arXiv subjects

Zeyu Xu

Publications and source records attributed to Zeyu Xu.

10 recordsLinked to original sources

arXiv2026

LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models

Vision-Language Models (VLMs) have achieved strong progress in multimodal understanding. However, scaling dense or sparse Mixture-of-Experts (MoE) models to improve performance limits deployment in resource-constrained environments due to the trade-off between high memory usage from full loading and increased latency from on-demand loading. Recently, the Per-Layer Embedding (PLE) architecture addresses this by scaling models with large external embedding tables stored in read-only memory (ROM) and performing lightweight lookup to retrieve relevant embeddings to enhance token representations. Nevertheless, existing PLE-style methods are primarily designed for text embeddings due to the convenience of ID-based retrieval, limiting their effectiveness in VLMs where multimodal embeddings contain richer information for visual tasks. In this paper, we propose LookME, the first framework that enables lookup-based enhancement for multimodal embeddings in VLMs while supporting partitioned storage and on-demand loading. To efficiently lookup arbitrary continuous multimodal embeddings from large-scale embedding tables, we propose a hierarchical two-level lookup method employing a coarse-to-fine strategy that performs lookups from the scene-level to the intra-scene primitive-level. Furthermore, we integrate the lookup method with a sparse injection strategy, which adaptively prioritizes critical embeddings over voluminous multimodal embeddings within layers, and facilitates embedding table reuse across neighboring layers, improving the trade-off among efficiency, model size, and performance. Experiments on multiple visual benchmarks show that LookME outperforms text-only PLE-style methods, validating the effectiveness of lookup-based multimodal embedding enhancement.

cs.CV↗

arXiv2026

Spandana: Reconciling Strict SLOs with Low Cost under Fine-Grained Load Fluctuations

Cloud-based online services face significant sub-second load fluctuations while needing to meet strict Service Level Objectives (SLOs). Cluster operators often over-provision resources to protect SLOs, sacrificing utilization and cost efficiency. Existing reactive and proactive autoscalers, serverless (FaaS) deployments, and VM/FaaS hybrid systems fail to reconcile strict SLO compliance with low cost and high utilization under fine-grained load fluctuation. We introduce Spandana, an architecture that addresses this trade off by decoupling SLO enforcement from cost optimization. A lightweight controller colocated with each application VM enforces SLOs by steering each arriving request between the VM and FaaS. Requests that can meet the SLO stay on the VM; the remaining requests are forwarded to a stock FaaS layer such as AWS Lambda. For cost optimization, Spandana's resource allocator determines the most-efficient VM provisioning by accounting for VM cost, FaaS cost, and traffic volatility, allowing the VM pool to run at high utilization. Our evaluation shows that Spandana maintains strict SLO adherence, achieves 76-86% CPU utilization, and reduces cost by 5-44% over three SOTA baselines.

cs.DC↗

arXiv2026

Evaluating Surrogates in Individualized Treatment Rules

In many decision-making problems, the primary outcome is expensive, time-consuming, or difficult to observe, so individualized treatment rules (ITRs) may be instead learned from surrogate endpoints. However, a surrogate that is highly associated with the primary outcome, or even satisfies existing surrogate criteria, may not necessarily induce a treatment rule that performs well on the primary outcome, especially under treatment resource budget constraints. In this paper, we develop a principled framework for evaluating the decision-making value of surrogate endpoints. We introduce three ITR-oriented performance measures: surrogate regret, which assesses the expected loss from using the surrogate-optimal ITR instead of outcome-optimal ITR; surrogate gain, which quantifies the benefit of surrogate-optimal ITRs relative to the no-treatment baseline; and surrogate efficiency, which evaluates improvement over random treatment assignment. We also extend them to budget-constrained settings. We propose augmented inverse probability weighted (AIPW) estimators for these measures and establish their large-sample properties. We demonstrate the proposed approach on both simulations and an application to the Criteo dataset.

