arXiv subjects

Yu Xiao

Publications and source records attributed to Yu Xiao.

At least 37 records · Page 2Linked to original sources

arXiv2026

DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

Visual document retrieval (VDR) is dominated by multi-billion-parameter models that are slow to index at full corpus scale and expensive to serve. Prior compression routes either train a smaller multi-vector encoder from scratch or distil only the query side; neither yields a compact single-vector retriever end-to-end. We present DistilVDR, a 524M end-to-end VDR system distilled bilaterally from a single 8B vision-language teacher under a pointwise cosine alignment loss. All supervision comes from the frozen teacher's embedding space, which was itself trained with relevance supervision, so the student objective needs no relevance labels, negative sampling, or contrastive term. We match VDR's text-query and image-document input asymmetry with an asymmetric encoder-only student that concentrates visual capacity on the document side and keeps the query side at 70M parameters. We release two variants that share the same encoders and training and differ only in the document encoder's visual-tile budget: DistilVDR-HiRes attains 61.74 average NDCG@5 on ViDoRe v1+v2+v3 (86.9% of the 8B teacher) and leads every reproduced sub-1B baseline on the high-resolution-sensitive v3 benchmark, while DistilVDR-Fast attains 59.98 at a 3 times smaller visual-token budget. Both variants store one million documents in a 15.6 times smaller index than the strongest sub-1B multi-vector baseline and index the corpus an order of magnitude faster. The code is available at https://github.com/Ryenhails/NanoVDR.

cs.IR↗

arXiv2026

Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels

Reliable visual document understanding requires a model to attribute each answer to the evidence regions that support it. Recent benchmarks and systems express this step through a coordinate interface: the model outputs the coordinates of bounding boxes that mark the evidence regions in the document. Under this interface, vision-language models often fail to identify the right regions even when the answer is correct, a failure known as Attribution Hallucination. We present a study that investigates whether this failure is partially limited by what the model can express through coordinates. On a verified bilingual CiteVQA subset, we compare the coordinate interface with a language interface in which the model outputs only text, quoting its evidence verbatim, and a multimodal retriever returns the location of each quote as a page region proposed by a layout parser (tables and figures are quoted through their captions or notes); the comparison is repeated over six open vision-language models. Compared with the coordinate interface, evidence recall rises from at most 8 points to between 26 and 47 and the hallucination rate roughly halves, with little change in answer quality. Building on this comparison, we use the same quote-and-retrieve pipeline as a training scaffold: because region-level evidence labels are expensive to collect for long documents, we introduce a GRPO recipe whose reward is a judge's reading of the gold answer and crops of the retrieved regions, training the model to quote better evidence without any region labels and raising an 8B backbone's strict attributed accuracy from 22.4 to 33.8. These findings indicate a practical path to improve attribution"without a coordinate interface and without costly region-level supervision.

cs.CV↗

arXiv2026

Converting T1-weighted MRI from 3T to 7T quality using deep learning

Ultra-high resolution 7 tesla (7T) magnetic resonance imaging (MRI) provides detailed anatomical views, offering better signal-to-noise ratio, resolution and tissue contrast than 3T MRI, though at the cost of accessibility. We present an advanced deep learning model for synthesizing 7T brain MRI from 3T brain MRI. Paired 7T and 3T T1-weighted images were acquired from 172 participants (124 cognitively unimpaired, 48 impaired) from the Swedish BioFINDER-2 study. To synthesize 7T MRI from 3T images, we trained two models: a specialized U-Net, and a U-Net integrated with a generative adversarial network (GAN U-Net). Our models outperformed two previous state-of-the-art 3T-to-7T models in image-based evaluation metrics. Four blinded MRI professionals judged our synthetic 7T images as comparable in detail to real 7T images, and superior in subjective visual quality to 7T images, due to the reduction of artifacts. Using both SynthSeg and NextBrain, automated segmentations of the synthetic 7T images were more similar to real 7T segmentations than automated segmentations from the 3T images that were used to synthesize the 7T images. Finally, synthetic 7T images showed similar performance to real 3T images in downstream prediction of cognitive status using MRI derivatives (n=3,168). In all, we show that synthetic T1-weighted brain images approaching 7T quality can be generated from 3T images, which may improve image quality and segmentation, without compromising performance in downstream tasks. Future directions, possible clinical use cases, and limitations are discussed.

