arXiv subjects

Xuan Zhang

Publications and source records attributed to Xuan Zhang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Towards Structure-aware Model for Multi-modal Knowledge Graph Completion

Knowledge graphs (KGs) play a key role in promoting various multimedia and AI applications. However, with the explosive growth of multi-modal information, traditional knowledge graph completion (KGC) models cannot be directly applied. This has attracted a large number of researchers to study multi-modal knowledge graph completion (MMKGC). Since MMKG extends KG to the visual and textual domains, MMKGC faces two main challenges: (1) how to deal with the fine-grained modality information interaction and awareness; (2) how to ensure the dominant role of graph structure in multi-modal knowledge fusion and deal with the noise generated by other modalities during modality fusion. To address these challenges, this paper proposes a novel MMKGC model named TSAM, which integrates fine-grained modality interaction and dominant graph structure to form a high-performance MMKGC framework. Specifically, to solve the challenges, TSAM proposes the Fine-grained Modality Awareness Fusion method (FgMAF), which uses pre-trained language models to better capture fine-grained semantic information interaction of different modalities and employs an attention mechanism to achieve fine-grained modality awareness and fusion. Additionally, TSAM presents the Structure-aware Contrastive Learning method (SaCL), which utilizes two contrastive learning approaches to align other modalities more closely with the structured modality. Extensive experiments show that the proposed TSAM model significantly outperforms existing MMKGC models on widely used multi-modal datasets.

cs.MM↗

arXiv2025

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images. However, their iterative denoising process results in significant computational overhead during inference, limiting their practical deployment in resource-constrained environments. Existing acceleration methods often adopt uniform strategies that fail to capture the temporal variations during diffusion generation, while the commonly adopted sequential pruning-then-fine-tuning strategy suffers from sub-optimality due to the misalignment between pruning decisions made on pretrained weights and the model's final parameters. To address these limitations, we introduce ALTER: All-in-One Layer Pruning and Temporal Expert Routing, a unified framework that transforms diffusion models into a mixture of efficient temporal experts. ALTER achieves a single-stage optimization that unifies layer pruning, expert routing, and model fine-tuning by employing a trainable hypernetwork, which dynamically generates layer pruning decisions and manages timestep routing to specialized, pruned expert sub-networks throughout the ongoing fine-tuning of the UNet. This unified co-optimization strategy enables significant efficiency gains while preserving high generative quality. Specifically, ALTER achieves same-level visual fidelity to the original 50-step Stable Diffusion v2.1 model while utilizing only 25.9% of its total MACs with just 20 inference steps and delivering a 3.64x speedup through 35% sparsity.

cs.CV↗

arXiv2025

A Survey of Real-time Scheduling on Accelerator-based Heterogeneous Architecture for Time Critical Applications

Accelerator-based heterogeneous architectures, such as CPU-GPU, CPU-TPU, and CPU-FPGA systems, are widely adopted to support the popular artificial intelligence (AI) algorithms that demand intensive computation. When deployed in real-time applications, such as robotics and autonomous vehicles, these architectures must meet stringent timing constraints. To summarize these achievements, this article presents a comprehensive survey of real-time scheduling techniques for accelerator-based heterogeneous platforms. It highlights key advancements from the past ten years, showcasing how proposed solutions have evolved to address the distinct challenges and requirements of these systems. This survey begins with an overview of the hardware characteristics and common task execution models used in accelerator-based heterogeneous systems. It then categorizes the reviewed works based on soft and hard deadline constraints. For soft real-time approaches, we cover real-time scheduling methods supported by hardware vendors and strategies focusing on timing-critical scheduling, energy efficiency, and thermal-aware scheduling. For hard real-time approaches, we first examine support from processor vendors. We then discuss scheduling techniques that guarantee hard deadlines (with strict response time analysis). After reviewing general soft and hard real-time scheduling methods, we explore application- or scenario-driven real-time scheduling techniques for accelerator-enabled heterogeneous computing platforms. Finally, the article concludes with a discussion of open issues and challenges within this research area.

cs.DC↗

arXiv2025

SN 2021hpr: A Normal Type Ia Supernova Showing Excess Emission in the Early Rising Phase

