arXiv subjects

Jiajie Zhu

Publications and source records attributed to Jiajie Zhu.

13 recordsLinked to original sources

arXiv2026

GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models

Tabular foundation models (TFMs) achieve strong performance through in-context learning, but context-dependent inference imposes substantial latency and memory costs, hindering large-scale deployment. We propose GEAR (\emph{Generative Expansion and Real Anchoring}), a modular two-stage framework that distills TFMs into lightweight MLP or tree-based predictors that can be deployed on commodity CPUs. Stage 1 uses synthetic covariates solely as teacher-query locations and trains the student on soft TFM targets, expanding coverage beyond observed rows. Stage 2 re-anchors the student to the target distribution using real labels and out-of-fold teacher predictions, whitch avoids self-labeling leakage. We further derive a risk certificate characterizing the trade-off between generated-query volume and generator fidelity. Experiments on TALENT and TabArena demonstrate the broad applicability of GEAR. Two-stage MLPs outperform supervised MLPs by 1.81--2.00 AUC points on binary tasks and 1.19--1.35 points on multiclass tasks, with additional gains over real-data-only distillation of 1.76--2.19 and 2.09--2.40 points, respectively. On binary tasks, the gains also transfer to LightGBM and XGBoost, and all three student families outperform CatBoost, the strongest non-TFM baseline, in mean AUC. Ablations show gains beyond longer training or alternative warm starts, greater stability from staged than mixed optimization, and generator-dependent diminishing returns as query volume increases. Finally, GEAR reduces median inference time by 57--2866 times and peak prediction memory by 1.9--3.3 times, while retaining higher AUC than matched supervised baselines.

cs.LG↗

arXiv2026

Causal-Invariant Cross-Domain Out-of-Distribution Recommendation

Cross-Domain Recommendation (CDR) aims to leverage knowledge from a relatively data-richer source domain to address the data sparsity problem in a relatively data-sparser target domain. While CDR methods need to address the distribution shifts between different domains, i.e., cross-domain distribution shifts (CDDS), they typically assume independent and identical distribution (IID) between training and testing data within the target domain. However, this IID assumption rarely holds in real-world scenarios due to single-domain distribution shift (SDDS). The above two co-existing distribution shifts lead to out-of-distribution (OOD) environments that hinder effective knowledge transfer and generalization, ultimately degrading recommendation performance in CDR. To address these co-existing distribution shifts, we propose a novel Causal-Invariant Cross-Domain Out-of-distribution Recommendation framework, called CICDOR. In CICDOR, we first learn dual-level causal structures to infer domain-specific and domain-shared causal-invariant user preferences for tackling both CDDS and SDDS under OOD environments in CDR. Then, we propose an LLM-guided confounder discovery module that seamlessly integrates LLMs with a conventional causal discovery method to extract observed confounders for effective deconfounding, thereby enabling accurate causal-invariant preference inference. Extensive experiments on two real-world datasets demonstrate the superior recommendation accuracy of CICDOR over state-of-the-art methods across various OOD scenarios.

cs.IR↗

arXiv2026

LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models

Instruction following is critical for large language models, yet real-world instructions often involve multiple constraints with logical structures, such as parallel composition, sequential dependencies, and conditional branching. Existing methods typically construct data by simply combining constraints and aggregate rewards by averaging individual constraint scores during training, overlooking logical dependencies and introducing noisy signals. We propose LsrIF, a training framework for logic-structured instruction following. LsrIF constructs data by organizing atomic constraints into parallel, sequential, conditional, and nested structures, and applies structure-aware reward aggregation aligned with their execution semantics: averaging rewards for parallel constraints, decaying later rewards after early failures in sequential structures, and rewarding only active branches in conditional structures. Experiments show that LsrIF improves instruction following in both in-domain and out-of-domain settings while also benefiting logic reasoning. Further analysis indicates that logic-structured training increases attention to constraint-related tokens and logical connectors, suggesting improved modeling of instruction logic. We will release our data and code for future research.

