arXiv subjects

Qi Xu

Publications and source records attributed to Qi Xu.

At least 55 records · Page 3Linked to original sources

arXiv2026

Augmenting Scholarly Reading with Cross-Media Annotations

Scholarly reading often involves engaging with various supplementary materials beyond PDFs to support understanding. In practice, scholars frequently incorporate such external materials into their reading workflow through annotation. However, most existing PDF annotation tools support only a limited range of media types for embedding annotations in PDF documents. This paper investigates cross-media annotation as a design space for augmenting academic reading. We present a design exploration of a cross-media annotation tool that allows scholars to easily link PDF content with other documents and materials such as audio, video or web pages. The proposed design has the potential to enrich reading practices and enable scholars to guide and support other researchers' reading experiences.

cs.HC↗

arXiv2026

Key-Value Pair-Free Continual Learner via Task-Specific Prompt-Prototype

Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this domain; however, they typically rely on key-value pairing, which can introduce inter-task interference and hinder scalability. To overcome these limitations, we propose a novel approach employing task-specific Prompt-Prototype (ProP), thereby eliminating the need for key-value pairs. In our method, task-specific prompts facilitate more effective feature learning for the current task, while corresponding prototypes capture the representative features of the input. During inference, predictions are generated by binding each task-specific prompt with its associated prototype. Additionally, we introduce regularization constraints during prompt initialization to penalize excessively large values, thereby enhancing stability. Experiments on several widely used datasets demonstrate the effectiveness of the proposed method. In contrast to mainstream prompt-based approaches, our framework removes the dependency on key-value pairs, offering a fresh perspective for future continual learning research.

cs.AI↗

arXiv2026

DT-BEHRT: Disease Trajectory-aware Transformer for Interpretable Patient Representation Learning

The growing adoption of electronic health record (EHR) systems has provided unprecedented opportunities for predictive modeling to guide clinical decision making. Structured EHRs contain longitudinal observations of patients across hospital visits, where each visit is represented by a set of medical codes. While sequence-based, graph-based, and graph-enhanced sequence approaches have been developed to capture rich code interactions over time or within the same visits, they often overlook the inherent heterogeneous roles of medical codes arising from distinct clinical characteristics and contexts. To this end, in this study we propose the Disease Trajectory-aware Transformer for EHR (DT-BEHRT), a graph-enhanced sequential architecture that disentangles disease trajectories by explicitly modeling diagnosis-centric interactions within organ systems and capturing asynchronous progression patterns. To further enhance the representation robustness, we design a tailored pre-training methodology that combines trajectory-level code masking with ontology-informed ancestor prediction, promoting semantic alignment across multiple modeling modules. Extensive experiments on multiple benchmark datasets demonstrate that DT-BEHRT achieves strong predictive performance and provides interpretable patient representations that align with clinicians' disease-centered reasoning. The source code is publicly accessible at https://github.com/GatorAIM/DT-BEHRT.git.

cs.LG↗

arXiv2026

ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring

Automatic sleep stage scoring is crucial for the diagnosis and treatment of sleep disorders. Although deep learning models have advanced the field, many existing models are computationally demanding and designed for single-channel electroencephalography (EEG), limiting their practicality for multimodal polysomnography (PSG) data. To overcome this, we propose ULW-SleepNet, an ultra-lightweight multimodal sleep stage scoring framework that efficiently integrates information from multiple physiological signals. ULW-SleepNet incorporates a novel Dual-Stream Separable Convolution (DSSC) Block, depthwise separable convolutions, channel-wise parameter sharing, and global average pooling to reduce computational overhead while maintaining competitive accuracy. Evaluated on the Sleep-EDF-20 and Sleep-EDF-78 datasets, ULW-SleepNet achieves accuracies of 86.9% and 81.4%, respectively, with only 13.3K parameters and 7.89M FLOPs. Compared to state-of-the-art methods, our model reduces parameters by up to 98.6% with only marginal performance loss, demonstrating its strong potential for real-time sleep monitoring on wearable and IoT devices. The source code for this study is publicly available at https://github.com/wzw999/ULW-SLEEPNET.

cs.LG↗

arXiv2026

Causal Decoding for Hallucination-Resistant Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) deliver detailed responses on vision-language tasks, yet remain susceptible to object hallucination (introducing objects not present in the image), undermining reliability in practice. Prior efforts often rely on heuristic penalties, post-hoc correction, or generic decoding tweaks, which do not directly intervene in the mechanisms that trigger object hallucination and thus yield limited gains. To address this challenge, we propose a causal decoding framework that applies targeted causal interventions during generation to curb spurious object mentions. By reshaping the decoding dynamics to attenuate spurious dependencies, our approach reduces false object tokens while maintaining descriptive quality. Across captioning and QA benchmarks, our framework substantially lowers object-hallucination rates and achieves state-of-the-art faithfulness without degrading overall output quality.

