Search arXiv⌕ Search

arXiv subjects

Jiayu Li

Publications and source records attributed to Jiayu Li.

At least 55 records · Page 3Linked to original sources
arXiv2026

AttentionRetriever: Attention Layers are Secretly Long Document Retrievers

Retrieval augmented generation (RAG) has been widely adopted to help Large Language Models (LLMs) to process tasks involving long documents. However, existing retrieval models are not designed for long document retrieval and fail to address several key challenges of long document retrieval, including context-awareness, causal dependence, and scope of retrieval. In this paper, we proposed AttentionRetriever, a novel long document retrieval model that leverages attention mechanism and entity-based retrieval to build context-aware embeddings for long document and determine the scope of retrieval. With extensive experiments, we found AttentionRetriever is able to outperform existing retrieval models on long document retrieval datasets by a large margin while remaining as efficient as dense retrieval models.

cs.IR↗
arXiv2026

Modewise Additive Factor Model for Matrix Time Series

We introduce a Modewise Additive Factor Model (MAFM) for matrix-valued time series that captures row-specific and column-specific latent effects through an additive structure, offering greater flexibility than multiplicative frameworks such as Tucker and CP factor models. In MAFM, each observation decomposes into a row-factor component, a column-factor component, and noise, allowing distinct sources of variation along different modes to be modeled separately. We develop a computationally efficient two-stage estimation procedure: Modewise Inner-product Eigendecomposition (MINE) for initialization, followed by Complement-Projected Alternating Subspace Estimation (COMPAS) for iterative refinement. The key methodological innovation is that orthogonal complement projections completely eliminate cross-modal interference when estimating each loading space. We establish convergence rates for the estimated factor loading matrices under proper conditions. We further derive asymptotic distributions for the loading matrix estimators and develop consistent covariance estimators, yielding a data-driven inference framework that enables confidence interval construction and hypothesis testing. As a technical contribution of independent interest, we establish matrix Bernstein inequalities for quadratic forms of dependent matrix time series. Numerical experiments on synthetic and real data demonstrate the advantages of the proposed method over existing approaches.

stat.ME↗
arXiv2026

Quasisymmetry Enriched Gapless Criticality at Chern Insulator Transitions

In continuous topological phase transitions (CTPTs), the low-energy physics is governed by gap-closing subspaces, where approximate "higher" symmetries, termed quasisymmetries, may emerge. Here, we introduce the notion of quasisymmetry enrichment of these transitions. Focusing on paradigmatic normal-to-Chern insulator transitions, we identify quasisymmetries in the gapless subspaces, which subdivide CTPTs of the same universality class according to quasisymmetry charges. Gapless criticalities with nontrivial charges exhibit regulated phenomena, including intrinsic correlations between charge and pseudospin currents and continuous generalized Hall conductivities governed by the generalized Středa formula, both conventionally exclusive to gapped phases. These features arise as quasisymmetry forbids certain matrix elements, rendering the generalized Berry curvature integrable. By establishing quasisymmetry as a fundamental classifying ingredient, our work adds a new dimension for understanding the rich landscape of quantum phase transitions.

cond-mat.mtrl-sci↗
arXiv2026

CASPER: Concept-integrated Sparse Representation for Scientific Retrieval

Identifying relevant research concepts is crucial for effective scientific search. However, primary sparse retrieval methods often lack concept-aware representations. To address this, we propose CASPER, a sparse retrieval model for scientific search that utilizes both tokens and keyphrases as representation units (i.e., dimensions in the sparse embedding space). This enables CASPER to represent queries and documents via research concepts and match them at both granular and conceptual levels. Furthermore, we construct training data by leveraging abundant scholarly references (including titles, citation contexts, author-assigned keyphrases, and co-citations), which capture how research concepts are expressed in diverse settings. Empirically, CASPER outperforms strong dense and sparse retrieval baselines across eight scientific retrieval benchmarks. We also explore the effectiveness-efficiency trade-off via representation pruning and demonstrate CASPER's interpretability by showing that it can serve as an effective and efficient keyphrase generation model.

cs.IR↗
arXiv2026

LLM Agents in Law: Taxonomy, Applications, and Challenges

Large language models (LLMs) have precipitated a dramatic improvement in the legal domain, yet the deployment of standalone models faces significant limitations regarding hallucination, outdated information, and verifiability. Recently, LLM agents have attracted significant attention as a solution to these challenges, utilizing advanced capabilities such as planning, memory, and tool usage to meet the rigorous standards of legal practice. In this paper, we present a comprehensive survey of LLM agents for legal tasks, analyzing how these architectures bridge the gap between technical capabilities and domain-specific needs. Our major contributions include: (1) systematically analyzing the technical transition from standard legal LLMs to legal agents; (2) presenting a structured taxonomy of current agent applications across distinct legal practice areas; (3) discussing evaluation methodologies specifically for agentic performance in law; and (4) identifying open challenges and outlining future directions for developing robust and autonomous legal assistants.

