 to v11

You Look Only Once (YOLO) models have been widely used for building real-time object detectors across various domains. With the increasing frequency of new YOLO versions being released, key questions arise. Are the newer versions always better than their previous versions? What are the core innovations in each YOLO version and how do these changes translate into real-world performance gains? In this paper, we summarize the key innovations from YOLOv1 to YOLOv11, introduce a comprehensive benchmark called ODverse33, which includes 33 datasets spanning 11 diverse domains (Autonomous driving, Agricultural, Underwater, Medical, Videogame, Industrial, Aerial, Wildlife, Retail, Microscopic, and Security), and explore the practical impact of model improvements in real-world, multi-domain applications through extensive experimental results. We hope this study can provide some guidance to the extensive users of object detection models and give some references for future real-time object detector development.

cs.CV↗

arXiv2025

Discourse-Driven Evaluation: Unveiling Factual Inconsistency in Long Document Summarization

Detecting factual inconsistency for long document summarization remains challenging, given the complex structure of the source article and long summary length. In this work, we study factual inconsistency errors and connect them with a line of discourse analysis. We find that errors are more common in complex sentences and are associated with several discourse features. We propose a framework that decomposes long texts into discourse-inspired chunks and utilizes discourse information to better aggregate sentence-level scores predicted by natural language inference models. Our approach shows improved performance on top of different model baselines over several evaluation benchmarks, covering rich domains of texts, focusing on long document summarization. This underscores the significance of incorporating discourse features in developing models for scoring summaries for long document factual inconsistency.

cs.CL↗

arXiv2025

Linear Scaling Calculation of Atomic Forces and Energies with Machine Learning Local Density Matrix

Accurately calculating energies and atomic forces with linear-scaling methods is a crucial approach to accelerating and improving molecular dynamics simulations. In this paper, we introduce HamGNN-DM, a machine learning model designed to predict atomic forces and energies using local density matrices in molecular dynamics simulations. This approach achieves efficient predictions with a time complexity of O(n), making it highly suitable for large-scale systems. Experiments in different systems demonstrate that HamGNN-DM achieves DFT-level precision in predicting the atomic forces in different system sizes, which is vital for the molecular dynamics. Furthermore, this method provides valuable electronic structure information throughout the dynamics and exhibits robust performance.

cond-mat.mtrl-sci↗

arXiv2024

In-depth Study of Spin- and Momentum-Dependent Interaction Potentials Between Two Spin-1/2 Fermions Mediated by Light Spin-0 Particles

We present a calculation by including the relativistic and off-shell contributions to the interaction potentials between two spin-1/2 fermions mediated by the exchange of light spin-0 particles, in both momentum and coordinate spaces. Our calculation is based on the four-point Green function rather than the scattering amplitude. Among the sixteen potential components, eight that vanish in the non-relativistic limit are shown to acquire nonzero relativistic and off-shell corrections. In addition to providing relativistic and off-shell corrections to the operator basis commonly used in the literature, we introduce an alternative operator basis that facilitates the derivation of interaction potentials in coordinate space. Furthermore, we calculate both the long-range and short-range components of the potentials, which can be useful for future experimental analyses at both macroscopic and atomic scales.

hep-ph↗

arXiv2024

Efficient prediction of potential energy surface and physical properties with Kolmogorov-Arnold Networks

The application of machine learning methodologies for predicting properties within materials science has garnered significant attention. Among recent advancements, Kolmogorov-Arnold Networks (KANs) have emerged as a promising alternative to traditional Multi-Layer Perceptrons (MLPs). This study evaluates the impact of substituting MLPs with KANs within three established machine learning frameworks: Allegro, Neural Equivariant Interatomic Potentials (NequIP), and the Edge-Based Tensor Prediction Graph Neural Network (ETGNN). Our results demonstrate that the integration of KANs generally yields enhanced prediction accuracies. Specifically, replacing MLPs with KANs in the output blocks leads to notable improvements in accuracy and, in certain scenarios, also results in reduced training times. Furthermore, employing KANs exclusively in the output block facilitates faster inference and improved computational efficiency relative to utilizing KANs throughout the entire model. The selection of an optimal basis function for KANs is found to be contingent upon the particular problem at hand. Our results demonstrate the strong potential of KANs in enhancing machine learning potentials and material property predictions.

physics.comp-ph↗

arXiv2024

Advancing Nonadiabatic Molecular Dynamics Simulations for Solids: Achieving Supreme Accuracy and Efficiency with Machine Learning