cs.LG↗

arXiv2026

Dist2ill: Distributional Distillation for One-Pass Uncertainty Estimation in Large Language Models

Large Language Models (LLMs) often exhibit misalignment between the quality of their generated responses and the confidence estimates they assign to them. Bayesian treatments, such as marginalizing over a reliable weight posterior or over the space of reasoning traces, provide an effective remedy, but incur substantial computational overhead due to repeated sampling at test time. To enable accurate uncertainty estimation in a single forward pass, we propose a novel distributional distillation framework (Dist2ill) that trains an LLM to produce multiple diverse reasoning paths within one inference pass, while using a lightweight parametric module to approximate empirical confidence scores derived from the sampling distribution. Extensive experiments demonstrate that Dist2ill preserves reasoning diversity and achieves state-of-the-art uncertainty estimation, substantially improving Expected Calibration Error (ECE) and Negative Log-Likelihood (NLL), while remaining computationally efficient.

cs.LG↗

arXiv2026

Sparse group principal component analysis via double thresholding with application to multi-cellular programs

Multi-cellular programs (MCPs) are coordinated patterns of gene expression across interacting cell types that collectively drive complex biological processes such as tissue development and immune responses. While MCPs are typically estimated from high-dimensional gene expression data using methods like sparse principal component analysis or latent factor models, these approaches often suffer from high computational costs and limited statistical power. In this work, we propose Sparse Group Principal Component Analysis (SGPCA) to estimate MCPs by leveraging their inherent group and individual sparsity. We introduce an efficient double-thresholding algorithm based on power iteration. In each iteration, a group thresholding step first identifies relevant gene groups, followed by an individual thresholding step to select active cell types. This algorithm achieves a linear computational complexity of $O(np)$, making it highly efficient and scalable for large-scale genomic analyses. We establish theoretical guarantees for SGPCA, including statistical consistency and a convergence rate that surpasses competing methods. Through extensive simulations, we demonstrate that SGPCA achieves superior estimation accuracy and improved statistical power for signal detection. Furthermore, We apply SGPCA to a Lupus study, discovering differentially expressed MCPs distinguishing Lupus patients from normal subjects.

stat.ME↗

arXiv2026

Causal-Informed Hybrid Online Adaptive Optimization for Ad Load Personalization in Large-Scale Social Networks

Personalizing ad load in large-scale social networks requires balancing user experience and conversions under operational constraints. Traditional primal-dual methods enforce constraints reliably but adapt slowly in dynamic environments, while Bayesian Optimization (BO) enables exploration but suffers from slow convergence. We propose a hybrid online adaptive optimization framework CTRCBO ( Cohort-Based Trust Region Contextual Bayesian Optimization), combining primal-dual with BO, enhanced by trust-region updates and Gaussian Process Regression (GPR) surrogates for both objectives and constraints. Our approach leverages a upstream Causal ML model to inform the surrogate, improving decision quality and enabling efficient exploration-exploitation and online tuning. We evaluate our method on a billion-user social network, demonstrating faster convergence, robust constraint satisfaction, and improved personalization metrics, including real-world online AB test results.

cs.SI↗

arXiv2025

Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks via Top-K activation and have shown resilience against catastrophic forgetting. However, their rigid modularity limits cross-task knowledge reuse and leads to performance degradation under high sparsity. We propose Selective Subnetwork Distillation (SSD), a structurally guided continual learning framework that treats distillation not as a regularizer but as a topology-aligned information conduit. SSD identifies neurons with high activation frequency and selectively distills knowledge within previous Top-K subnetworks and output logits, without requiring replay or task labels. This enables structural realignment while preserving sparse modularity. Experiments on Split CIFAR-10, CIFAR-100, and MNIST demonstrate that SSD improves accuracy, retention, and representation coverage, offering a structurally grounded solution for sparse continual learning.

cs.LG↗

arXiv2025

AVM: Towards Structure-Preserving Neural Response Modeling in the Visual Cortex Across Stimuli and Individuals