cs.CY↗
arXiv2025

Hierarchy-Aware Fine-Tuning of Vision-Language Models

Vision-Language Models (VLMs) learn powerful multimodal representations through large-scale image-text pretraining, but adapting them to hierarchical classification is underexplored. Standard approaches treat labels as flat categories and require full fine-tuning, which is expensive and produces inconsistent predictions across taxonomy levels. We propose an efficient hierarchy-aware fine-tuning framework that updates a few parameters while enforcing structural consistency. We combine two objectives: Tree-Path KL Divergence (TP-KL) aligns predictions along the ground-truth label path for vertical coherence, while Hierarchy-Sibling Smoothed Cross-Entropy (HiSCE) encourages consistent predictions among sibling classes. Both losses work in the VLM's shared embedding space and integrate with lightweight LoRA adaptation. Experiments across multiple benchmarks show consistent improvements in Full-Path Accuracy and Tree-based Inconsistency Error with minimal parameter overhead. Our approach provides an efficient strategy for adapting VLMs to structured taxonomies.

cs.CV↗
arXiv2025

IRG: Modular Synthetic Relational Database Generation with Complex Relational Schemas

Relational databases (RDBs) are widely used by corporations and governments to store multiple related tables. Their relational schemas pose unique challenges to synthetic data generation for privacy-preserving data sharing, e.g., for collaborative analytical and data mining tasks, as well as software testing at various scales. Relational schemas typically include a set of primary and foreign key constraints to specify the intra-and inter-table entity relations, which also imply crucial intra-and inter-table data correlations in the RDBs. Existing synthetic RDB generation approaches often focus on the relatively simple and basic parent-child relations, failing to address the ubiquitous real-world complexities in relational schemas in key constraints like composite keys, intra-table correlations like sequential correlation, and inter-table data correlations like indirectly connected tables. In this paper, we introduce incremental relational generator (IRG), a modular framework designed to handle these real-world challenges. In IRG, each table is generated by learning context from a depth-first traversal of relational connections to capture indirect inter-table relationships and constructs different parts of a table through several classical generative and predictive modules to preserve complex key constraints and data correlations. Compared to 3 prior art algorithms across 10 real-world RDB datasets, IRG successfully handles the relational schemas and captures critical data relationships for all datasets while prior works are incapable of. The generated synthetic data also demonstrates better fidelity and utility than prior works, implying its higher potential as a replacement for the basis of analytical tasks and data mining applications. Code is available at: https://github.com/li-jiayu-ljy/irg.

cs.DB↗
arXiv2025

High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees

High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on sparsity or Tucker structures and often lack theoretical guarantees. Motivated by empirical evidence that discriminative signals concentrate along a few multilinear components, we introduce CP low-rank structure for the discriminant tensor, a modeling perspective not previously explored. Under a Tensor Gaussian Mixture Model, we propose high-dimensional CP low-rank Tensor Discriminant Analysis (CP-TDA) with Randomized Composite PCA (\textsc{rc-PCA}) initialization, that is essential for handling dependent and anisotropic noise under weaker signal strength and incoherence conditions, followed by iterative refinement algorithm. We establish global convergence and minimax-optimal misclassification rates. To handle tensor data deviating from tensor normality, we develop the first semiparametric tensor discriminant model, in which learned tensor representations are mapped via deep generative models into a latent space tailored for CP-TDA. Misclassification risk decomposes into representation, approximation, and estimation errors. Numerical studies and real data analysis on graph classification demonstrate substantial gains over existing tensor classifiers and state-of-the-art graph neural networks, particularly in high-dimensional, small-sample regimes.

cs.LG↗
arXiv2025

TAEGAN: Generating Synthetic Tabular Data For Data Augmentation

Synthetic tabular data generation has gained significant attention for its potential in data augmentation and privacy-preserving data sharing. While recent methods like diffusion and auto-regressive models (i.e., transformer) have advanced the field, generative adversarial networks (GANs) remain highly competitive due to their training efficiency and strong data generation capabilities. In this paper, we introduce Tabular Auto-Encoder Generative Adversarial Network (TAEGAN), a novel GAN-based framework that leverages a masked auto-encoder as the generator. TAEGAN is the first to incorporate self-supervised warmup training of generator into tabular GANs. It enhances GAN stability and exposes the generator to richer information beyond the discriminator's feedback. Additionally, we propose a novel sampling method tailored for imbalanced or skewed data and an improved loss function to better capture data distribution and correlations. We evaluate TAEGAN against seven state-of-the-art synthetic tabular data generation algorithms. Results from eight datasets show that TAEGAN outperforms all baselines on five datasets, achieving a 27% overall utility boost over the best-performing baseline while maintaining a model size less than 5% of the best-performing baseline model. Code is available at: https://github.com/BetterdataLabs/taegan.