cs.AI↗

arXiv2026

SEIF: Self-Evolving Reinforcement Learning for Instruction Following

Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Existing methods typically rely either on costly external supervision from humans or strong teacher models, or on self-play training with static-difficulty instructions that cannot evolve as the model's capabilities improve. To address these limitations, we propose SEIF (Self-Evolving Reinforcement Learning for Instruction Following), a self-evolving framework for enhancing the instruction-following ability of LLMs. SEIF forms a closed self-evolution loop that improves the model's instruction-following ability, where instruction difficulty evolution and model capability evolution reinforce each other. SEIF consists of four roles: an Instructor that generates increasingly challenging instructions, a Filter that removes conflicting or invalid instructions to ensure data quality, a Follower that learns to follow evolved instructions, and a Judger that provides reward signals for reinforcement learning. The Instructor and Follower are alternately trained and co-evolve throughout the process. Experiments across multiple model scales and architectures show that SEIF consistently improves instruction-following performance, suggesting strong generality. Further analyses reveal the sources of improvement and identify an effective training strategy for self-evolution on open-ended tasks: sufficient early-stage training to build a solid foundation, followed by moderate late-stage training to mitigate overfitting and achieve better final performance. The code and data are publicly available at https://github.com/Rainier-rq1/SEIF.

cs.CL↗

arXiv2026

Cross-Domain Fake News Detection on Unseen Domains via LLM-Based Domain-Aware User Modeling

Cross-domain fake news detection (CD-FND) transfers knowledge from a source domain to a target domain and is crucial for real-world fake news mitigation. This task becomes particularly important yet more challenging when the target domain is previously unseen (e.g., the COVID-19 outbreak or the Russia-Ukraine war). However, existing CD-FND methods overlook such scenarios and consequently suffer from the following two key limitations: (1) insufficient modeling of high-level semantics in news and user engagements; and (2) scarcity of labeled data in unseen domains. Targeting these limitations, we find that large language models (LLMs) offer strong potential for CD-FND on unseen domains, yet their effective use remains non-trivial. Nevertheless, two key challenges arise: (1) how to capture high-level semantics from both news content and user engagements using LLMs; and (2) how to make LLM-generated features more reliable and transferable for CD-FND on unseen domains. To tackle these challenges, we propose DAUD, a novel LLM-Based Domain-Aware framework for fake news detection on Unseen Domains. DAUD employs LLMs to extract high-level semantics from news content. It models users' single- and cross-domain engagements to generate domain-aware behavioral representations. In addition, DAUD captures the relations between original data-driven features and LLM-derived features of news, users, and user engagements. This allows it to extract more reliable domain-shared representations that improve knowledge transfer to unseen domains. Extensive experiments on real-world datasets demonstrate that DAUD outperforms state-of-the-art baselines in both general and unseen-domain CD-FND settings.

cs.SI↗

arXiv2026

Diagnostic-Guided Dynamic Profile Optimization for LLM-based User Simulators in Sequential Recommendation

Recent advances in large language models (LLMs) have enabled realistic user simulators for developing and evaluating recommender systems (RSs). However, existing LLM-based simulators for RSs face two major limitations: (1) static and single-step prompt-based inference that leads to inaccurate and incomplete user profile construction; (2) unrealistic and single-round recommendation-feedback interaction pattern that fails to capture real-world scenarios. To address these limitations, we propose DGDPO (Diagnostic-Guided Dynamic Profile Optimization), a novel framework that constructs user profile through a dynamic and iterative optimization process to enhance the simulation fidelity. Specifically, DGDPO incorporates two core modules within each optimization loop: firstly, a specialized LLM-based diagnostic module, calibrated through our novel training strategy, accurately identifies specific defects in the user profile. Subsequently, a generalized LLM-based treatment module analyzes the diagnosed defect and generates targeted suggestions to refine the profile. Furthermore, unlike existing LLM-based user simulators that are limited to single-round interactions, we are the first to integrate DGDPO with sequential recommenders, enabling a bidirectional evolution where user profiles and recommendation strategies adapt to each other over multi-round interactions. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness of our proposed framework.

