arXiv subjects

Xi Yu

Publications and source records attributed to Xi Yu.

At least 37 records · Page 2Linked to original sources

arXiv2025

Explanatory Summarization with Discourse-Driven Planning

Lay summaries for scientific documents typically include explanations to help readers grasp sophisticated concepts or arguments. However, current automatic summarization methods do not explicitly model explanations, which makes it difficult to align the proportion of explanatory content with human-written summaries. In this paper, we present a plan-based approach that leverages discourse frameworks to organize summary generation and guide explanatory sentences by prompting responses to the plan. Specifically, we propose two discourse-driven planning strategies, where the plan is conditioned as part of the input or part of the output prefix, respectively. Empirical experiments on three lay summarization datasets show that our approach outperforms existing state-of-the-art methods in terms of summary quality, and it enhances model robustness, controllability, and mitigates hallucination.

cs.CL↗

arXiv2025

What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific Presentations

Transforming recorded videos into concise and accurate textual summaries is a growing challenge in multimodal learning. This paper introduces VISTA, a dataset specifically designed for video-to-text summarization in scientific domains. VISTA contains 18,599 recorded AI conference presentations paired with their corresponding paper abstracts. We benchmark the performance of state-of-the-art large models and apply a plan-based framework to better capture the structured nature of abstracts. Both human and automated evaluations confirm that explicit planning enhances summary quality and factual consistency. However, a considerable gap remains between models and human performance, highlighting the challenges of our dataset. This study aims to pave the way for future research on scientific video-to-text summarization.

cs.CL↗

arXiv2025

Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction

Multi-task semantic communication can serve multiple learning tasks using a shared encoder model. Existing models have overlooked the intricate relationships between features extracted during an encoding process of tasks. This paper presents a new graph attention inter-block (GAI) module to the encoder/transmitter of a multi-task semantic communication system, which enriches the features for multiple tasks by embedding the intermediate outputs of encoding in the features, compared to the existing techniques. The key idea is that we interpret the outputs of the intermediate feature extraction blocks of the encoder as the nodes of a graph to capture the correlations of the intermediate features. Another important aspect is that we refine the node representation using a graph attention mechanism to extract the correlations and a multi-layer perceptron network to associate the node representations with different tasks. Consequently, the intermediate features are weighted and embedded into the features transmitted for executing multiple tasks at the receiver. Experiments demonstrate that the proposed model surpasses the most competitive and publicly available models by 11.4% on the CityScapes 2Task dataset and outperforms the established state-of-the-art by 3.97% on the NYU V2 3Task dataset, respectively, when the bandwidth ratio of the communication channel (i.e., compression level for transmission over the channel) is as constrained as 1 12 .

cs.LG↗

arXiv2024

Empirical Measurements of AI Training Power Demand on a GPU-Accelerated Node

The expansion of artificial intelligence (AI) applications has driven substantial investment in computational infrastructure, especially by cloud computing providers. Quantifying the energy footprint of this infrastructure requires models parameterized by the power demand of AI hardware during training. We empirically measured the instantaneous power draw of an 8-GPU NVIDIA H100 HGX node during the training of open-source image classifier (ResNet) and large-language models (Llama2-13b). The maximum observed power draw was approximately 8.4 kW, 18% lower than the manufacturer-rated 10.2 kW, even with GPUs near full utilization. Holding model architecture constant, increasing batch size from 512 to 4096 images for ResNet reduced total training energy consumption by a factor of 4. These findings can inform capacity planning for data center operators and energy use estimates by researchers. Future work will investigate the impact of cooling technology and carbon-aware scheduling on AI workload energy consumption.

cs.AR↗

arXiv2024

A Three-Tiered Hierarchical Computational Framework Bridging Molecular Systems and Junction-Level Charge Transport