We present extensive optical observations of a nearby Type Ia supernova (SN Ia), SN 2021hpr, located in the spiral galaxy NGC 3147 at a distance of $\sim$ 45 Mpc. Our observations cover a phase within $\sim 1-2$ days to $\sim 290$ days after the explosion. SN 2021hpr is found to be a spectroscopically normal SN Ia, with an absolute B-band peak magnitude of $M_{max}(B) \approx -19.16 \pm 0.14$ mag and a post-peak decline rate of $Δm_{15}(B)= 1.00 \pm 0.01 $ mag. Early-time light curves showed a $\sim 7.0 \%$ excess emission compared to a homogeneously expanding fireball model, likely due to SN ejecta interacting with a companion or immediate circumstellar matter. The optical spectra of SN 2021hpr are overall similar to those of normal SNe Ia, but characterized by prominent detached high-velocity features (HVFs) of Si {\sc ii} and Ca {\sc ii} in the early phase. After examining a small sample of well-observed normal SNe Ia, we find that the HVFs are likely common for the subgroup with early-excess emission. The association of early bump feature with the HVFs could be attributed to density or abundance enhancement at the outer layer of the exploding star, likely as a result of interactions with companion$/$CSM or experiencing more complete burning. Nevertheless, the redshifted Fe {\sc ii} and Ni {\sc ii} lines in the nebular-phase spectra of SN 2021hpr, contrary to the blueshift trend seen in other SNe Ia showing early bump features, indicate its peculiarity in the explosion that remains to be understood.

astro-ph.HE↗

arXiv2025

FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding

Recent advancements in video understanding within visual large language models (VLLMs) have led to notable progress. However, the complexity of video data and contextual processing limitations still hinder long-video comprehension. A common approach is video feature compression to reduce token input to large language models, yet many methods either fail to prioritize essential features, leading to redundant inter-frame information, or introduce computationally expensive modules.To address these issues, we propose FiLA(Fine-grained Vision Language Model)-Video, a novel framework that leverages a lightweight dynamic-weight multi-frame fusion strategy, which adaptively integrates multiple frames into a single representation while preserving key video information and reducing computational costs. To enhance frame selection for fusion, we introduce a keyframe selection strategy, effectively identifying informative frames from a larger pool for improved summarization. Additionally, we present a simple yet effective long-video training data generation strategy, boosting model performance without extensive manual annotation. Experimental results demonstrate that FiLA-Video achieves superior efficiency and accuracy in long-video comprehension compared to existing methods.

cs.CV↗

arXiv2025

FPGA-Optimized Hardware Accelerator for Fast Fourier Transform and Singular Value Decomposition in AI

This research introduces an FPGA-based hardware accelerator to optimize the Singular Value Decomposition (SVD) and Fast Fourier transform (FFT) operations in AI models. The proposed design aims to improve processing speed and reduce computational latency. Through experiments, we validate the performance benefits of the hardware accelerator and show how well it handles FFT and SVD operations. With its strong security and durability, the accelerator design achieves significant speedups over software implementations, thanks to its modules for data flow control, watermark embedding, FFT, and SVD.

cs.AR↗

arXiv2025

Graph-based Diffusion Model for Collaborative Filtering

Recently, diffusion-based recommendation methods have achieved impressive results. However, existing approaches predominantly treat each user's historical interactions as independent training samples, overlooking the potential of higher-order collaborative signals between users and items. Such signals, which encapsulate richer and more nuanced relationships, can be naturally captured using graph-based data structures. To address this limitation, we extend diffusion-based recommendation methods to the graph domain by directly modeling user-item bipartite graphs with diffusion models. This enables better modeling of the higher-order connectivity inherent in complex interaction dynamics. However, this extension introduces two primary challenges: (1) Noise Heterogeneity, where interactions are influenced by various forms of continuous and discrete noise, and (2) Relation Explosion, referring to the high computational costs of processing large-scale graphs. To tackle these challenges, we propose a Graph-based Diffusion Model for Collaborative Filtering (GDMCF). To address noise heterogeneity, we introduce a multi-level noise corruption mechanism that integrates both continuous and discrete noise, effectively simulating real-world interaction complexities. To mitigate relation explosion, we design a user-active guided diffusion process that selectively focuses on the most meaningful edges and active users, reducing inference costs while preserving the graph's topological integrity. Extensive experiments on three benchmark datasets demonstrate that GDMCF consistently outperforms state-of-the-art methods, highlighting its effectiveness in capturing higher-order collaborative signals and improving recommendation performance.