eess.IV↗

arXiv2026

Quantitative rapid boundary stabilization via modal decomposition and its application to the Allen-Cahn equation

We investigate quantitative rapid stabilization for the one-dimensional Allen--Cahn equation and develop a quantitative modal decomposition approach that makes explicit the dependence of the feedback laws and stabilization costs on the prescribed decay rate. We construct an explicit feedback law on the finite-dimensional unstable modes via Ackermann's formula. The explicit structure of the feedback allows us to derive quantitative low-frequency estimates, which, combined with the frequency Lyapunov method, yield quantitative stabilization estimates. Together with the stabilization framework of [37], the resulting estimates can be adapted to a broader class of one-dimensional parabolic models. We further construct piecewise feedback laws that yield the null controllability with control costs and finite-time stabilization.

math.AP↗

arXiv2026

Fine-grained Motion Retrieval via Joint-Angle Motion Images and Token-Patch Late Interaction

Text-motion retrieval aims to learn a semantically aligned latent space between natural language descriptions and 3D human motion skeleton sequences, enabling bidirectional search across the two modalities. Most existing methods use a dual-encoder framework that compresses motion and text into global embeddings, discarding fine-grained local correspondences, and thus reducing accuracy. Additionally, these global-embedding methods offer limited interpretability of the retrieval results. To overcome these limitations, we propose an interpretable, joint-angle-based motion representation that maps joint-level local features into a structured pseudo-image, compatible with pre-trained Vision Transformers. For text-to-motion retrieval, we employ MaxSim, a token-wise late interaction mechanism, and enhance it with Masked Language Modeling regularization to foster robust, interpretable text-motion alignment. Extensive experiments on HumanML3D and KIT-ML show that our method outperforms state-of-the-art text-motion retrieval approaches while offering interpretable fine-grained correspondences between text and motion. The code is available in the supplementary material.

cs.CV↗

arXiv2026

UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection

Visual anomaly detection is a fundamental task in industrial automation. While existing approaches have achieved notable progress in identifying structural defects, the detection of logical anomalies remains relatively underexplored. In practice, structural and logical anomalies frequently co-occur in industrial workflows. Therefore, a solution capable of detecting both structural and logical anomalies is crucial for advancing comprehensive anomaly detection research. To address this limitation, we propose a unified framework, termed UniSLAD, which jointly addresses logical and structural anomalies without additional training, enabling a practical solution for dynamic industrial environments. First, we introduce a dual-feature extractor that synergistically integrates a Convolutional Neural Network (CNN) backbone for local texture perception with a Transformer backbone for global contextual reasoning, yielding richer and more comprehensive representations. Building on this foundation, we design dual-granularity feature representation modules. At the patch level, memory banks enhanced by the Mahalanobis Transform (MT) preserve representative features and support more discriminative anomaly scoring. At the image level, distribution maps are aggregated using Lower-Upper Mean (LUM) and Power Mean Pooling (PMP), yielding a more robust global representation than conventional average pooling. Extensive experiments on the two industrial benchmarks demonstrate that UniSLAD achieves competitive performance in comprehensive anomaly detection, achieving 99.4% and 93.1%, respectively. Furthermore, ablation studies verify the individual contributions and effectiveness of each proposed component.

cs.CV↗

arXiv2026

Quantitative rapid stabilization for parabolic equations via the linear quadratic theory

This paper addresses the problem of quantitative rapid stabilization via the linear quadratic (LQ) theory. Specifically, for non-self-adjoint parabolic equations, by virtue of the LQ theory, we derive the quantitative rapid stabilization by selecting a special cost functional and combining it with a quantitative observability inequality. Furthermore, this approach reveals the equivalence between the quantitative rapid stabilization and the quantitative observability inequality for linear systems. In addition, we apply this framework to the Navier--Stokes equations and establish the quantitative rapid stabilization around nontrivial steady states. Finally, we extend this methodology to finite-dimensional feedback laws in self-adjoint cases.

math.OC↗

arXiv2026

Benchmarking and Mechanistic Analysis of Vision-Language Models for Cross-Depiction Assembly Instruction Alignment

