Searcharxiv⌕ Search

arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 127 records · Page 7Linked to original sources
arXiv2026

A multi-architecture study of specificity refinement and false-positive mechanism analysis in prostate MRI

Objectives: To characterize residual false positives in prostate MRI detection, and to evaluate a lightweight post-hoc refinement head for case-level specificity. Materials and Methods: This retrospective study used PI-CAI (5-fold cross-validation) and Prostate158 (n=158; external). A context-aware evidence head and an 89,216-parameter refinement head were trained on a frozen detection backbone; the evidence head was also trained on four further backbones (bare nnU-Net, bare U-Net, bare Mamba, MIGF-Mamba). For each false-positive region, T2-weighted, apparent-diffusion-coefficient, and high-b-value contrast ratios versus peri-lesional rings were compared against ground-truth lesions and contralateral benign regions. Results: False positives were closer to true cancers than to benign tissue in evidence and raw T2-weighted and apparent-diffusion-coefficient contrast, reproducing 35/35 across five architectures (Cohen's d 1.10; FP/benign evidence ratio 2.38x) and 105/105 across modality-perturbation scenarios. On PI-CAI fold-0, refinement raised case-level specificity from 0.469 to 0.549 (+17.2%) at preserved sensitivity (0.943); 5-fold cross-validation showed fold-conditional behavior (9/15 observations positive; range -22% to +28%). On Prostate158, both models saturated (McNemar pooled p=0.69), while the false-positive contrast-matching finding replicated. Conclusion: Residual false positives are contrast-matched to cancer (sharing raw imaging features rather than histologically confirmed mimicry), reproducing across five architectures -- a data-level imaging property, not model-specific artifacts; post-hoc refinement adds practical specificity in-domain but is fold-conditional.

eess.IV↗
arXiv2026

SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy

Volume microscopy, including electron and light microscopy, suffers from severe anisotropic resolution due to physical axial sectioning. Existing self-supervised axial super-resolution (ASR) methods face a trilemma bounded by overly smoothed regression textures, structural hallucinations of pure diffusion models, and prohibitive inference latency. In this paper, we propose Skeleton-refinE Microscopy (SkelEM), a self-supervised framework that decouples ASR at the training-signal level: a frozen topological network and a diffusion refiner are optimized by disjoint objectives, separating low-frequency topology formulation from high-frequency detail enhancement. Building on this deterministic skeleton, we exploit a unified cycle-consistent mechanism on input sparse slices to simultaneously extract a real-domain residual prior and bidirectionally align the diffusion refiner, washing away cross-plane artifacts without synthetic bias. By truncating the reverse diffusion process with this physical prior, SkelEM achieves high-fidelity detail restoration in merely $\le 5$ steps. To rigorously assess cross-instrument generalization, we further introduce BRAVE-ASR, a new benchmark of co-aligned anisotropic and isotropic volumes acquired on a Plasma-FIB instrument. Across public benchmarks, SkelEM achieves the most favorable balance across the fidelity-perception trade-off among self-supervised methods, with state-of-the-art downstream membrane segmentation performance and robust zero-shot generalization across distinct modalities.

cs.CV↗
arXiv2026

MobileManiBench: Simplifying Model Verification for Mobile Manipulation

Vision-language-action models have advanced robotic manipulation but remain constrained by reliance on the large, teleoperation-collected datasets dominated by the static, tabletop scenes. We propose a simulation-first framework to verify VLA architectures before real-world deployment and introduce MobileManiBench, a large-scale benchmark for mobile-based robotic manipulation. Built on NVIDIA Isaac Sim and powered by reinforcement learning, our pipeline autonomously generates diverse manipulation trajectories with rich annotations (language instructions, multi-view RGB-depth-segmentation images, synchronized object/robot states and actions). MobileManiBench features 2 mobile platforms (parallel-gripper and dexterous-hand robots), 2 synchronized cameras (head and right wrist), 630 objects in 20 categories, 5 skills (open, close, pull, push, pick) with over 100 tasks performed in 100 realistic scenes, yielding 300K trajectories. This design enables controlled, scalable studies of robot embodiments, sensing modalities, and policy architectures, accelerating research on data efficiency and generalization. We benchmark representative VLA models and report insights into perception, reasoning, and control in complex simulated environments, with all code, datasets, and models publicly released.

cs.RO↗
arXiv2026

Scalable Behavior Cloning with Open Data, Training, and Evaluation

We introduce ABC, a fully open-source stack for manipulation with behavior cloning. At its core is ABC-130K: the largest open-source teleoperation dataset to date, featuring 3,500 hours of data spanning over 130K episodes across 195 diverse tasks. Furthermore, we open-source our accessible hardware setup, training infrastructure, and simulation pipeline. We also release 400 hours of sim-teleop data and provide a co-training recipe that produces correlated simulation and real-world evaluation, offering a reliable proxy for ablating model-design and training decisions before costly real-world evaluation. We explore various training recipes and compare common architectural choices for Diffusion Transformers (DiT) and Vision-Language-Action (VLA) models, grounding our findings in real-world evaluations. The resulting policies successfully execute dexterous tasks such as box folding and extracting credit cards from wallets. By providing a reproducible toolkit, we aim to place researchers on an equal footing, establishing the necessary foundation to learn the ABCs of Behavior Cloning together as a community.

