arXiv subjects

Xiaotong Liu

Publications and source records attributed to Xiaotong Liu.

At least 19 recordsLinked to original sources

arXiv2026

Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected?

Coding agents can now rewrite repository-scale codebases while preserving tested behavior, creating a new challenge for plagiarism detection, license auditing, and software provenance. We ask whether such rewrites can still be traced to their source. Existing clone benchmarks emphasize fragments and bounded edits, while repository-transformation benchmarks evaluate functional correctness rather than provenance. Moreover, ranking the most similar source does not establish derivation when independent implementations can be similarly close. We define repository-level agentic code laundering and introduce Launder-Bench, to our knowledge the first repository-level benchmark for provenance under agentic rewriting, constructed from 282 real-world repositories. A source-hidden reconstruction protocol decomposes source behavior, reconstructs modules and repository structure, and retains rewrites only after execution-based verification. We evaluate the same provenance problem in two complementary settings: Launder-Bench-Pair contains 1,128 pairwise instances asking whether two repositories share provenance, while Launder-Bench-Attr contains 229 source-attribution instances asking which candidate is the source, with abstention when evidence is insufficient. Measured same-domain independent repositories establish how much similarity can arise without shared provenance and provide detector-specific reference bands. Existing methods remain far from saturating Launder-Bench: the strongest static method reaches only 0.66 AUROC on pairwise detection, while repository encoders rank the true source first on up to 22% of attribution queries but earn calibrated attribution credit on only 1-2%. These results reveal a systematic gap between relative code similarity and source-specific provenance evidence, providing a reproducible target for provenance detection under agentic rewriting.

cs.SE↗

arXiv2026

Deterministic preparation of squeezed and non-Gaussian states in coupled qubit-boson systems

Deterministic preparation of bosonic resource states is a central task in continuous-variable quantum information processing and quantum metrology. Here we develop a measurement-based imaginary time evolution (MITE) protocol for preparing squeezed and non-Gaussian states. The protocol combines ancilla-mediated weak measurements of the Hamiltonian with a conditional phase rotation that suppresses excited state trapping and stabilizes convergence toward the ground state. The method is potentially applicable in hybrid discrete variable-continuous variable (DV-CV) platforms, where the qubit acts as the measurement readout. We demonstrate deterministic convergence over a broad range of parameters and show that the performance degradation near the stability boundary is governed by the shrinking Bogoliubov quasiparticle gap. The same framework also extends to non-Gaussian bosonic resource states, including Schrödinger cat states and excited states of the single-mode squeezing Hamiltonian, which display Wigner negativity. The squeezed states remain robust under bosonic loss over experimentally relevant regimes.

quant-ph↗

arXiv2026

What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model's realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model's played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.

cs.SD↗

arXiv2026

Staypoint Detection from Noisy Trajectory Data [Experiment Paper]

Detecting staypoints from raw trajectory data is fundamental to numerous spatial computing applications. This process transforms raw numeric sequences of geolocations into semantically meaningful locations, such as homes, workplaces, or restaurants. Despite its importance for semantic trajectory analysis, staypoint detection lacks standard benchmarks, and existing algorithms have never been systematically evaluated. This gap persists because no publicly available datasets provide both raw individual trajectories and ground-truth staypoint annotations. This benchmark paper addresses this limitation with two key contributions: (1) we introduce 16 large-scale simulated datasets capturing thousands of agents with annotated staypoints across varying trajectory noise levels, and (2) we evaluate nine staypoint detection algorithms-including both state-of-the-art and novel methods-to analyze their robustness to noise. Our evaluation reveals that existing state-of-the-art algorithms perform poorly under realistic noise conditions. Conversely, our proposed unsupervised methods yield substantial improvements, while supervised approaches drastically outperform existing baselines. While these results are very promising, these datasets and methods are only meant as starting points for future research in staypoint detection.

cs.LG↗

arXiv2026

Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving

End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited improvements. This limitation is compounded by the inherent ambiguity of driving: each scene typically provides only a single human trajectory, making it difficult to learn multimodal behaviors. In this work, we propose Drive-JEPA, a framework that integrates Video Joint-Embedding Predictive Architecture (V-JEPA) with multimodal trajectory distillation for end-to-end driving. First, we adapt V-JEPA for end-to-end driving, pretraining a ViT encoder on large-scale driving videos to produce predictive representations aligned with trajectory planning. Second, we introduce a proposal-centric planner that distills diverse simulator-generated trajectories alongside human trajectories, with a momentum-aware selection mechanism to promote stable and safe behavior. When evaluated on NAVSIM, the V-JEPA representation combined with a simple transformer-based decoder outperforms prior methods by 3 PDMS in the perception-free setting. The complete Drive-JEPA framework achieves 93.3 PDMS on v1 and 87.8 EPDMS on v2, setting a new state-of-the-art.