2D assembly diagrams are often abstract and hard to follow, creating a need for intelligent assistants that can monitor progress, detect errors, and provide step-by-step guidance. In mixed reality settings, such systems must recognize completed and ongoing steps from the camera feed and align them with the diagram instructions. Vision Language Models (VLMs) show promise for this task, but face a depiction gap because assembly diagrams and video frames share few visual features. To systematically assess this gap, we construct IKEA-Bench, a benchmark of 1,623 questions across 6 task types on 29 IKEA furniture products, and evaluate 19 VLMs (2B-38B) under three alignment strategies. Our key findings: (1) assembly instruction understanding is recoverable via text, but text simultaneously degrades diagram-to-video alignment; (2) architecture family predicts alignment accuracy more strongly than parameter count; (3) video understanding remains a hard bottleneck unaffected by strategy. A three-level mechanistic analysis further reveals that diagrams and video occupy disjoint ViT subspaces, and that adding text shifts models from visual to text-driven reasoning. These results identify visual encoding as the primary target for improving cross-depiction robustness. Project page: https://ryenhails.github.io/IKEA-Bench/

cs.CV↗

arXiv2026

Encoder-Free Human Motion Understanding via Structured Motion Descriptions

The world knowledge and reasoning capabilities of text-based large language models (LLMs) are advancing rapidly, yet current approaches to human motion understanding, including motion question answering and captioning, have not fully exploited these capabilities. Existing LLM-based methods typically learn motion-language alignment through dedicated encoders that project motion features into the LLM's embedding space, remaining constrained by cross-modal representation and alignment. Inspired by biomechanical analysis, where joint angles and body-part kinematics have long served as a precise descriptive language for human movement, we propose \textbf{Structured Motion Description (SMD)}, a rule-based, deterministic approach that converts joint position sequences into structured natural language descriptions of joint angles, body part movements, and global trajectory. By representing motion as text, SMD enables LLMs to apply their pretrained knowledge of body parts, spatial directions, and movement semantics directly to motion reasoning, without requiring learned encoders or alignment modules. We show that this approach goes beyond state-of-the-art results on both motion question answering (66.7\% on BABEL-QA, 90.1\% on HuMMan-QA) and motion captioning (R@1 of 0.584, CIDEr of 53.16 on HumanML3D), surpassing all prior methods. SMD additionally offers practical benefits: the same text input works across different LLMs with only lightweight LoRA adaptation (validated on 8 LLMs from 6 model families), and its human-readable representation enables interpretable attention analysis over motion descriptions. Code, data, and pretrained LoRA adapters are available at https://yaozhang182.github.io/motion-smd/.

cs.CV↗

arXiv2026

ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models

Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color names or codes, while their capacity to handle \emph{implicit concepts}, such as emotions and visual states, remains underexplored. To address this gap, we introduce ColorConceptBench, an expert-annotated benchmark that systematically evaluates color-concept associations through probabilistic color distributions. ColorConceptBench moves beyond explicit color specifications by examining how models interpret 1,281 implicit color concepts, grounded in 6,584 human annotations. Our evaluation of nine leading T2I models reveals that performance varies substantially across semantic categories, and models exhibit a significant lack of sensitivity to abstract semantics. These limitations persist even when applying classifier-free guidance scaling at inference time, suggesting that achieving human-like color understanding demands a shift in how models learn and represent implicit semantic meaning.

cs.CV↗

arXiv2026

100x Cost & Latency Reduction: Performance Analysis of AI Query Approximation using Lightweight Proxy Models

Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of queries one can express over the combination of structured and unstructured data. LLMs offer remarkable semantic reasoning capabilities, making them an essential tool for complex and nuanced queries that blend structured and unstructured data. While extremely powerful, these AI queries can become prohibitively costly when invoked thousands of times. This paper provides an extensive evaluation of a recent AI query approximation approach that enables low cost analytics and database applications to benefit from AI queries. The approach delivers >100x cost and latency reduction for the semantic filter operator and also important gains for semantic ranking. The cost and performance gains come from utilizing cheap and accurate proxy models over embedding vectors. We show that despite the massive gains in latency and cost, these proxy models preserve accuracy and occasionally improve accuracy across various benchmark datasets, including the extended Amazon reviews benchmark that has 10M rows. We present an OLAP-friendly architecture within Google BigQuery for this approach for purely online (ad hoc) queries, and a low-latency HTAP database-friendly architecture in AlloyDB that could further improve the latency by moving the proxy model training offline. We present techniques that accelerate the proxy model training.