While deep learning models have shown strong performance in simulating neural responses, they often fail to clearly separate stable visual encoding from condition-specific adaptation, which limits their ability to generalize across stimuli and individuals. We introduce the Adaptive Visual Model (AVM), a structure-preserving framework that enables condition-aware adaptation through modular subnetworks, without modifying the core representation. AVM keeps a Vision Transformer-based encoder frozen to capture consistent visual features, while independently trained modulation paths account for neural response variations driven by stimulus content and subject identity. We evaluate AVM in three experimental settings, including stimulus-level variation, cross-subject generalization, and cross-dataset adaptation, all of which involve structured changes in inputs and individuals. Across two large-scale mouse V1 datasets, AVM outperforms the state-of-the-art V1T model by approximately 2% in predictive correlation, demonstrating robust generalization, interpretable condition-wise modulation, and high architectural efficiency. Specifically, AVM achieves a 9.1% improvement in explained variance (FEVE) under the cross-dataset adaptation setting. These results suggest that AVM provides a unified framework for adaptive neural modeling across biological and experimental conditions, offering a scalable solution under structural constraints. Its design may inform future approaches to cortical modeling in both neuroscience and biologically inspired AI systems.

cs.CV↗

arXiv2025

Representation Retrieval Learning for Heterogeneous Data Integration

In the era of big data, large-scale, multi-source, multi-modality datasets are increasingly ubiquitous, offering unprecedented opportunities for predictive modeling and scientific discovery. However, these datasets often exhibit complex heterogeneity, such as covariates shift, posterior drift, and blockwise missingness, which worsen predictive performance of existing supervised learning algorithms. To address these challenges simultaneously, we propose a novel Representation Retrieval (R2) framework, which integrates a dictionary of representation learning modules (representer dictionary) with data source-specific sparsity-induced machine learning model (learners). Under the R2 framework, we introduce the notion of integrativeness for each representer, and propose a novel Selective Integration Penalty (SIP) to explicitly encourage more integrative representers to improve predictive performance. Theoretically, we show that the excess risk bound of the R2 framework is characterized by the integrativeness of representers, and SIP effectively improves the excess risk. Extensive simulation studies validate the superior performance of R2 framework and the effect of SIP. We further apply our method to two real-world datasets to confirm its empirical success.

cs.LG↗

arXiv2025

A geophysical free-boundary system modeling an ice-sheet interacting with an ocean

We consider a free-boundary model for the ice-sheet interacting with an ocean. The model captures the coupling between a viscous geophysical fluid and an elastic interface through kinematic and dynamic boundary conditions that account for hydrodynamic loading. Using the ALE formulation, we derive a system on a fixed reference domain and establish local-in-time a priori estimates for strong solutions with initial data in $H^2$. The main analytical difficulties arise from the nonlinear terms involving vertical derivatives and from high-order pressure contributions on the interface.

math.AP↗

arXiv2025

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

Semantic retrieval is crucial for modern applications yet remains underexplored in current research. Existing datasets are limited to single languages, single images, or singular retrieval conditions, often failing to fully exploit the expressive capacity of visual information as evidenced by maintained performance when images are replaced with captions. However, practical retrieval scenarios frequently involve interleaved multi-condition queries with multiple images. Hence, this paper introduces MERIT, the first multilingual dataset for interleaved multi-condition semantic retrieval, comprising 320,000 queries with 135,000 products in 5 languages, covering 7 distinct product categories. Extensive experiments on MERIT identify existing models's limitation: focusing solely on global semantic information while neglecting specific conditional elements in queries. Consequently, we propose Coral, a novel fine-tuning framework that adapts pre-trained MLLMs by integrating embedding reconstruction to preserve fine-grained conditional elements and contrastive learning to extract comprehensive global semantics. Experiments demonstrate that Coral achieves a 45.9% performance improvement over conventional approaches on MERIT, with strong generalization capabilities validated across 8 established retrieval benchmarks. Collectively, our contributions - a novel dataset, identification of critical limitations in existing approaches, and an innovative fine-tuning framework - establish a foundation for future research in interleaved multi-condition semantic retrieval.

cs.CV↗

arXiv2025

Difference-in-Differences with Compositional Changes

This paper studies Difference-in-Differences (DiD) setups with repeated cross-sectional data and potential compositional changes across time periods. We begin our analysis by deriving the efficient influence function and the semiparametric efficiency bound for the average treatment effect on the treated (ATT). We introduce nonparametric estimators that attain the semiparametric efficiency bound under mild rate conditions on the estimators of the nuisance functions, exhibiting a type of rate doubly robust (DR) property. Additionally, we document a trade-off related to compositional changes: We derive the asymptotic bias of DR DiD estimators that erroneously exclude compositional changes and the efficiency loss when one fails to correctly rule out compositional changes. We propose a nonparametric Hausman-type test for compositional changes based on these trade-offs. The finite sample performance of the proposed DiD tools is evaluated through Monte Carlo experiments and an empirical application. We consider extensions of our framework that accommodate double machine learning procedures with cross-fitting, and setups when some units are observed in both pre- and post-treatment periods. As a by-product of our analysis, we present a new uniform stochastic expansion of the local polynomial multinomial logit estimator, which may be of independent interest.

