arXiv subjects

Xinyun Liu

Publications and source records attributed to Xinyun Liu.

11 recordsLinked to original sources

arXiv2026

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

Federated learning (FL) is vulnerable to multi-level attacks. However, existing methods address them separately, leaving FL exposed to data leakage, unauthorized reuse, and malicious gradient manipulation. In this work, we propose an FL framework that couples keyed context-provenance watermarking with verifiable lattice-based secure aggregation of Real-World Anchored Watermarking and Lattice-Based Zero-Knowledge Secure Aggregation. At the data layer, we propose a Kerckhoffs-compliant scheme that utilizes Physical Anchor Metadata (PAM) to ensure data provenance. PAM is defined as a context-provenance token derived from trusted infrastructure data (time, location, and server ID) and then subjected to a keyed HMAC-SHA-256 transformation to produce a watermark payload that cannot be generated without the client's secret key. We further design FMGAN, a GAN-based robust image watermarking framework that embeds this transformed payload using a feature fusion module and a Mamba-guided linear attention mechanism. At the computation layer, we adopt a lattice-based zero-knowledge secure aggregation (LZKSA) protocol that verifies key correctness, L2 norm bounds, and cosine similarity constraints over committed gradients without revealing private updates. The RLWE-based design guarantees post-quantum security. Extensive experiments validate the complementary protection of the two layers under composite attack scenarios. To our knowledge, no prior verification workflow has jointly evaluated both layers in a hybrid, end-to-end trustworthy FL framework.

cs.CR↗

arXiv2026

Agentic AI-driven Immersive Simulation: A Knowledge-Aware Virtual Training Platform forHigh Dose Rate (HDR) Brachytherapy

The convergence of the Metaverse and Large Language Model (LLM)-based AI agent is catalyzing a shift toward autonomous, immersive, and personalized pedagogical frameworks in medical education. This paper presents a novel agentic AI-driven immersive simulation specifically designed for High Dose Rate (HDR) vaginal cylinder (VC) brachytherapy in cancer care. By integrating Virtual Reality (VR) and mobile computing, the system establishes a high-fidelity, risk-free environment that allows trainees to master complex procedural skills without the facility or safety constraints posed by physical anatomy or live radioactive sources. A core contribution of this work is the seamless integration of a knowledge-aware assistant leveraging Retrieval-Augmented Generation (RAG) to ground agent interactions in authoritative clinical guidelines. This architecture also enables an interactive agent to provide natural language interfaces and hands-free, real-time guidance during intricate medical maneuvers. We validate the proposed system through a prototype deployment comprising a Meta Quest 3 interface linked to a local GPU-accelerated AI backend, demonstrating a feasible architecture for HDR brachytherapy simulation. Experimental results indicate that the system maintains suitable end-to-end latency and high context precision, answer completeness, and relevance in the RAG-enhanced pedagogical support.

cs.AI↗

arXiv2026

HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language Models

Large vision-language models (LVLMs) achieve strong multimodal performance, but still suffer from hallucinations caused by unstable visual grounding and over-reliance on language priors. Existing training-free decoding methods typically apply calibration at every decoding step, introducing unnecessary computation and potentially disrupting stable predictions. We address this problem by identifying layer-wise hesitation, a simple signal of grounding instability reflected by fluctuations in token preference across intermediate layers. Based on this observation, we propose Hesitation-Triggered Differential Calibration (HTDC), a training-free decoding framework that preserves standard full-branch inference and activates calibration only at hesitation-prone steps. When triggered, HTDC contrasts the full branch with two lightweight probes, a visual-nullification probe and a semantic-nullification probe, to suppress hallucination-prone candidates while avoiding unnecessary intervention on stable steps. Experiments on representative hallucination benchmarks show that HTDC consistently reduces hallucinations while maintaining strong task accuracy, achieving a favorable trade-off between effectiveness and computational overhead.

cs.CV↗

arXiv2026

When Cubic Is Not Isotropic: Phonon-Exciton Decoupling in CuInSnS$_4$ Single Crystals

Atomic-scale disorder can create hidden optical anisotropy even in crystals that are structurally cubic on average. Here, we show that CuInSnS$_4$ single crystals host locally symmetry-broken environments arising from intrinsic In/Sn cation disorder, which affect vibrational and excitonic properties in markedly different ways. Combining polarization- and temperature-dependent Raman spectroscopy, infrared near-field microscopy, steady-state and time-resolved photoluminescence, and first-principles calculations, we find that phonons remain largely symmetry-averaged and locally homogeneous on the nanoscale. In contrast, photoluminescence reveals a lower-energy band-tail emission with pronounced polarization anisotropy following a well-defined angular symmetry, highlighting the strong sensitivity of excitonic states to local symmetry breaking. This phonon-exciton decoupling reveals that intrinsic disorder can localize excitons while preserving vibrational coherence and dielectric homogeneity, thereby opening new opportunities for polarization-sensitive light sources, anisotropic photodetectors, and exciton-based optical functionalities even in nominally cubic multinary semiconductors.

cond-mat.mtrl-sci↗

arXiv2026

GazeSummary: Exploring Gaze as an Implicit Prompt for Personalization in Text-based LLM Tasks