cs.DB↗

arXiv2026

Exploring Human-AI Collaboration in E-Textile Design: A Case Study on Flex Sensor Placement for Shoulder Motion Detection

Flex sensors are widely used in e-textiles for detecting joint motions and, subsequently, full-body movements. A critical initial step in utilizing these sensors is determining the optimal placement on the body to accurately capture human motions. This task requires a combination of expertise in fields such as anatomy, biomechanics, and textile design, which is seldom found in a single practitioner. Generative AI, such as Large Language Models (LLMs), has recently shown promise in facilitating design. However, to our knowledge, the extent to which LLMs can aid in the e-textile design process remains largely unexplored in the literature. To address this open question, we conducted a case study focusing on shoulder motion detection using flex sensors. We enlisted three human designers to participate in an experiment involving human-AI collaborative design. We examined design efficiency across three scenarios: designs produced by LLMs alone, by humans alone, and through collaboration between LLMs and human designers. Our quantitative and qualitative analyses revealed an intriguing relationship between expertise and outcomes: the least experienced human designer achieved continuous improvement through collaboration, ultimately matching the best performance achieved by humans alone, whereas the most experienced human designer experienced a decline in performance. Additionally, the effectiveness of human-AI collaboration is affected by the granularity of feedback - incremental adjustments outperformed sweeping redesigns - and the level of abstraction, with observation-oriented feedback producing better outcomes than prescriptive anatomical directives. These findings offer valuable insights into the opportunities and challenges associated with human-AI collaborative e-textile design.

cs.HC↗

arXiv2026

LingoMotion: An Interpretable and Unambiguous Symbolic Representation for Human Motion

Existing representations for human motion, such as MotionGPT, often operate as black-box latent vectors with limited interpretability and build on joint positions which can cause ambiguity. Inspired by the hierarchical structure of natural languages - from letters to words, phrases, and sentences - we propose LingoMotion, a motion language that facilitates interpretable and unambiguous symbolic representation for both simple and complex human motion. In this paper, we introduce the concept design of LingoMotion, including the definitions of motion alphabet based on joint angles, the morphology for forming words and phrases to describe simple actions like walking and their attributes like speed and scale, as well as the syntax for describing more complex human activities with sequences of words and phrases. The preliminary results, including the implementation and evaluation of motion alphabet using a large-scale motion dataset Motion-X, demonstrate the high fidelity of motion representation.

cs.CV↗

arXiv2025

Efficient Online Continual Learning in Sensor-Based Human Activity Recognition

Machine learning models for sensor-based human activity recognition (HAR) are expected to adapt post-deployment to recognize new activities and different ways of performing existing ones. To address this need, Online Continual Learning (OCL) mechanisms have been proposed, allowing models to update their knowledge incrementally as new data become available while preserving previously acquired information. However, existing OCL approaches for sensor-based HAR are computationally intensive and require extensive labeled samples to represent new changes. Recently, pre-trained model-based (PTM-based) OCL approaches have shown significant improvements in performance and efficiency for computer vision applications. These methods achieve strong generalization capabilities by pre-training complex models on large datasets, followed by fine-tuning on downstream tasks for continual learning. However, applying PTM-based OCL approaches to sensor-based HAR poses significant challenges due to the inherent heterogeneity of HAR datasets and the scarcity of labeled data in post-deployment scenarios. This paper introduces PTRN-HAR, the first successful application of PTM-based OCL to sensor-based HAR. Unlike prior PTM-based OCL approaches, PTRN-HAR pre-trains the feature extractor using contrastive loss with a limited amount of data. This extractor is then frozen during the streaming stage. Furthermore, it replaces the conventional dense classification layer with a relation module network. Our design not only significantly reduces the resource consumption required for model training while maintaining high performance, but also improves data efficiency by reducing the amount of labeled data needed for effective continual learning, as demonstrated through experiments on three public datasets, outperforming the state-of-the-art. The code can be found here: https://anonymous.4open.science/r/PTRN-HAR-AF60/

cs.CV↗

arXiv2025

StrengthSense: A Dataset of IMU Signals Capturing Everyday Strength-Demanding Activities