cs.SI↗

arXiv2025

SnapPix: Efficient-Coding--Inspired In-Sensor Compression for Edge Vision

Energy-efficient image acquisition on the edge is crucial for enabling remote sensing applications where the sensor node has weak compute capabilities and must transmit data to a remote server/cloud for processing. To reduce the edge energy consumption, this paper proposes a sensor-algorithm co-designed system called SnapPix, which compresses raw pixels in the analog domain inside the sensor. We use coded exposure (CE) as the in-sensor compression strategy as it offers the flexibility to sample, i.e., selectively expose pixels, both spatially and temporally. SNAPPIX has three contributions. First, we propose a task-agnostic strategy to learn the sampling/exposure pattern based on the classic theory of efficient coding. Second, we co-design the downstream vision model with the exposure pattern to address the pixel-level non-uniformity unique to CE-compressed images. Finally, we propose lightweight augmentations to the image sensor hardware to support our in-sensor CE compression. Evaluating on action recognition and video reconstruction, SnapPix outperforms state-of-the-art video-based methods at the same speed while reducing the energy by up to 15.4x. We have open-sourced the code at: https://github.com/horizon-research/SnapPix.

cs.CV↗

arXiv2025

3D-TAFS: A Training-free Framework for 3D Affordance Segmentation

Translating high-level linguistic instructions into precise robotic actions in the physical world remains challenging, particularly when considering the feasibility of interacting with 3D objects. In this paper, we introduce 3D-TAFS, a novel training-free multimodal framework for 3D affordance segmentation. To facilitate a comprehensive evaluation of such frameworks, we present IndoorAfford-Bench, a large-scale benchmark containing 9,248 images spanning 20 diverse indoor scenes across 6 areas, supporting standardized interaction queries. In particular, our framework integrates a large multimodal model with a specialized 3D vision network, enabling a seamless fusion of 2D and 3D visual understanding with language comprehension. Extensive experiments on IndoorAfford-Bench validate the proposed 3D-TAFS's capability in handling interactive 3D affordance segmentation tasks across diverse settings, showcasing competitive performance across various metrics. Our results highlight 3D-TAFS's potential for enhancing human-robot interaction based on affordance understanding in complex indoor environments, advancing the development of more intuitive and efficient robotic frameworks for real-world applications.

cs.RO↗

arXiv2025

AnalogGenie: A Generative Engine for Automatic Discovery of Analog Circuit Topologies

The massive and large-scale design of foundational semiconductor integrated circuits (ICs) is crucial to sustaining the advancement of many emerging and future technologies, such as generative AI, 5G/6G, and quantum computing. Excitingly, recent studies have shown the great capabilities of foundational models in expediting the design of digital ICs. Yet, applying generative AI techniques to accelerate the design of analog ICs remains a significant challenge due to critical domain-specific issues, such as the lack of a comprehensive dataset and effective representation methods for analog circuits. This paper proposes, $\textbf{AnalogGenie}$, a $\underline{\textbf{Gen}}$erat$\underline{\textbf{i}}$ve $\underline{\textbf{e}}$ngine for automatic design/discovery of $\underline{\textbf{Analog}}$ circuit topologies--the most challenging and creative task in the conventional manual design flow of analog ICs. AnalogGenie addresses two key gaps in the field: building a foundational comprehensive dataset of analog circuit topology and developing a scalable sequence-based graph representation universal to analog circuits. Experimental results show the remarkable generation performance of AnalogGenie in broadening the variety of analog ICs, increasing the number of devices within a single design, and discovering unseen circuit topologies far beyond any prior arts. Our work paves the way to transform the longstanding time-consuming manual design flow of analog ICs to an automatic and massive manner powered by generative AI. Our source code is available at https://github.com/xz-group/AnalogGenie.

cs.LG↗

arXiv2025

Uniform distribution mod $1$ for sequences of ergodic sums and continued fractions

We establish a coboundary condition for a sequence of ergodic sums (i.e.~Birkhoff partial sums) to be almost surely uniformly distributed mod $1$. Applications are given when the sequence is generated by a Gibbs-Markov map. In particular, we show that for almost every real number, the sequence of denominators of the convergents of its continued fraction expansion satisfies Benford's law.