The Non-Equilibrium Green's Function (NEGF) method combined with ab initio calculations has been widely used to study charge transport in molecular junctions. However, the significant computational demands of high-resolution calculations for all device components pose challenges in simulating junctions with complex molecular structures and understanding the functionality of molecular devices. In this study, we developed a series of approximation methods capable of effectively handling the molecular Hamiltonian, electrode self-energy, and their interfacial coupling at different levels of approximation. These methods, as three-tiered hierarchical levels, enable efficient charge transport computations ranging from individual molecules to complete junction systems, achieving an optimal balance between computational cost and accuracy, and are able to addresses specific research objectives by isolating and analyzing the dominant factors governing charge transport. Integrated into a Question-Driven Hierarchical Computation (QDHC) framework, we show this three-tiered framework significantly enhances the efficiency of analyzing charge transport mechanisms, as validated through a series of benchmark studies on diverse molecular junction systems, demonstrating its capability to accurately and efficiently elucidate charge transport mechanisms in complex molecular devices.

physics.comp-ph↗

arXiv2024

Certifying the quantumness of a nuclear spin qudit through its uniform precession

Spin precession is a textbook example of dynamics of a quantum system that exactly mimics its classical counterpart. Here we challenge this view by certifying the quantumness of exotic states of a nuclear spin through its uniform precession. The key to this result is measuring the positivity, instead of the expectation value, of the $x$-projection of the precessing spin, and using a spin > 1/2 qudit, that is not restricted to semi-classical spin coherent states. The experiment is performed on a single spin-7/2 $^{123}$Sb nucleus, implanted in a silicon nanoelectronic device, amenable to high-fidelity preparation, control, and projective single-shot readout. Using Schr\"odinger cat states and other bespoke states of the nucleus, we violate the classical bound by 19 standard deviations, proving that no classical probability distribution can explain the statistic of this spin precession, and highlighting our ability to prepare quantum resource states with high fidelity in a single atomic-scale qudit.

quant-ph↗

arXiv2024

Schr\"odinger cat states of a nuclear spin qudit in silicon

High-dimensional quantum systems are a valuable resource for quantum information processing. They can be used to encode error-correctable logical qubits, which has been demonstrated using continuous-variable states in microwave cavities or the motional modes of trapped ions. For example, high-dimensional systems can be used to realise `Schr\"{o}dinger cat' states, superpositions of widely displaced coherent states that can also be used to illustrate quantum effects at large scales. Recent proposals have suggested encoding qubits in high-spin atomic nuclei, finite-dimensional systems that can host hardware-efficient versions of continuous-variable codes. Here we demonstrate the creation and manipulation of Schrodinger cat states using the spin-7/2 nucleus of an antimony atom embedded in a silicon nanoelectronic device. We use a multi-frequency control scheme to produce spin rotations that preserve the symmetry of the qudit, and constitute logical Pauli operations for qubits encoded in the Schrodinger cat states. Our work demonstrates the ability to prepare and control nonclassical resource states, a prerequisite for applications in quantum information processing and quantum error correction using our scalable, manufacturable semiconductor platform.

quant-ph↗

arXiv2024

Cauchy-Schwarz Divergence Information Bottleneck for Regression

The information bottleneck (IB) approach is popular to improve the generalization, robustness and explainability of deep neural networks. Essentially, it aims to find a minimum sufficient representation $\mathbf{t}$ by striking a trade-off between a compression term $I(\mathbf{x};\mathbf{t})$ and a prediction term $I(y;\mathbf{t})$, where $I(\cdot;\cdot)$ refers to the mutual information (MI). MI is for the IB for the most part expressed in terms of the Kullback-Leibler (KL) divergence, which in the regression case corresponds to prediction based on mean squared error (MSE) loss with Gaussian assumption and compression approximated by variational inference. In this paper, we study the IB principle for the regression problem and develop a new way to parameterize the IB with deep neural networks by exploiting favorable properties of the Cauchy-Schwarz (CS) divergence. By doing so, we move away from MSE-based regression and ease estimation by avoiding variational approximations or distributional assumptions. We investigate the improved generalization ability of our proposed CS-IB and demonstrate strong adversarial robustness guarantees. We demonstrate its superior performance on six real-world regression tasks over other popular deep IB approaches. We additionally observe that the solutions discovered by CS-IB always achieve the best trade-off between prediction accuracy and compression ratio in the information plane. The code is available at \url{https://github.com/SJYuCNEL/Cauchy-Schwarz-Information-Bottleneck}.