Tracking strength-demanding activities with wearable sensors like IMUs is crucial for monitoring muscular strength, endurance, and power. However, there is a lack of comprehensive datasets capturing these activities. To fill this gap, we introduce \textit{StrengthSense}, an open dataset that encompasses IMU signals capturing 11 strength-demanding activities, such as sit-to-stand, climbing stairs, and mopping. For comparative purposes, the dataset also includes 2 non-strength demanding activities. The dataset was collected from 29 healthy subjects utilizing 10 IMUs placed on limbs and the torso, and was annotated using video recordings as references. This paper provides a comprehensive overview of the data collection, pre-processing, and technical validation. We conducted a comparative analysis between the joint angles estimated by IMUs and those directly extracted from video to verify the accuracy and reliability of the sensor data. Researchers and developers can utilize \textit{StrengthSense} to advance the development of human activity recognition algorithms, create fitness and health monitoring applications, and more.

cs.CV↗

arXiv2025

Rapid boundary stabilization of 1D nonlinear parabolic equations

In this paper, we focus on the rapid boundary stabilization of 1D nonlinear parabolic equations via the modal decomposition method. The nonlinear term is assumed to satisfy certain local Lipschitz continuity and global growth conditions. Through the modal decomposition, we construct a feedback control that modifies only the unstable eigenvalues to achieve spectral reduction. Under this control, we establish locally rapid stabilization by estimating the nonlinearity in Lyapunov stability analysis. Furthermore, utilizing the dissipative property, we derive a globally rapid stabilization result for dissipative systems such as the Burgers equation and the Allen-Cahn equation.

math.AP↗

arXiv2025

Carrier-phonon decoupling via annealing enhances thermoelectric performance of Bi2(Te,Se)3

Thermoelectric cooling based on the Peltier effect requires high-performance materials near room temperature. In this work, Bi2Te2.6Se0.4 synthesized by melting-hot pressing followed by 100 h annealing (MT-HP-AN) at 723 K exhibits markedly improved performance. Annealing introduces cation vacancies via Te(Se) volatilization, lowering carrier density and enhancing mobility, while simultaneously increasing phonon scattering. A peak ZT of 1.06 at 373 K and an average ZT of 0.99 at 300-423 K are achieved. This MT-HP-AN approach offers a simple yet effective strategy to decouple carrier and phonon transport, advancing the potential of n-type BTS for thermo-electric cooling applications.

cond-mat.mtrl-sci↗

arXiv2025

Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing

The demand for edge artificial intelligence to process event-based, complex data calls for hardware beyond conventional digital, von-Neumann architectures. Neuromorphic computing, using spiking neural networks (SNNs) with emerging memristors, is a promising solution, but existing systems often discard temporal information, demonstrate non-competitive accuracy, or rely on neuron designs with large capacitors that limit the scalability and processing speed. Here we experimentally demonstrate a fully integrated memristive SNN with a 128x24 memristor array integrated on a CMOS chip and custom-designed analog neurons, achieving high-speed, energy-efficient event-driven processing of accelerated spatiotemporal spike signals with high computational fidelity. This is achieved through a proportional time-scaling property of the analog neurons, which allows them to use only compact on-chip capacitors and train directly on the spatiotemporal data without special encoding by backpropagation through surrogate gradient, thus overcoming the speed, scalability and accuracy limitations of previous designs. We experimentally validated our hardware using the DVS128 Gesture dataset, accelerating each sample 50,000-fold to a 30 us duration. The system achieves an experimental accuracy of 93.06% with a measured energy efficiency of 101.05 TSOPS/W. We project significant future efficiency gains by leveraging picosecond-width spikes and advanced fabrication nodes. By decoupling the hardware's operational timescale from the data's natural timescale, this work establishes a viable pathway for developing neuromorphic processors capable of high-throughput analysis, critical for rapid-response edge computing applications like high-speed analysis of buffered sensor data or ultra-fast in-sensor machine vision.

physics.app-ph↗