econ.EM↗

arXiv2025

Characterizing the astrometric quality of AGNs in Gaia-CRF3

Active Galactic Nuclei (AGNs), owing to their great distances and compact sizes, serve as fundamental anchors for defining the celestial reference frame. With about 1.9 million AGNs observed in Gaia DR3 at optical precision comparable to radio wavelengths, Gaia provides a solid foundation for constructing the next-generation, kinematically non-rotating optical reference frame. Accurate assessment of systematic residuals in AGN astrometry is therefore crucial. In this talk, we analysed the parallaxes and proper motions of Gaia DR3 AGNs to characterize systematic errors and their correlations with various physical and observational properties. A subset of Gaia-CRF3 AGNs exhibits significant astrometric offsets, mainly arising from dual or lensed quasars whose structural variations induce photocenter jitter, mimicking parallax and proper motion. Such sources must be carefully excluded from reference frame construction. To this end, we introduce an astrometric quality index for each source to quantify its astrometric reliability. The results reveal a strong correlation between lower quality index values and increasing errors in position, proper motion, and parallax, demonstrating that the proposed index provides an effective metric for selecting high-fidelity AGNs as primary reference sources.

astro-ph.GA↗

arXiv2025

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging explicit structure-and-motion priors in the parametrization to improve event alignment. The former notably introduces bias in results and computational overhead, while the latter, which parametrizes the optical flow in terms of the scene depth and the camera motion, often converges to suboptimal local minima. To address these issues, we propose an unsupervised framework that jointly optimizes egomotion and optical flow via implicit spatial-temporal and geometric regularization. First, by modeling camera's egomotion as a continuous spline and optical flow as an implicit neural representation, our method inherently embeds spatial-temporal coherence through inductive biases. Second, we incorporate structure-and-motion priors through differential geometric constraints, bypassing explicit depth estimation while maintaining rigorous geometric consistency. As a result, our framework (called E-MoFlow) unifies egomotion and optical flow estimation via implicit regularization under a fully unsupervised paradigm. Experiments demonstrate its versatility to general 6-DoF motion scenarios, achieving state-of-the-art performance among unsupervised methods and competitive even with supervised approaches.

cs.CV↗

arXiv2025

SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

Simultaneous understanding and 3D reconstruction plays an important role in developing end-to-end embodied intelligent systems. To achieve this, recent approaches resort to 2D-to-3D feature alignment paradigm, which leads to limited 3D understanding capability and potential semantic information loss. In light of this, we propose SIU3R, the first alignment-free framework for generalizable simultaneous understanding and 3D reconstruction from unposed images. Specifically, SIU3R bridges reconstruction and understanding tasks via pixel-aligned 3D representation, and unifies multiple understanding (segmentation) tasks into a set of unified learnable queries, enabling native 3D understanding without the need of alignment with 2D models. To encourage collaboration between the two tasks with shared representation, we further conduct in-depth analyses of their mutual benefits, and propose two lightweight modules to facilitate their interaction. Extensive experiments demonstrate that our method achieves state-of-the-art performance not only on the individual tasks of 3D reconstruction and understanding, but also on the task of simultaneous understanding and 3D reconstruction, highlighting the advantages of our alignment-free framework and the effectiveness of the mutual benefit designs. Project page: https://insomniaaac.github.io/siu3r/

cs.CV↗

arXiv2025

Hybrid Quantum-Classical Neural Networks for Few-Shot Credit Risk Assessment

Quantum Machine Learning (QML) offers a new paradigm for addressing complex financial problems intractable for classical methods. This work specifically tackles the challenge of few-shot credit risk assessment, a critical issue in inclusive finance where data scarcity and imbalance limit the effectiveness of conventional models. To address this, we design and implement a novel hybrid quantum-classical workflow. The methodology first employs an ensemble of classical machine learning models (Logistic Regression, Random Forest, XGBoost) for intelligent feature engineering and dimensionality reduction. Subsequently, a Quantum Neural Network (QNN), trained via the parameter-shift rule, serves as the core classifier. This framework was evaluated through numerical simulations and deployed on the Quafu Quantum Cloud Platform's ScQ-P21 superconducting processor. On a real-world credit dataset of 279 samples, our QNN achieved a robust average AUC of 0.852 +/- 0.027 in simulations and yielded an impressive AUC of 0.88 in the hardware experiment. This performance surpasses a suite of classical benchmarks, with a particularly strong result on the recall metric. This study provides a pragmatic blueprint for applying quantum computing to data-constrained financial scenarios in the NISQ era and offers valuable empirical evidence supporting its potential in high-stakes applications like inclusive finance.

cs.LG↗