cs.LG↗
arXiv2025

Towards Irreversible Machine Unlearning for Diffusion Models

Diffusion models are renowned for their state-of-the-art performance in generating synthetic images. However, concerns related to safety, privacy, and copyright highlight the need for machine unlearning, which can make diffusion models forget specific training data and prevent the generation of sensitive or unwanted content. Current machine unlearning methods for diffusion models are primarily designed for conditional diffusion models and focus on unlearning specific data classes or features. Among these methods, finetuning-based machine unlearning methods are recognized for their efficiency and effectiveness, which update the parameters of pre-trained diffusion models by minimizing carefully designed loss functions. However, in this paper, we propose a novel attack named Diffusion Model Relearning Attack (DiMRA), which can reverse the finetuning-based machine unlearning methods, posing a significant vulnerability of this kind of technique. Without prior knowledge of the unlearning elements, DiMRA optimizes the unlearned diffusion model on an auxiliary dataset to reverse the unlearning, enabling the model to regenerate previously unlearned elements. To mitigate this vulnerability, we propose a novel machine unlearning method for diffusion models, termed as Diffusion Model Unlearning by Memorization (DiMUM). Unlike traditional methods that focus on forgetting, DiMUM memorizes alternative data or features to replace targeted unlearning data or features in order to prevent generating such elements. In our experiments, we demonstrate the effectiveness of DiMRA in reversing state-of-the-art finetuning-based machine unlearning methods for diffusion models, highlighting the need for more robust solutions. We extensively evaluate DiMUM, demonstrating its superior ability to preserve the generative performance of diffusion models while enhancing robustness against DiMRA.

cs.LG↗
arXiv2025

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models

Vision-Language-Action (VLA) models enable robots to interpret natural-language instructions and perform diverse tasks, yet their integration of perception, language, and control introduces new safety vulnerabilities. Despite growing interest in attacking such models, the effectiveness of existing techniques remains unclear due to the absence of a unified evaluation framework. One major issue is that differences in action tokenizers across VLA architectures hinder reproducibility and fair comparison. More importantly, most existing attacks have not been validated in real-world scenarios. To address these challenges, we propose AttackVLA, a unified framework that aligns with the VLA development lifecycle, covering data construction, model training, and inference. Within this framework, we implement a broad suite of attacks, including all existing attacks targeting VLAs and multiple adapted attacks originally developed for vision-language models, and evaluate them in both simulation and real-world settings. Our analysis of existing attacks reveals a critical gap: current methods tend to induce untargeted failures or static action states, leaving targeted attacks that drive VLAs to perform precise long-horizon action sequences largely unexplored. To fill this gap, we introduce BackdoorVLA, a targeted backdoor attack that compels a VLA to execute an attacker-specified long-horizon action sequence whenever a trigger is present. We evaluate BackdoorVLA in both simulated benchmarks and real-world robotic settings, achieving an average targeted success rate of 58.4% and reaching 100% on selected tasks. Our work provides a standardized framework for evaluating VLA vulnerabilities and demonstrates the potential for precise adversarial manipulation, motivating further research on securing VLA-based embodied systems.

cs.CR↗
arXiv2025

Linear Poisson Equations with Potential on Riemann Surfaces

We study interior estimates for solutions of the linear Poisson equation: $$ \triangle u = g u + f $$ where $g$ and $f$ belong to the Zygmund space $L\ln L$ on a Riemann surface $M$ satisfying the isoperimetric inequality. As applications, we derive corresponding interior estimates, Harnack inequalities, and a global estimate.

math.DG↗
arXiv2025

Time-Varying Factor-Augmented Models for Volatility Forecasting

Accurate volatility forecasts are vital in modern finance for risk management, portfolio allocation, and strategic decision-making. However, existing methods face key limitations. Fully multivariate models, while comprehensive, are computationally infeasible for realistic portfolios. Factor models, though efficient, primarily use static factor loadings, failing to capture evolving volatility co-movements when they are most critical. To address these limitations, we propose a novel, model-agnostic Factor-Augmented Volatility Forecast framework. Our approach employs a time-varying factor model to extract a compact set of dynamic, cross-sectional factors from realized volatilities with minimal computational cost. These factors are then integrated into both statistical and AI-based forecasting models, enabling a unified system that jointly models asset-specific dynamics and evolving market-wide co-movements. Our framework demonstrates strong performance across two prominent asset classes-large-cap U.S. technology equities and major cryptocurrencies-over both short-term (1-day) and medium-term (7-day) horizons. Using a suite of linear and non-linear AI-driven models, we consistently observe substantial improvements in predictive accuracy and economic value. Notably, a practical pairs-trading strategy built on our forecasts delivers superior risk-adjusted returns and profitability, particularly under adverse market conditions.