Non-adiabatic molecular dynamics (NAMD) simulations have become an indispensable tool for investigating excited-state dynamics in solids. In this work, we propose a general framework, N$^2$AMD which employs an E(3)-equivariant deep neural Hamiltonian to boost the accuracy and efficiency of NAMD simulations. The preservation of Euclidean symmetry of Hamiltonian enables N$^2$AMD to achieve state-of-the-art performance. Distinct from conventional machine learning methods that predict key quantities in NAMD, N$^2$AMD computes these quantities directly with a deep neural Hamiltonian, ensuring supreme accuracy, efficiency, and consistency. Furthermore, N$^2$AMD demonstrates excellent generalizability and enables seamless integration with advanced NAMD techniques and infrastructures. Taking several extensively investigated semiconductors as the prototypical system, we successfully simulate carrier recombination in both pristine and defective systems at large scales where conventional NAMD often significantly underestimates or even qualitatively incorrectly predicts lifetimes. This framework not only boosts the efficiency and precision of NAMD simulations but also opens new avenues to advance materials research.

physics.comp-ph↗

arXiv2024

Identifying Direct Bandgap Silicon Structures with High-throughput Search and Machine Learning Methods

Utilizations of silicon-based luminescent devices are restricted by the indirect-gap nature of diamond silicon. In this study, the high-throughput method is employed to expedite discoveries of direct-gap silicon crystals. The machine learning (ML) potential is utilized to construct a dataset comprising 2637 silicon allotropes, which is subsequently screened using an ML Hamiltonian model and density functional theory calculations, resulting in identification of 47 direct-gap Si structures. We calculate transition dipole moments (TDM), energies, and phonon bandstructures of these structures to validate their performance. Additionally, we recalculate bandgaps of these structures employing the HSE06 functional. 22 silicon allotropes are identified as potential photovoltaic materials. Among them, the energy per atom of Si22-Pm, which has a direct bandgap of 1.27 eV, is 0.026 eV/atom higher than diamond silicon. Si18-C2/m, which has a direct bandgap of 0.796 eV, exhibits the highest TDM among identified structures. Si16-P21/c, which has a direct bandgap of 0.907 eV, has the mass density of 2.316 g/cm3, which is the highest among identified structures and higher than that of diamond silicon. The structure Si12-P1, which possesses a direct bandgap of 1.69 eV, exhibits the highest spectroscopic limited maximum efficiency (SLME) among identified structures at 32.28%, surpassing that of diamond silicon. This study offers insights into properties of silicon crystals while presenting a systematic high-throughput method for material discovery.

cond-mat.mtrl-sci↗

arXiv2024

Topological interfacial states in ferroelectric domain walls of two-dimensional bismuth

Using machine learning methods, we explore different types of domain walls in the recently unveiled single-element ferroelectric, the bismuth monolayer [Nature 617, 67 (2023)]. Remarkably, our investigation reveals that the charged domain wall configuration exhibits lower energy compared to the uncharged domain wall structure. We also demonstrate that the experimentally discovered tail-to-tail domain wall maintains topological interfacial states caused by the change in the Z_2 number between ferroelectric and paraelectric states. Interestingly, due to the intrinsic built-in electric fields in asymmetry DW configurations, we find that the energy of topological interfacial states splits, resulting in an accidental band crossing at the Fermi level. Our study suggests that domain walls in two-dimensional bismuth hold potential as a promising platform for the development of ferroelectric domain wall devices.

cond-mat.mtrl-sci↗

arXiv2024

ReflectSumm: A Benchmark for Course Reflection Summarization

This paper introduces ReflectSumm, a novel summarization dataset specifically designed for summarizing students' reflective writing. The goal of ReflectSumm is to facilitate developing and evaluating novel summarization techniques tailored to real-world scenarios with little training data, %practical tasks with potential implications in the opinion summarization domain in general and the educational domain in particular. The dataset encompasses a diverse range of summarization tasks and includes comprehensive metadata, enabling the exploration of various research questions and supporting different applications. To showcase its utility, we conducted extensive evaluations using multiple state-of-the-art baselines. The results provide benchmarks for facilitating further research in this area.

cs.CL↗

arXiv2024

Universal Machine Learning Kohn-Sham Hamiltonian for Materials

While density functional theory (DFT) serves as a prevalent computational approach in electronic structure calculations, its computational demands and scalability limitations persist. Recently, leveraging neural networks to parameterize the Kohn-Sham DFT Hamiltonian has emerged as a promising avenue for accelerating electronic structure computations. Despite advancements, challenges such as the necessity for computing extensive DFT training data to explore each new system and the complexity of establishing accurate ML models for multi-elemental materials still exist. Addressing these hurdles, this study introduces a universal electronic Hamiltonian model trained on Hamiltonian matrices obtained from first-principles DFT calculations of nearly all crystal structures on the Materials Project. We demonstrate its generality in predicting electronic structures across the whole periodic table, including complex multi-elemental systems, solid-state electrolytes, Moiré twisted bilayer heterostructure, and metal-organic frameworks (MOFs). Moreover, we utilize the universal model to conduct high-throughput calculations of electronic structures for crystals in GeNOME datasets, identifying 3,940 crystals with direct band gaps and 5,109 crystals with flat bands. By offering a reliable efficient framework for computing electronic properties, this universal Hamiltonian model lays the groundwork for advancements in diverse fields, such as easily providing a huge data set of electronic structures and also making the materials design across the whole periodic table possible.