cs.CV↗

arXiv2026

Towards Accurate and Interpretable Time-series Forecasting: A Polynomial Learning Approach

Time series forecasting enables early warning and has driven asset performance management from traditional planned maintenance to predictive maintenance. However, the lack of interpretability in forecasting methods undermines users' trust and complicates debugging for developers. Consequently, interpretable time-series forecasting has attracted increasing research attention. Nevertheless, existing methods suffer from several limitations, including insufficient modeling of temporal dependencies, lack of feature-level interpretability to support early warning, and difficulty in simultaneously achieving the accuracy and interpretability. This paper proposes the interpretable polynomial learning (IPL) method, which integrates interpretability into the model structure by explicitly modeling original features and their interactions of arbitrary order through polynomial representations. This design preserves temporal dependencies, provides feature-level interpretability, and offers a flexible trade-off between prediction accuracy and interpretability by adjusting the polynomial degree. We evaluate IPL on simulated and Bitcoin price data, showing that it achieves high prediction accuracy with superior interpretability compared with widely used explainability methods. Experiments on field-collected antenna data further demonstrate that IPL yields simpler and more efficient early warning mechanisms.

cs.LG↗

arXiv2026

Beyond Cross-Validation: Adaptive Parameter Selection for Kernel-Based Gradient Descents

This paper proposes a novel parameter selection strategy for kernel-based gradient descent (KGD) algorithms, integrating bias-variance analysis with the splitting method. We introduce the concept of empirical effective dimension to quantify iteration increments in KGD, deriving an adaptive parameter selection strategy that is implementable. Theoretical verifications are provided within the framework of learning theory. Utilizing the recently developed integral operator approach, we rigorously demonstrate that KGD, equipped with the proposed adaptive parameter selection strategy, achieves the optimal generalization error bound and adapts effectively to different kernels, target functions, and error metrics. Consequently, this strategy showcases significant advantages over existing parameter selection methods for KGD.

stat.ML↗

arXiv2026

Rethinking Camera Choice: An Empirical Study on Fisheye Camera Properties in Robotic Manipulation

The adoption of fisheye cameras in robotic manipulation, driven by their exceptionally wide Field of View (FoV), is rapidly outpacing a systematic understanding of their downstream effects on policy learning. This paper presents the first comprehensive empirical study to bridge this gap, rigorously analyzing the properties of wrist-mounted fisheye cameras for imitation learning. Through extensive experiments in both simulation and the real world, we investigate three critical research questions: spatial localization, scene generalization, and hardware generalization. Our investigation reveals that: (1) The wide FoV significantly enhances spatial localization, but this benefit is critically contingent on the visual complexity of the environment. (2) Fisheye-trained policies, while prone to overfitting in simple scenes, unlock superior scene generalization when trained with sufficient environmental diversity. (3) While naive cross-camera transfer leads to failures, we identify the root cause as scale overfitting and demonstrate that hardware generalization performance can be improved with a simple Random Scale Augmentation (RSA) strategy. Collectively, our findings provide concrete, actionable guidance for the large-scale collection and effective use of fisheye datasets in robotic learning. More results and videos are available on https://robo-fisheye.github.io/

cs.RO↗

arXiv2026

Two-Stage Data Synthesization: A Statistics-Driven Restricted Trade-off between Privacy and Prediction

Synthetic data have gained increasing attention across various domains, with a growing emphasis on their performance in downstream prediction tasks. However, most existing synthesis strategies focus on maintaining statistical information. Although some studies address prediction performance guarantees, their single-stage synthesis designs make it challenging to balance the privacy requirements that necessitate significant perturbations and the prediction performance that is sensitive to such perturbations. We propose a two-stage synthesis strategy. In the first stage, we introduce a synthesis-then-hybrid strategy, which involves a synthesis operation to generate pure synthetic data, followed by a hybrid operation that fuses the synthetic data with the original data. In the second stage, we present a kernel ridge regression (KRR)-based synthesis strategy, where a KRR model is first trained on the original data and then used to generate synthetic outputs based on the synthetic inputs produced in the first stage. By leveraging the theoretical strengths of KRR and the covariant distribution retention achieved in the first stage, our proposed two-stage synthesis strategy enables a statistics-driven restricted privacy--prediction trade-off and guarantee optimal prediction performance. We validate our approach and demonstrate its characteristics of being statistics-driven and restricted in achieving the privacy--prediction trade-off both theoretically and numerically. Additionally, we showcase its generalizability through applications to a marketing problem and five real-world datasets.