q-fin.ST↗
arXiv2025

ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation

Missing data in financial panels presents a critical obstacle, undermining asset-pricing models and reducing the effectiveness of investment strategies. Such panels are often inherently multi-dimensional, spanning firms, time, and financial variables, which adds complexity to the imputation task. Conventional imputation methods often fail by flattening the data's multidimensional structure, struggling with heterogeneous missingness patterns, or overfitting in the face of extreme data sparsity. To address these limitations, we introduce an Adaptive, Cluster-based Temporal smoothing tensor completion framework (ACT-Tensor) tailored for severely and heterogeneously missing multi-dimensional financial data panels. ACT-Tensor incorporates two key innovations: a cluster-based completion module that captures cross-sectional heterogeneity by learning group-specific latent structures; and a temporal smoothing module that proactively removes short-lived noise while preserving slow-moving fundamental trends. Extensive experiments show that ACT-Tensor consistently outperforms state-of-the-art benchmarks in terms of imputation accuracy across a range of missing data regimes, including extreme sparsity scenarios. To assess its practical financial utility, we evaluate the imputed data with an asset-pricing pipeline tailored for tensor-structured financial data. Results show that ACT-Tensor not only reduces pricing errors but also significantly improves risk-adjusted returns of the constructed portfolio. These findings confirm that our method delivers highly accurate and informative imputations, offering substantial value for financial decision-making.

stat.AP↗
arXiv2025

The quantitative behavior of $α$-Yang-Mills-Higgs fields on surfaces

We investigate the blow-up behavior of $α$-Yang--Mills--Higgs ($α$-YMH) fields over closed Riemannian surfaces with the target fiber $F = S^{K-1} \subset \mathbb{R}^K$ being the round sphere, focusing on the establishment of the $α$-energy identity and the no-neck property during the bubbling process. A central innovation is the identification of a hidden Jacobian structure through Hodge decomposition and a new conservation law. Furthermore, we derive a Pohozaev-type identity for $α$-YMH fields, which enables refined control of the energy density. Together, these advances ensure the validity of the $α$-energy identity as $α\to 1$. Our analysis further sharpens the Lorentz space estimates from the $L^{2,\infty}$ to the optimal $L^{2,1}$ scale, ultimately yielding the no-neck property in the blow-up regime. These results provide a unified and quantitative framework for understanding singularity formation in variational gauge theories.

math.DG↗
arXiv2025

Are Recommenders Self-Aware? Label-Free Recommendation Performance Estimation via Model Uncertainty

Can a recommendation model be self-aware? This paper investigates the recommender's self-awareness by quantifying its uncertainty, which provides a label-free estimation of its performance. Such self-assessment can enable more informed understanding and decision-making before the recommender engages with any users. To this end, we propose an intuitive and effective method, probability-based List Distribution uncertainty (LiDu). LiDu measures uncertainty by determining the probability that a recommender will generate a certain ranking list based on the prediction distributions of individual items. We validate LiDu's ability to represent model self-awareness in two settings: (1) with a matrix factorization model on a synthetic dataset, and (2) with popular recommendation algorithms on real-world datasets. Experimental results show that LiDu is more correlated with recommendation performance than a series of label-free performance estimators. Additionally, LiDu provides valuable insights into the dynamic inner states of models throughout training and inference. This work establishes an empirical connection between recommendation uncertainty and performance, framing it as a step towards more transparent and self-evaluating recommender systems.

cs.IR↗
arXiv2025

AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning

Fine-tuning large language models (LLMs) for specific tasks requires diverse, high-quality training data. However, obtaining sufficient relevant data remains a significant challenge. Existing data synthesis methods either depend on extensive seed datasets or struggle to balance task relevance and data diversity. To address these challenges, we propose Attribute-guided multI-hop Data Expansion (AIDE), a novel data synthesis framework that uses a multi-hop process to expand very few seed data points while ensuring data diversity and task relevance. AIDE extracts the main topic and key knowledge attributes from the seeds to guide the synthesis steps. The process repeats for K hops, using the generated data as seeds. To prevent irrelevant data generation as the hop depth increases, AIDE incorporates a residual connection mechanism. Our empirical results show that AIDE enables fine-tuning of Mistral-7B, Llama-3.1-8B and Llama-3.2-3B from 10 seeds, surpassing the models fine-tuned on human curated data. Furthermore, AIDE outperforms state-of-the-art data synthesis methods, such as Evol-Instruct, by over 30% in task-specific fine-tuning. Code is available at https://github.com/Code4Graph/AIDE.

cs.CL↗