physics.comp-ph↗

arXiv2024

General time-reversal equivariant neural network potential for magnetic materials

This study introduces time-reversal E(3)-equivariant neural network and SpinGNN++ framework for constructing a comprehensive interatomic potential for magnetic systems, encompassing spin-orbit coupling and noncollinear magnetic moments. SpinGNN++ integrates multitask spin equivariant neural network with explicit spin-lattice terms, including Heisenberg, Dzyaloshinskii-Moriya, Kitaev, single-ion anisotropy, and biquadratic interactions, and employs time-reversal equivariant neural network to learn high-order spin-lattice interactions using time-reversal E(3)-equivariant convolutions. To validate SpinGNN++, a complex magnetic model dataset is introduced as a benchmark and employed to demonstrate its capabilities. SpinGNN++ provides accurate descriptions of the complex spin-lattice coupling in monolayer CrI$_3$ and CrTe$_2$, achieving sub-meV errors. Importantly, it facilitates large-scale parallel spin-lattice dynamics, thereby enabling the exploration of associated properties, including the magnetic ground state and phase transition. Remarkably, SpinGNN++ identifies a new ferrimagnetic state as the ground magnetic state for monolayer CrTe2, thereby enriching its phase diagram and providing deeper insights into the distinct magnetic signals observed in various experiments.

cond-mat.mtrl-sci↗

arXiv2023

Image Classifier Based Generative Method for Planar Antenna Design

To extend the antenna design on printed circuit boards (PCBs) for more engineers of interest, we propose a simple method that models PCB antennas with a few basic components. By taking two separate steps to decide their geometric dimensions and positions, antenna prototypes can be facilitated with no experience required. Random sampling statistics relate to the quality of dimensions are used in selecting among dimension candidates. A novel image-based classifier using a convolutional neural network (CNN) is introduced to further determine the positions of these fixed-dimension components. Two examples from wearable products have been chosen to examine the entire workflow. Their final designs are realistic and their performance metrics are not inferior to the ones designed by experienced engineers.

cs.CV↗

arXiv2023

Overview of ImageArg-2023: The First Shared Task in Multimodal Argument Mining

This paper presents an overview of the ImageArg shared task, the first multimodal Argument Mining shared task co-located with the 10th Workshop on Argument Mining at EMNLP 2023. The shared task comprises two classification subtasks - (1) Subtask-A: Argument Stance Classification; (2) Subtask-B: Image Persuasiveness Classification. The former determines the stance of a tweet containing an image and a piece of text toward a controversial topic (e.g., gun control and abortion). The latter determines whether the image makes the tweet text more persuasive. The shared task received 31 submissions for Subtask-A and 21 submissions for Subtask-B from 9 different teams across 6 countries. The top submission in Subtask-A achieved an F1-score of 0.8647 while the best submission in Subtask-B achieved an F1-score of 0.5561.

cs.CL↗

arXiv2023

STRONG -- Structure Controllable Legal Opinion Summary Generation

We propose an approach for the structure controllable summarization of long legal opinions that considers the argument structure of the document. Our approach involves using predicted argument role information to guide the model in generating coherent summaries that follow a provided structure pattern. We demonstrate the effectiveness of our approach on a dataset of legal opinions and show that it outperforms several strong baselines with respect to ROUGE, BERTScore, and structure similarity.

cs.CL↗

arXiv2023

Transferable Machine Learning Approach for Predicting Electronic Structures of Charged Defects

The study of the electronic properties of charged defects is crucial for our understanding of various electrical properties of materials. However, the high computational cost of density functional theory (DFT) hinders the research on large defect models. In this study, we present an E(3) equivariant graph neural network framework (HamGNN-Q), which can predict the tight-binding Hamiltonian matrices for various defect types with different charges using only one set of network parameters. By incorporating features of background charge into the element representation, HamGNN-Q enables a direct mapping from structure and background charge to the electronic Hamiltonian matrix of charged defect systems without DFT calculation. We demonstrate the model's high precision and transferability through testing on GaAs systems with various charged defect configurations. Our approach provides a practical solution for accelerating charged defect electronic structure calculations and advancing the design of materials with tailored electronic properties.

physics.comp-ph↗