Smart glasses are accelerating progress toward more seamless and personalized LLM-based assistance by integrating multimodal inputs. Yet, these inputs rely on obtrusive explicit prompts. The advent of gaze tracking on smart devices offers a unique opportunity to extract implicit user intent for personalization. This paper investigates whether LLMs can interpret user gaze for text-based tasks. We evaluate different gaze representations for personalization and validate their effectiveness in realistic reading tasks. Results show that LLMs can leverage gaze to generate high-quality personalized summaries and support users in downstream tasks, highlighting the feasibility and value of gaze-driven personalization for future mobile and wearable LLM applications.

cs.HC↗

arXiv2025

Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment

Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for shortest path: we need generalization from synthetic graph data to real-world tasks with implicit graph structures. In this work, we propose to unlock generalizable learning of graph with post-training alignment with synthetic data. We first design solution-based and process-based rewards for synthetic graph problems: instead of rigid memorizing response patterns in direct fine-tuning, we posit that post-training alignment would help LLMs grasp the essentials underlying graph reasoning and alleviate overfitting on synthetic data. We employ post-training alignment algorithms such as GRPO and DPO, aligning both off-the-shelf LLMs and LLMs fine-tuned on synthetic graph data. We then compare them against existing settings on both in-domain synthetic tasks and out-of-domain real-world tasks with implicit graph structures such as multi-hop QA, structured planning, and more. Extensive experiments demonstrate that our post-training alignment recipe leads to statistically significant improvement on 5 datasets, with an average gain of 12.9% over baseline settings. Further analysis reveals that process-based rewards consistently outperform solution-based rewards on synthetic data but not on real-world tasks, and compositionality and explainable intermediate steps remains a critical challenge even after post-training alignment.

cs.LG↗

arXiv2025

Unknown Word Detection for English as a Second Language (ESL) Learners Using Gaze and Pre-trained Language Models

English as a Second Language (ESL) learners often encounter unknown words that hinder their text comprehension. Automatically detecting these words as users read can enable computing systems to provide just-in-time definitions, synonyms, or contextual explanations, thereby helping users learn vocabulary in a natural and seamless manner. This paper presents EyeLingo, a transformer-based machine learning method that predicts the probability of unknown words based on text content and eye gaze trajectory in real time with high accuracy. A 20-participant user study revealed that our method can achieve an accuracy of 97.6%, and an F1-score of 71.1%. We implemented a real-time reading assistance prototype to show the effectiveness of EyeLingo. The user study shows improvement in willingness to use and usefulness compared to baseline methods.

cs.HC↗

arXiv2024

AGFA-Net: Attention-Guided and Feature-Aggregated Network for Coronary Artery Segmentation using Computed Tomography Angiography

Coronary artery disease (CAD) remains a prevalent cardiovascular condition, posing significant health risks worldwide. This pathology, characterized by plaque accumulation in coronary artery walls, leads to myocardial ischemia and various symptoms, including chest pain and shortness of breath. Accurate segmentation of coronary arteries from coronary computed tomography angiography (CCTA) images is crucial for diagnosis and treatment planning. Traditional segmentation methods face challenges in handling low-contrast images and complex anatomical structures. In this study, we propose an attention-guided, feature-aggregated 3D deep network (AGFA-Net) for coronary artery segmentation using CCTA images. AGFA-Net leverages attention mechanisms and feature refinement modules to capture salient features and enhance segmentation accuracy. Evaluation on a dataset comprising 1,000 CCTA scans demonstrates AGFA-Net's superior performance, achieving an average Dice coefficient similarity of 86.74% and a Hausdorff distance of 0.23 mm during 5-fold cross-validation. Ablation studies further validate the effectiveness of the proposed modules, highlighting their contributions to improved segmentation accuracy. Overall, AGFA-Net offers a robust and reliable solution for coronary artery segmentation, addressing challenges posed by varying vessel sizes, complex anatomies, and low image contrast.

eess.IV↗

arXiv2024

snompy: a package for modelling scattering-type scanning near-field optical microscopy

Scattering-type scanning near-field optical microscopy (s-SNOM) is a powerful technique for extreme subwavelength imaging and spectroscopy, with around 20 nm spatial resolution. But quantitative relationships between experiment and material properties requires modelling, which can be computationally and conceptually challenging. In this work, we present snompy an open-source Python library which contains implementations of two of the most common s-SNOM models, the finite dipole model (FDM) and the point dipole model (PDM). We show a series of typical uses for this package with demonstrations including simulating nano-Fourier transform infrared (FTIR) spectra and recovering permittivity from experimental s-SNOM data. We also discuss the challenges faced with this sort of modelling, such as competing descriptions of the models in literature, and finite size effects. We hope that snompy will make quantitative s-SNOM modelling more accessible to the wider research community, which will further empower the use of s-SNOM for investigating nanoscale material properties.

cond-mat.mtrl-sci↗

arXiv2022

On Matrix Method of Symmetric Games

This paper provides a new version of matrix semi-tensor product method based on adjacent transpositions to test symmetric games. The advantage of using adjacent transpositions lies in the great simplification of analysis of symmetric games. By using the new method, new necessary and sufficient conditions for symmetric games are proposed, and a group of bases of a symmetric game space can be easily calculated. Moreover, the testing equations with the minimum number can be concretely determined. Finally, two examples are displayed to show the effectiveness of the proposed method.

cs.GT↗

arXiv2015

On Potential Equations of Finite Games

In this paper, some new criteria for detecting whether a finite game is potential are proposed by solving potential equations. The verification equations with the minimal number for checking a potential game are obtained for the first time. Some connections between the potential equations and the existing characterizations of potential games are established. It is revealed that a finite game is potential if and only if its every bi-matrix sub-game is potential.

cs.GT↗