stat.ME↗

arXiv2026

Room Impulse Response Completion Using Signal-Prediction Diffusion Models Conditioned on Simulated Early Reflections

Room impulse responses (RIRs) are fundamental to audio data augmentation, acoustic signal processing, and immersive audio rendering. While geometric simulators such as the image source method (ISM) can efficiently generate early reflections, they lack the realism of measured RIRs due to missing acoustic wave effects. We propose a diffusion-based RIR completion method using signal-prediction conditioned on ISM-simulated direct-path and early reflections. Unlike state-of-the-art methods, our approach imposes no fixed duration constraint on the input early reflections. We further incorporate classifier-free guidance to steer generation toward a target distribution learned from physically realistic RIRs simulated with the Treble SDK. Objective evaluation demonstrates that the proposed method outperforms a state-of-the-art baseline in early RIR completion and energy decay curve reconstruction.

eess.AS↗

arXiv2025

MagicVL-2B: Empowering Vision-Language Models on Mobile Devices with Lightweight Visual Encoders via Curriculum Learning

Vision-Language Models (VLMs) have achieved remarkable breakthroughs in recent years, enabling a diverse array of applications in everyday life. However, the substantial computational and storage demands of VLMs pose significant challenges for their efficient deployment on mobile devices, which represent the most ubiquitous and accessible computing platforms today. In this work, we introduce MagicVL-2B, a novel VLM meticulously optimized for flagship smartphones. MagicVL-2B leverages a lightweight visual encoder with fewer than 100M parameters and features a redesigned dynamic resolution scheme that adaptively generates image tokens without excessive modification of image dimensions. To further enhance the performance of this compact encoder within VLMs, we propose a multimodal curriculum learning strategy that incrementally increases task difficulty and data information density throughout training. This approach substantially improves the model's performance across a variety of sub-tasks. Extensive evaluations on standard VLM benchmarks demonstrate that MagicVL-2B matches the accuracy of current state-of-the-art models while reducing on-device power consumption by 41.1%. These results establish MagicVL-2B as a practical and robust solution for real-world mobile vision-language applications, enabling advanced multimodal intelligence to run directly on smartphones.

cs.CV↗

arXiv2025

E-VRAG: Enhancing Long Video Understanding with Resource-Efficient Retrieval Augmented Generation

Vision-Language Models (VLMs) have enabled substantial progress in video understanding by leveraging cross-modal reasoning capabilities. However, their effectiveness is limited by the restricted context window and the high computational cost required to process long videos with thousands of frames. Retrieval-augmented generation (RAG) addresses this challenge by selecting only the most relevant frames as input, thereby reducing the computational burden. Nevertheless, existing video RAG methods struggle to balance retrieval efficiency and accuracy, particularly when handling diverse and complex video content. To address these limitations, we propose E-VRAG, a novel and efficient video RAG framework for video understanding. We first apply a frame pre-filtering method based on hierarchical query decomposition to eliminate irrelevant frames, reducing computational costs at the data level. We then employ a lightweight VLM for frame scoring, further reducing computational costs at the model level. Additionally, we propose a frame retrieval strategy that leverages the global statistical distribution of inter-frame scores to mitigate the potential performance degradation from using a lightweight VLM. Finally, we introduce a multi-view question answering scheme for the retrieved frames, enhancing the VLM's capability to extract and comprehend information from long video contexts. Experiments on four public benchmarks show that E-VRAG achieves about 70% reduction in computational cost and higher accuracy compared to baseline methods, all without additional training. These results demonstrate the effectiveness of E-VRAG in improving both efficiency and accuracy for video RAG tasks.

cs.CV↗

arXiv2024

Diagnosis Assistant for Liver Cancer Utilizing a Large Language Model with Three Types of Knowledge