cs.LG↗

arXiv2026

Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary Queries

Vision-Language Models like CLIP create aligned embedding spaces for text and images, making it possible for anyone to build a visual classifier by simply naming the classes they want to distinguish. However, a model that works well in one domain may fail in another, and non-expert users have no straightforward way to assess whether their chosen VLM will work on their problem. We build on prior work using text-only comparisons to evaluate how well a model works for a given natural language task, and explore approaches that also generate synthetic images relevant to that task to evaluate and refine the prediction of zero-shot accuracy. We show that generated imagery to the baseline text-only scores substantially improves the quality of these predictions. Additionally, it gives a user feedback on the kinds of images that were used to make the assessment. Experiments on standard CLIP benchmark datasets demonstrate that the image-based approach helps users predict, without any labeled examples, whether a VLM will be effective for their application.

cs.CV↗

arXiv2025

Pre-emptive parametric kill switch for evaporative atomic sources in vacuum

A robust pre-emptive kill switch for cold atom experiments is introduced to significantly reduce costly system reassembly or replacement. The design incorporates upper (alarm) and lower (evaporation) event detection mechanisms based on predefined thresholds. Meanwhile, a duty cycle timing methodology is used to avert unintentional activation of the dispenser in circumstances where pulse signals occur. The circuit employs generic components, a modular design, and formalized logic, ensuring cost-effectiveness, making the design suitable for school laboratories and other research environments. This design is highly versatile and can be applied to other sensitive devices beyond dispensers, such as heating filaments, titanium sublimation pumps, tungsten lamps, and comparable systems.

physics.atom-ph↗

arXiv2025

Transcending Sparse Measurement Limits: Operator-Learning-Driven Data Super-Resolution for Inverse Source Problem

Inverse source localization from Helmholtz boundary data collected over a narrow aperture is highly ill-posed and severely undersampled, undermining classical solvers (e.g., the Direct Sampling Method). We present a modular framework that significantly improves multi-source localization from extremely sparse single-frequency measurements. First, we extend a uniqueness theorem for the inverse source problem, proving that a unique solution is guaranteed under limited viewing apertures. Second, we employ a Deep Operator Network (DeepONet) with a branch-trunk architecture to interpolate the sparse measurements, lifting six to ten samples within the narrow aperture to a sufficiently dense synthetic aperture. Third, the super-resolved field is fed into the Direct Sampling Method (DSM). For a single source, we derive an error estimate showing that sparse data alone can achieve grid-level precision. In two- and three-source trials, localization from raw sparse measurements is unreliable, whereas DeepONet-reconstructed data reduce localization error by about an order of magnitude and remain effective with apertures as small as $π/4$. By decoupling interpolation from inversion, the framework allows the interpolation and inversion modules to be swapped with neural operators and classical algorithms, respectively, providing a practical and flexible design that improves localization accuracy compared with standard baselines.

math.NA↗

arXiv2025

Dual-domain Microwave Photonic Radar for Non-contact High-resolution Monitoring of Vital Signs in Multiple Individuals

We present a dual-domain microwave photonic radar system for multi-parameter vital sign monitoring, utilizing ultra-wideband radiofrequency signals to achieve high-precision chest displacement measurements, while high-frequency optical signals enable accurate Doppler detection of pulse-induced micro-motions. We experimentally validated the system by simultaneously monitoring respiratory and pulse rate of two male volunteers, demonstrating high performance with average accuracies of 98.1% for pulse detection and 99.85% for respiratory detection. Additionally, the system facilitates rapid, indirect blood pressure estimation, achieving a coefficient of determination of 0.905. With the help of low-loss distribution capability of optical fibers, the system can be scaled into a distributed, non-contact multiple vital signs monitoring platform, highlighting its potential for clinical and healthcare applications.

physics.optics↗

arXiv2025

Striking the Perfect Balance: Preserving Privacy While Boosting Utility in Collaborative Medical Prediction Platforms

Online collaborative medical prediction platforms offer convenience and real-time feedback by leveraging massive electronic health records. However, growing concerns about privacy and low prediction quality can deter patient participation and doctor cooperation. In this paper, we first clarify the privacy attacks, namely attribute attacks targeting patients and model extraction attacks targeting doctors, and specify the corresponding privacy principles. We then propose a privacy-preserving mechanism and integrate it into a novel one-shot distributed learning framework, aiming to simultaneously meet both privacy requirements and prediction performance objectives. Within the framework of statistical learning theory, we theoretically demonstrate that the proposed distributed learning framework can achieve the optimal prediction performance under specific privacy requirements. We further validate the developed privacy-preserving collaborative medical prediction platform through both toy simulations and real-world data experiments.