cs.LG↗

arXiv2024

Adversarial Reweighting with $α$-Power Maximization for Domain Adaptation

The practical Domain Adaptation (DA) tasks, e.g., Partial DA (PDA), open-set DA, universal DA, and test-time adaptation, have gained increasing attention in the machine learning community. In this paper, we propose a novel approach, dubbed Adversarial Reweighting with $α$-Power Maximization (ARPM), for PDA where the source domain contains private classes absent in target domain. In ARPM, we propose a novel adversarial reweighting model that adversarially learns to reweight source domain data to identify source-private class samples by assigning smaller weights to them, for mitigating potential negative transfer. Based on the adversarial reweighting, we train the transferable recognition model on the reweighted source distribution to be able to classify common class data. To reduce the prediction uncertainty of the recognition model on the target domain for PDA, we present an $α$-power maximization mechanism in ARPM, which enriches the family of losses for reducing the prediction uncertainty for PDA. Extensive experimental results on five PDA benchmarks, i.e., Office-31, Office-Home, VisDA-2017, ImageNet-Caltech, and DomainNet, show that our method is superior to recent PDA methods. Ablation studies also confirm the effectiveness of components in our approach. To theoretically analyze our method, we deduce an upper bound of target domain expected error for PDA, which is approximately minimized in our approach. We further extend ARPM to open-set DA, universal DA, and test time adaptation, and verify the usefulness through experiments.

cs.CV↗

arXiv2024

Farthest Point Sampling in Property Designated Chemical Feature Space as a General Strategy for Enhancing the Machine Learning Model Performance for Small Scale Chemical Dataset

Machine learning model development in chemistry and materials science often grapples with the challenge of small scale, unbalanced labelled datasets, a common limitation in scientific experiments. These dataset imbalances can precipitate overfit ting and diminish model generalization. Our study explores the efficacy of the farthest point sampling (FPS) strategy within target ed chemical feature spaces, demonstrating its capacity to generate well-distributed training datasets and consequently enhance model performance. We rigorously evaluated this strategy across various machine learning models, including artificial neural net works (ANN), support vector machines (SVM), and random forests (RF), using datasets encapsulating physicochemical properties like standard boiling points and enthalpy of vaporization. Our findings reveal that FPS-based models consistently surpass those trained via random sampling, exhibiting superior predictive accuracy and robustness, alongside a marked reduction in overfitting. This improvement is particularly pronounced in smaller training datasets, attributable to increased diversity within the training data's chemical feature space. Consequently, FPS emerges as a universally effective and adaptable approach in approaching high performance machine learning models by small and biased experimental datasets prevalent in chemistry and materials science.

physics.chem-ph↗

arXiv2024

Robust Macroscopic Schrödinger's Cat on a Nucleus

We propose a scheme to generate spin cat states, i.e., superpositions of maximally separated quasiclassical states on a single high-dimensional nuclear spin in a solid-state device. We exploit a strong quadrupolar nonlinearity to drive the nucleus significantly faster than usual gate sequences, achieving collapses and revivals two orders of magnitude faster than the dephasing timescale. Furthermore, these states are engineered without entanglement with an ancilla, hence, are robust against error propagation. With our multitone control, we can realize arbitrary high-spin rotations within an experimentally feasible regime, as well as transform a spin coherent state to a spin cat state using only phase modulation, opening the possibility of storing and manipulating high-fidelity cat states.

quant-ph↗

arXiv2023

Exploring Non-Steady-State Charge Transport Dynamics in Information Processing: Insights from Reservoir Computing