cs.IR↗

arXiv2026

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection

The rapid advancements in artificial intelligence have significantly accelerated the adoption of speech recognition technology, leading to its widespread integration across various applications. However, this surge in usage also highlights a critical issue: audio data is highly vulnerable to unauthorized exposure and analysis, posing significant privacy risks for businesses and individuals. This paper introduces an Information-Obfuscation Reversible Adversarial Example (IO-RAE) framework, the pioneering method designed to safeguard audio privacy using reversible adversarial examples. IO-RAE leverages large language models to generate misleading yet contextually coherent content, effectively preventing unauthorized eavesdropping by humans and Automatic Speech Recognition (ASR) systems. Additionally, we propose the Cumulative Signal Attack technique, which mitigates high-frequency noise and enhances attack efficacy by targeting low-frequency signals. Our approach ensures the protection of audio data without degrading its quality or our ability. Experimental evaluations demonstrate the superiority of our method, achieving a targeted misguidance rate of 96.5% and a remarkable 100% untargeted misguidance rate in obfuscating target keywords across multiple ASR models, including a commercial black-box system from Google. Furthermore, the quality of the recovered audio, measured by the Perceptual Evaluation of Speech Quality score, reached 4.45, comparable to high-quality original recordings. Notably, the recovered audio processed by ASR systems exhibited an error rate of 0%, indicating nearly lossless recovery. These results highlight the practical applicability and effectiveness of our IO-RAE framework in protecting sensitive audio privacy.

cs.SD↗

arXiv2025

Causal Deconfounding via Confounder Disentanglement for Dual-Target Cross-Domain Recommendation

In recent years, dual-target Cross-Domain Recommendation (CDR) has been proposed to capture comprehensive user preferences in order to ultimately enhance the recommendation accuracy in both data-richer and data-sparser domains simultaneously. However, in addition to users' true preferences, the user-item interactions might also be affected by confounders (e.g., free shipping, sales promotion). As a result, dual-target CDR has to meet two challenges: (1) how to effectively decouple observed confounders, including single-domain confounders and cross-domain confounders, and (2) how to preserve the positive effects of observed confounders on predicted interactions, while eliminating their negative effects on capturing comprehensive user preferences. To address the above two challenges, we propose a Causal Deconfounding framework via Confounder Disentanglement for dual-target Cross-Domain Recommendation, called CD2CDR. In CD2CDR, we first propose a confounder disentanglement module to effectively decouple observed single-domain and cross-domain confounders. We then propose a causal deconfounding module to preserve the positive effects of such observed confounders and eliminate their negative effects via backdoor adjustment, thereby enhancing the recommendation accuracy in each domain. Extensive experiments conducted on seven real-world datasets demonstrate that CD2CDR significantly outperforms the state-of-the-art methods.

cs.IR↗

arXiv2025

Adaptive Graph Unlearning

Graph unlearning, which deletes graph elements such as nodes and edges from trained graph neural networks (GNNs), is crucial for real-world applications where graph data may contain outdated, inaccurate, or privacy-sensitive information. However, existing methods often suffer from (1) incomplete or over unlearning due to neglecting the distinct objectives of different unlearning tasks, and (2) inaccurate identification of neighbors affected by deleted elements across various GNN architectures. To address these limitations, we propose AGU, a novel Adaptive Graph Unlearning framework that flexibly adapts to diverse unlearning tasks and GNN architectures. AGU ensures the complete forgetting of deleted elements while preserving the integrity of the remaining graph. It also accurately identifies affected neighbors for each GNN architecture and prioritizes important ones to enhance unlearning performance. Extensive experiments on seven real-world graphs demonstrate that AGU outperforms existing methods in terms of effectiveness, efficiency, and unlearning capability.

cs.LG↗

arXiv2025

DP-TRAE: A Dual-Phase Merging Transferable Reversible Adversarial Example for Image Privacy Protection