Liver cancer has a high incidence rate, but primary healthcare settings often lack experienced doctors. Advances in large models and AI technologies offer potential assistance. This work aims to address limitations in liver cancer diagnosis models, such as poor understanding of medical images, insufficient consideration of liver blood vessels, and ensuring accurate medical information. We propose a specialized diagnostic assistant to improve the diagnostic capabilities of less experienced doctors. Our framework combines large and small models, using optimized small models for precise patient image perception. Specifically, a segmentation network iteratively removes ambiguous pixels for liver tumor segmentation, and a multi-scale, multi-level differential network segments liver vessels. Features from these segmentations and medical records form a patient's personalized knowledge base. For diagnosis, Chain of Thought (COT) technology designs prompts mimicking experienced doctors' thought patterns, and Retrieval-Augmented Generation (RAG) technology provides answers based on reliable domain knowledge and trusted cases. Our small model methods improve liver tumor and vessel segmentation performance, resulting in more accurate information extraction. The large model component scores over 1 point higher on a 10-point scale in evaluations by doctors compared to control methods. Our method enhances semantic perception of medical images, improves classification of ambiguous pixels, and optimizes small object perception. It considers blood vessel positions for specific treatments and improves response credibility and interpretability by mimicking experienced doctors' thought processes using reliable resources. This approach has been recognized by doctors and benefits liver cancer auxiliary diagnosis.

physics.med-ph↗

arXiv2023

Simulating room transfer functions between transducers mounted on audio devices using a modified image source method

The image source method (ISM) is often used to simulate room acoustics due to its ease of use and computational efficiency. The standard ISM is limited to simulations of room impulse responses between point sources and omnidirectional receivers. In this work, the ISM is extended using spherical harmonic directivity coefficients to include acoustic diffraction effects due to source and receiver transducers mounted on physical devices, which are typically encountered in practical situations. The proposed method is verified using finite element simulations of various loudspeaker and microphone configurations in a rectangular room. It is shown that the accuracy of the proposed method is related to the sizes, shapes, number, and positions of the devices inside a room. A simplified version of the proposed method, which can significantly reduce computational effort, is also presented. The proposed method and its simplified version can simulate room transfer functions more accurately than currently available image source methods and can aid the development and evaluation of speech and acoustic signal processing algorithms, including speech enhancement, acoustic scene analysis, and acoustic parameter estimation.

eess.AS↗

arXiv2021

Coherent Integration for Targets with Constant Cartesian Velocities Based on Accurate Range Model

Long-time coherent integration (LTCI) is one of the most important techniques to improve radar detection performance of weak targets. However, for the targets moving with constant Cartesian velocities (CCV), the existing LTCI methods based on polynomial motion models suffer from limited integration time and coverage of target speed due to model mismatch. Here, a novel generalized Radon Fourier transform method for CCV targets is presented, based on the accurate range evolving model, which is a square root of a polynomial with terms up to the second order with target speed as the factor. The accurate model instead of approximate polynomial models used in the proposed method enables effective energy integration on characteristic invariant with feasible computational complexity. The target samplings are collected and the phase fluctuation among pulses is compensated according to the accurate range model. The high order range migration and complex Doppler frequency migration caused by the highly nonlinear signal are eliminated simultaneously. Integration results demonstrate that the proposed method can not only achieve effective coherent integration of CCV targets regardless of target speed and coherent processing interval, but also provide additional observation and resolution in speed domain.

eess.SP↗

arXiv2018

Video Processing on the Edge for Multimedia IoT Systems

In this article, we first survey the current situation of video processing on the edge for multimedia Internet-of-Things (M-IoT) systems in three typical scenarios, i.e., smart cities, satellite networks, and Internet-of-Vehicles. By summarizing a general model of the edge video processing, the importance of developing an edge computing platform is highlighted. Then, we give a method of implementing cooperative video processing on an edge computing platform based on light-weighted virtualization technologies. Performance evaluation is conducted and some insightful observations can be obtained. Moreover, we summarize challenges and opportunities of realizing effective edge video processing for M-IoT systems.

cs.MM↗