Exploring nonlinear chemical dynamic systems for information processing has emerged as a frontier in chemical and computational research, seeking to replicate the brain's neuromorphic and dynamic functionalities. We have extensively explored the information processing capabilities of a nonlinear chemical dynamic system through theoretical modeling by integrating a non-steady-state proton-coupled charge transport system into reservoir computing (RC) architecture. Our system demonstrated remarkable success in tasks such as waveform recognition, voice identification and chaos system prediction. More importantly, through a quantitative study, we revealed the key role of the alignment between the signal processing frequency of the RC and the characteristic time of the dynamics of the nonlinear system, which dictates the efficiency of RC task execution, the reservoir states and the memory capacity in information processing. The system's information processing frequency range was further modulated by the characteristic time of the dynamic system, resulting in an implementation akin to a 'chemically-tuned band-pass filter' for selective frequency processing. Our study thus elucidates the fundamental requirements and dynamic underpinnings of the non-steady-state charge transport dynamic system for RC, laying a foundational groundwork for the application of dynamic molecular devices for in-materia computing.

physics.chem-ph↗

arXiv2023

Where to Deploy an Airborne Relay in Unknown Environments: Feasible Locations for Throughput and LoS Enhancement

The deployment of heterogeneous teams of both air and ground mobile assets combines the advantages of mobility, sensing capability, and operational duration when performing complex tasks. Air assets in such teams act to relay information between ground assets but must maintain unblocked paths to enable high-capacity communication modes. Obstacles in the operational environment may block the line of sight (LoS) between air assets and ground assets depending on their locations and heights. In this paper, we analyze the probability of spanning a two-hop communication between a pair of ground assets deployed in an environment with obstacles at random locations and with random heights (i.e. a Poisson Forest) using an air asset at any location near the ground assets. We provide a closed-form expression of the LoS probability based on the 3-dimensional locations of the air asset. We then compute a 3-D manifold of the air asset locations that satisfy a given LoS probability constraint. We further consider throughput as a measure of communication quality, and use it as an optimization objective.

cs.MA↗

arXiv2023

INSURE: An Information Theory Inspired Disentanglement and Purification Model for Domain Generalization

Domain Generalization (DG) aims to learn a generalizable model on the unseen target domain by only training on the multiple observed source domains. Although a variety of DG methods have focused on extracting domain-invariant features, the domain-specific class-relevant features have attracted attention and been argued to benefit generalization to the unseen target domain. To take into account the class-relevant domain-specific information, in this paper we propose an Information theory iNspired diSentanglement and pURification modEl (INSURE) to explicitly disentangle the latent features to obtain sufficient and compact (necessary) class-relevant feature for generalization to the unseen domain. Specifically, we first propose an information theory inspired loss function to ensure the disentangled class-relevant features contain sufficient class label information and the other disentangled auxiliary feature has sufficient domain information. We further propose a paired purification loss function to let the auxiliary feature discard all the class-relevant information and thus the class-relevant feature will contain sufficient and compact (necessary) class-relevant information. Moreover, instead of using multiple encoders, we propose to use a learnable binary mask as our disentangler to make the disentanglement more efficient and make the disentangled features complementary to each other. We conduct extensive experiments on four widely used DG benchmark datasets including PACS, OfficeHome, TerraIncognita, and DomainNet. The proposed INSURE outperforms the state-of-art methods. We also empirically show that domain-specific class-relevant features are beneficial for domain generalization.

cs.CV↗

arXiv2023

Improved placement precision of implanted donor spin qubits in silicon using molecule ions