math.DS↗

arXiv2025

PulseBat: A field-accessible dataset for second-life battery diagnostics from realistic histories using multidimensional rapid pulse test

As electric vehicles (EVs) approach the end of their operational life, their batteries retain significant economic value and present promising opportunities for second-life use and material recycling. This is particularly compelling for Global South and other underdeveloped regions, where reliable energy storage is vital to addressing critical challenges posed by weak and even nonexistent power grid and energy infrastructures. However, despite this potential, widespread adoption has been hindered by critical uncertainties surrounding the technical performance, safety, and recertification of second-life batteries. In cases where they have been redeployed, mismatches between estimated and actual performance often render batteries technically unsuitable or hazardous, turning them into liabilities for communities they were intended to benefit. This considerable misalignment exacerbates energy access disparities and undermines the broader vision of energy justice, highlighting an urgent need for robust and scalable solutions to unlock the potential. In the PulseBat Dataset, the authors tested 464 retired lithium-ion batteries, covering 3 cathode material types, 6 historical usages, 3 physical formats, and 6 capacity designs. The pulse test experiments were performed repeatedly for each second-life battery with 10 pulse width, 10 pulse magnitude, multiple state-of-charge, and state-of-health conditions, e.g., from 0.37 to 1.03. The PulseBat Dataset recorded these test conditions and the voltage response as well as the temperature signals that were subject to the injected pulse current, which could be used as a valuable data resource for critical diagnostics tasks such as state-of-charge estimation, state-of-health estimation, cathode material type identification, open-circuit voltage reconstruction, thermal management, and beyond.

cs.AI↗

arXiv2025

AGDA+: Proximal Alternating Gradient Descent Ascent Method with a Nonmonotone Adaptive Step-Size Search for Nonconvex Minimax Problems

We consider double-regularized nonconvex-strongly concave (NCSC) minimax problems of the form $(P):\min_{x\in\mathcal{X}} \max_{y\in\mathcal{Y}}g(x)+f(x,y)-h(y)$, where $g$, $h$ are closed convex, $f$ is $L$-smooth in $(x,y)$ and strongly concave in $y$. We propose a proximal alternating gradient descent ascent method AGDA+ that can adaptively choose nonmonotone primal-dual stepsizes to compute an approximate stationary point for $(P)$ without requiring the knowledge of the global Lipschitz constant $L$ and the concavity modulus $μ$. Using a nonmonotone step-size search (backtracking) scheme, AGDA+ stands out by its ability to exploit the local Lipschitz structure and eliminates the need for precise tuning of hyper-parameters. AGDA+ achieves the optimal iteration complexity of $\mathcal{O}(ε^{-2})$ and it is the first step-size search method for NCSC minimax problems that require only $3$ calls to $\nabla f$ on average per backtracking iteration. The numerical experiments demonstrate its robustness and efficiency.

math.OC↗

arXiv2025

Characterization and Optimization of Tunable Couplers via Adiabatic Control in Superconducting Circuits

In the pursuit of scalable superconducting quantum computing, tunable couplers have emerged as a pivotal component, offering the flexibility required for complex quantum operations of high performance. In most current architectures of superconducting quantum chips, such couplers are not equipped with dedicated readout circuits to reduce complexity in both design and operation. However, this strategy poses challenges in precise characterization, calibration, and control of the couplers. In this work, we develop a hardware-efficient and robust technique based on adiabatic control to address the above issue. The critical ingredient of this technique is adiabatic swap (aSWAP) operation between a tunable coupler and nearby qubits. Using this technique, we have characterized and calibrated tunable couplers in our chips and achieved straightforward and precise control over these couplers. For example, we have demonstrated the calibration and correction of the flux distortion of couplers. In addition, we have also expanded this technique to tune the dispersive shift between a frequency-fixed qubit and its readout resonator over a wide range.

quant-ph↗

arXiv2025

PICE: A Semantic-Driven Progressive Inference System for LLM Serving in Cloud-Edge Networks

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, including decreased response quality from SLMs, a tradeoff between the brevity and comprehensiveness of sketches, as well as increased latency caused by network transmission and edge inference. In this work, we propose and implement PICE, an LLM serving system with semantic-level cloud-edge collaboration, enhancing inference throughput and quality through dynamic inference task scheduling, ensemble learning, and parallel edge inference. Extensive testbed experiments illustrate that our approach achieves $1.5-2\times$ throughput enhancement and up to 43% latency reduction, while also potentially enhancing the quality compared to SOTA systems.