cs.LG↗

arXiv2025

NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Driving

Autonomous driving systems have made significant advances in Q&A, perception, prediction, and planning based on local visual information, yet they struggle to incorporate broader navigational context that human drivers routinely utilize. We address this critical gap between local sensor data and global navigation information by proposing NavigScene, an auxiliary navigation-guided natural language dataset that simulates a human-like driving environment within autonomous driving systems. Moreover, we develop three complementary paradigms to leverage NavigScene: (1) Navigation-guided Reasoning, which enhances vision-language models by incorporating navigation context into the prompting approach; (2) Navigation-guided Preference Optimization, a reinforcement learning method that extends Direct Preference Optimization to improve vision-language model responses by establishing preferences for navigation-relevant summarized information; and (3) Navigation-guided Vision-Language-Action model, which integrates navigation guidance and vision-language models with conventional driving models through feature fusion. Extensive experiments demonstrate that our approaches significantly improve performance across perception, prediction, planning, and question-answering tasks by enabling reasoning capabilities beyond visual range and improving generalization to diverse driving scenarios. This work represents a significant step toward more comprehensive autonomous driving systems capable of navigating complex, unfamiliar environments with greater reliability and safety.

cs.RO↗

arXiv2024

A signal recovery guarantee with Restricted Isometry Property and Null Space Property for weighted $\ell_1$ minimization

Signal reconstruction is a crucial aspect of compressive sensing. In weighted cases, there are two common types of weights. In order to establish a unified framework for handling various types of weights, the sparse function is introduced. By employing this sparse function, a generalized form of the weighted null space property is developed, which is sufficient and necessary to exact recovery through weighted $\ell_1$ minimization. This paper will provide a new recovery guarantee called $ω$-RIP-NSP with the weighted $\ell_1$ minimization, combining the weighted null space property and the weighted restricted isometry property. The new recovery guarantee only depends on the kernel of matrices and provides robust and stable error bounds. The third aim is to explain the relationships between $ω$-RIP, $ω$-RIP-NSP and $ω$-NSP. $ω$-RIP is obviously stronger than $ω$-RIP-NSP by definition. We show that $ω$-RIP-NSP is stronger than the weighted null space property by constructing a matrix that satisfies the weighted null space property but not $ω$-RIP-NSP.

math.CA↗

arXiv2024

Reconstruction with prior support information and non-Gaussian constraints

In this study, we introduce a novel model, termed the Weighted Basis Pursuit Dequantization ($ω$-BPDQ$_p$), which incorporates prior support information by assigning weights on the $\ell_1$ norm in the $\ell_1$ minimization process and replaces the $\ell_2$ norm with the $\ell_p$ norm in the constraint. This adjustment addresses cases where noise deviates from a Gaussian distribution, such as quantized errors, which are common in practice. We demonstrate that Restricted Isometry Property (RIP$_{p,q}$) and Weighted Robust Null Space Property ($ω$-RNSP$_{p,q}$) ensure stable and robust reconstruction within $ω$-BPDQ$_p$, with the added observation that standard Gaussian random matrices satisfy these properties with high probability. Moreover, we establish a relationship between RIP$_{p,q}$ and $ω$-RNSP$_{p,q}$ that RIP$_{p,q}$ implies $ω$-RNSP$_{p,q}$. Additionally, numerical experiments confirm that the incorporation of weights and the non-Gaussian constraint results in improved reconstruction quality.

eess.SP↗

arXiv2024

Vision-based Wearable Steering Assistance for People with Impaired Vision in Jogging

Outdoor sports pose a challenge for people with impaired vision. The demand for higher-speed mobility inspired us to develop a vision-based wearable steering assistance. To ensure broad applicability, we focused on a representative sports environment, the athletics track. Our efforts centered on improving the speed and accuracy of perception, enhancing planning adaptability for the real world, and providing swift and safe assistance for people with impaired vision. In perception, we engineered a lightweight multitask network capable of simultaneously detecting track lines and obstacles. Additionally, due to the limitations of existing datasets for supporting multi-task detection in athletics tracks, we diligently collected and annotated a new dataset (MAT) containing 1000 images. In planning, we integrated the methods of sampling and spline curves, addressing the planning challenges of curves. Meanwhile, we utilized the positions of the track lines and obstacles as constraints to guide people with impaired vision safely along the current track. Our system is deployed on an embedded device, Jetson Orin NX. Through outdoor experiments, it demonstrated adaptability in different sports scenarios, assisting users in achieving free movement of 400-meter at an average speed of 1.34 m/s, meeting the level of normal people in jogging. Our MAT dataset is publicly available from https://github.com/snoopy-l/MAT

cs.CV↗