Donor spins in silicon-28 ($^{28}$Si) are among the most performant qubits in the solid state, offering record coherence times and gate fidelities above 99%. Donor spin qubits can be fabricated using the semiconductor-industry compatible method of deterministic ion implantation. Here we show that the precision of this fabrication method can be boosted by implanting molecule ions instead of single atoms. The bystander ions, co-implanted with the dopant of interest, carry additional kinetic energy and thus increase the detection confidence of deterministic donor implantation employing single ion detectors to signal the induced electron-hole pairs. This allows the placement uncertainty of donor qubits to be minimised without compromising on detection confidence. We investigate the suitability of phosphorus difluoride (PF$_2^+$) molecule ions to produce high quality P donor qubits. Since $^{19}$F nuclei have a spin of $I = 1/2$, it is imperative to ensure that they do not hyperfine couple to P donor electrons as they would cause decoherence by adding magnetic noise. Using secondary ion mass spectrometry, we confirm that F diffuses away from the active region of qubit devices while the P donors remain close to their original location during a donor activation anneal. PF$_2$-implanted qubit devices were then fabricated and electron spin resonance (ESR) measurements were performed on the P donor electron. A pure dephasing time of $T_2^* = 20.5 \pm 0.5$ $\mu$s and a coherence time of $T_2^{Hahn} = 424 \pm 5$ $\mu$s were extracted for the P donor electron-values comparable to those found in previous P-implanted qubit devices. Closer investigation of the P donor ESR spectrum revealed that no $^{19}$F nuclear spins were found in the vicinity of the P donor. Molecule ions therefore show great promise for producing high-precision deterministically-implanted arrays of long-lived donor spin qubits.

cond-mat.mes-hall↗

arXiv2022

Receding Horizon Control on the Broadcast of Information in Stochastic Networks

This paper focuses on the broadcast of information on robot networks with stochastic network interconnection topologies. Problematic communication networks are almost unavoidable in areas where we wish to deploy multi-robotic systems, usually due to a lack of environmental consistency, accessibility, and structure. We tackle this problem by modeling the broadcast of information in a multi-robot communication network as a stochastic process with random arrival times, which can be produced by irregular robot movements, wireless attenuation, and other environmental factors. Using this model, we provide and analyze a receding horizon control strategy to control the statistics of the information broadcast. The resulting strategy compels the robots to re-direct their communication resources to different neighbors according to the current propagation process to fulfill global broadcast requirements. Based on this method, we provide an approach to compute the expected time to broadcast the message to all nodes. Numerical examples are provided to illustrate the results.

cs.RO↗

arXiv2022

Air-Aided Communication Between Ground Assets in a Poisson Forest

Ground assets deployed in a cluttered environment with randomized obstacles (e.g., a forest) may experience line of sight (LoS) obstruction due to those obstacles. Air assets can be deployed in the vicinity to aid the communication by establishing two-hop paths between the ground assets. Obstacles that are taller than a position-dependent critical height may still obstruct the LoS between a ground asset and an air asset. In this paper, we provide an analytical framework for computing the probability of obtaining a LoS path in a Poisson forest. Given the locations and heights of a ground asset and an air asset, we establish the critical height, which is a function of distance. To account for this dependence on distance, the blocking is modeled as an inhomogenous Poisson point process, and the LoS probability is its void probability. Examples and closed-form expressions are provided for two obstruction height distributions: uniform and truncated Gaussian. The examples are validated through simulation. Additionally, the end-to-end throughput is determined and shown to be a metric that balances communication distance with the impact of LoS blockage. Throughput is used to determine the range at which it is better to relay communications through the air asset, and, when the air asset is deployed, its optimal height.

cs.RO↗

arXiv2022

Flow-Based Control of Marine Robots in Gyre-Like Environments

We present a flow-based control strategy that enables resource-constrained marine robots to patrol gyre-like flow environments on an orbital trajectory with a periodicity in a given range. The controller does not require a detailed model of the flow field and relies only on the robot's location relative to the center of the gyre. Instead of precisely tracking a pre-defined trajectory, the robots are tasked to stay in between two bounding trajectories with known periodicity. Furthermore, the proposed strategy leverages the surrounding flow field to minimize control effort. We prove that the proposed strategy enables robots to cycle in the flow satisfying the desired periodicity requirements. Our method is tested and validated both in simulation and in experiments using a low-cost, underactuated, surface swimming robot, i.e. the Modboat.

cs.RO↗