cs.DC↗

arXiv2024

A Geometry-Aware Message Passing Neural Network for Modeling Aerodynamics over Airfoils

Computational modeling of aerodynamics is a key problem in aerospace engineering, often involving flows interacting with solid objects such as airfoils. Deep surrogate models have emerged as purely data-driven approaches that learn direct mappings from simulation conditions to solutions based on either simulation or experimental data. Here, we consider modeling of incompressible flows over solid objects, wherein geometric structures are a key factor in determining aerodynamics. To effectively incorporate geometries, we propose a message passing scheme that efficiently and expressively integrates the airfoil shape with the mesh representation. Under this framework, we first obtain a representation of the geometry in the form of a latent graph on the airfoil surface. We subsequently propagate this representation to all collocation points through message passing on a directed, bipartite graph. We demonstrate that this framework supports efficient training by downsampling the solution mesh while avoiding distribution shifts at test time when evaluated on the full mesh. To enable our model to be able to distinguish between distinct spatial regimes of dynamics relative to the airfoil, we represent mesh points in both a leading edge and trailing edge coordinate system. We further enhance the expressiveness of our coordinate system representations by embedding our hybrid Polar-Cartesian coordinates using sinusoidal and spherical harmonics bases. We additionally find that a change of basis to canonicalize input representations with respect to inlet velocity substantially improves generalization. Altogether, these design choices lead to a purely data-driven machine learning framework known as GeoMPNN, which won the Best Student Submission award at the NeurIPS 2024 ML4CFD Competition, placing 4th overall. Our code is publicly available as part of the AIRS library (https://github.com/divelab/AIRS).

cs.LG↗

arXiv2024

Optical turbulence in the atmospheric surface layer at the Pamir Plateau Muztagh-ata site

In this paper, we conducted a detailed analysis of optical turbulence in the Atmospheric Surface Layer (ASL) at Muztagh-ata site during on-site testing. We utilized ultrasonic anemometers positioned on a 30-meter tower to collect and process data at five height levels, obtaining data from October 1, 2021 to the present. We investigated the behavior of optical turbulence parameters ($C_n^2$ and seeing $\varepsilon$) in the ASL. Nighttime $C_n^2$ primarily fluctuated in the range of $10^{-16}$ to $10^{-14}$, exhibiting an exponential decrease with height. During the day, it showed a $h^{-0.82}$ dependency, while at night, it displayed a $h^{-0.48}$ dependency. Additionally, we presented the distribution of seeing across different layers within the ASL, showing a gradual decrease with increasing height, with a median seeing of 0.24 arcseconds at nighttime and 0.48 arcseconds at daytime between 6-30m. We investigated the relationship between surface temperature inversion, seeing in the ASL, and wind speed at the site. Our results show that under temperature inversion conditions, seeing significantly improves and is often accompanied by low to moderate wind speeds, while high wind speeds are usually associated with poorer seeing. Preliminary calculations and observational results, combined with the high altitude and unique geographical location, suggest that Muztagh-ata site has the potential to be an outstanding optical astronomical observatory in the western plateau of china.

physics.ao-ph↗

arXiv2024

Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs

The recent development of chain-of-thought (CoT) decoding has enabled large language models (LLMs) to generate explicit logical reasoning paths for complex problem-solving. However, research indicates that these paths are not always deliberate and optimal. The tree-of-thought (ToT) method employs tree-searching to extensively explore the reasoning space and find better reasoning paths that CoT decoding might overlook. This deliberation, however, comes at the cost of significantly increased inference complexity. In this work, we demonstrate that fine-tuning LLMs leveraging the search tree constructed by ToT allows CoT to achieve similar or better performance, thereby avoiding the substantial inference burden. This is achieved through Chain of Preference Optimization (CPO), where LLMs are fine-tuned to align each step of the CoT reasoning paths with those of ToT using the inherent preference information in the tree-search process. Extensive experimental results show that CPO significantly improves LLM performance in solving a variety of complex problems, including question answering, fact verification, and arithmetic reasoning, demonstrating its effectiveness. Our code is available at https://github.com/sail-sg/CPO.

cs.CL↗