In the field of digital security, Reversible Adversarial Examples (RAE) combine adversarial attacks with reversible data hiding techniques to effectively protect sensitive data and prevent unauthorized analysis by malicious Deep Neural Networks (DNNs). However, existing RAE techniques primarily focus on white-box attacks, lacking a comprehensive evaluation of their effectiveness in black-box scenarios. This limitation impedes their broader deployment in complex, dynamic environments. Further more, traditional black-box attacks are often characterized by poor transferability and high query costs, significantly limiting their practical applicability. To address these challenges, we propose the Dual-Phase Merging Transferable Reversible Attack method, which generates highly transferable initial adversarial perturbations in a white-box model and employs a memory augmented black-box strategy to effectively mislead target mod els. Experimental results demonstrate the superiority of our approach, achieving a 99.0% attack success rate and 100% recovery rate in black-box scenarios, highlighting its robustness in privacy protection. Moreover, we successfully implemented a black-box attack on a commercial model, further substantiating the potential of this approach for practical use.

cs.CR↗

arXiv2023

Large-area, freestanding single-crystal gold of single nanometer thickness

Two-dimensional single-crystal metals are highly sought after for next-generation technologies. Here, we report large-area (>10^4 μm2), single-crystal two-dimensional gold with thicknesses down to a single-nanometer level, employing an atomic-level-precision chemical etching approach. The ultrathin thickness and single-crystal quality endow two-dimensional gold with unique properties including significantly quantum-confinement-augmented optical nonlinearity, low sheet resistance, high transparency and excellent mechanical flexibility. By patterning the two-dimensional gold into nanoribbon arrays, extremely-confined near-infrared plasmonic resonances are further demonstrated with quality factors up to 5. The freestanding nature of two-dimensional gold allows its straightforward manipulation and transfer-printing for integration with other structures. The developed two-dimensional gold provides an emerging platform for fundamental studies in various disciplines and opens up new opportunities for applications in high-performance ultrathin optoelectronic, photonic and quantum devices.

physics.optics↗

arXiv2023

Domain Disentanglement with Interpolative Data Augmentation for Dual-Target Cross-Domain Recommendation

The conventional single-target Cross-Domain Recommendation (CDR) aims to improve the recommendation performance on a sparser target domain by transferring the knowledge from a source domain that contains relatively richer information. By contrast, in recent years, dual-target CDR has been proposed to improve the recommendation performance on both domains simultaneously. However, to this end, there are two challenges in dual-target CDR: (1) how to generate both relevant and diverse augmented user representations, and (2) how to effectively decouple domain-independent information from domain-specific information, in addition to domain-shared information, to capture comprehensive user preferences. To address the above two challenges, we propose a Disentanglement-based framework with Interpolative Data Augmentation for dual-target Cross-Domain Recommendation, called DIDA-CDR. In DIDA-CDR, we first propose an interpolative data augmentation approach to generating both relevant and diverse augmented user representations to augment sparser domain and explore potential user preferences. We then propose a disentanglement module to effectively decouple domain-specific and domain-independent information to capture comprehensive user preferences. Both steps significantly contribute to capturing more comprehensive user preferences, thereby improving the recommendation performance on each domain. Extensive experiments conducted on five real-world datasets show the significant superiority of DIDA-CDR over the state-of-the-art methods.

cs.IR↗

arXiv2019

A Decentralized Multi-block ADMM for Demand-side Primary Frequency Control using Local Frequency Measurements

We consider demand-side primary frequency control in the power grid provided by smart and flexible loads: loads change consumption to match generation and help the grid while minimizing disutility for consumers incurred by consumption changes. The dual formulation of this problem has been solved previously by Zhao et al. in a decentralized manner for consumer disutilities that are twice continuously differentiable with respect to consumption changes. In this work, we propose a decentralized multi-block alternating-direction-method-of-multipliers (DM-ADMM) algorithm to solve this problem. In contrast to the dual ascent algorithm of Zhao et al., the proposed DM-ADMM algorithm does not require the disutilities to be continuously differentiable; this allows disutility functions that model consumer behavior that may be quite common. In this work, we prove convergence of the DM-ADMM algorithm in the deterministic setting (i.e., when loads may estimate the consumption-generation mismatch from frequency measurements exactly). We test the performance of the DM-ADMM algorithm in simulations, and we compare (when applicable) with the previously proposed solution for the dual formulation. We also present numerical results for a previously proposed ADMM algorithm, whose results were not previously reported.

math.OC↗