cs.RO↗
arXiv2026

Scattering of the defocusing Calogero--Moser derivative nonlinear Schrödinger equation

In this paper, we study the long time behavior of solutions to the defocusing Calogero--Moser derivative nonlinear Schrödinger equation (CM-DNLS). Using the Gérard-type explicit formula, we prove the scattering result of solutions to this equation with initial data in $L_{+}^2(\mathbb{R}):=\left\{f \in L^2(\mathbb{R}): \operatorname{supp}(\widehat{f}) \subset[0,+\infty)\right\}$. We also characterize the scattering term using the distorted Fourier transform associated with the Lax operator. This is one of the first works that apply the Gérard-type explicit formula to study the long-time behavior of an integrable equation for a broad class of initial data, beyond the previously studied rational cases.

math.AP↗
arXiv2026

The Memory-Enhanced Gaussian Noise (MEGN) Model for Fiber-Optic Channels

The enhanced Gaussian noise (EGN) model is widely used for estimating the nonlinear interference (NLI) power accumulated in coherent fiber-optic transmission systems. Given a fixed fiber link, under the assumption that transmitted symbols are independent and identically distributed (i.i.d.), the EGN model establishes that the NLI power depends on time-invariant signal statistics, i.e., the second-, fourth-, and sixth-order moments of the symbols, which are determined by the modulation format and its probability distribution. However, recent advances in coded modulation have sought to mitigate NLI by introducing controlled temporal correlations among transmitted symbols, thereby violating the i.i.d. assumption underlying the EGN model. Among these correlations, symbol energy correlations are believed to exert the most significant influence on NLI. This work presents a rigorous mathematical derivation of a memory extension of the EGN model that explicitly accounts for symbol energy correlations, referred to as the MEGN model. The proposed MEGN model is validated through both numerical simulations and transmission experiments. Normalized average NLI power estimations with less than 5% errors across a wide range of symbol rates and transmission distances are reported. The model also provides a theoretical framework for analyzing and optimizing optical transmission systems employing temporally correlated modulation schemes.

eess.SP↗
arXiv2026

Smooth time-dependent control of dipolar Bose-Einstein condensates

We consider protocols for control of dipolar Bose-Einstein condensates where the critical role is played by the long-range anisotropic interatomic magnetic dipole-dipole interaction. The phase diagram of such a condensate has been explored theoretically and experimentally with certain values of the interatomic scattering length corresponding to superfluid and supersolid phases, where supersolidity appears as a modulation in the ground state density. Preparation of this modulated ground state is challenging, since excitations appear as a result of a finite-time evolution required to produce qualitative changes in the wavefunction density. To solve this problem we consider the time-dependent control of a dipolar Bose-Einstein condensate using shortcuts to adiabaticity techniques, concentrating on design of the time-dependent scattering length, a parameter of the system easily tunable by contemporary experiments. The first technique is the variational approach based on the Euler-Lagrange equations for a separable ansatz describing the evolution of the superfluid state. Secondly, we study the transition from superfluid to supersolid using a direct optimization protocol. We discuss the fidelity of the developed protocols in terms of the evolution time.

cond-mat.quant-gas↗
arXiv2026

LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories

Scientific laboratories increasingly rely on AI systems to reason about experiments, but the physical act of doing science remains largely outside their reach. AI can help read literature, generate hypotheses, and plan protocols, yet the execution of those protocols at the bench still requires a human operator. Vision-Language-Action (VLA) models provide one possible interface between written protocols and robot execution, but existing policies are trained mostly on household and tabletop demonstrations and rarely encounter the instruments, transparent liquids, or fixed protocol workflows found in scientific laboratories. Closing this gap requires both laboratory-specific supervision and a unified learning framework that can accommodate the diverse robot embodiments used to execute experimental protocols. We therefore identify data and embodiment as central bottlenecks alongside model design. To address the data side, we build RoboGenesis, a simulation-based workflow and data engine that composes configured laboratory workflows from atomic skills, validates and filters rollouts, and exports structured demonstrations across supported robot profiles. On the policy side, we present LabVLA, trained with a two-stage recipe: FAST action token pretraining first makes the Qwen3-VL-4B-Instruct backbone action aware before any continuous control is learned, and flow matching posttraining then attaches a DiT action expert under knowledge insulation. On the LabUtopia benchmark, LabVLA achieves the highest average success rate among all evaluated baselines under both in-distribution and out-of-distribution settings.

cs.CL↗
arXiv2026

SkillWiki: A Living Knowledge Infrastructure for Agent Skills

While knowledge is managed through Wikipedia and software through GitHub, agent skills still lack an infrastructure for large-scale production, governance, and evolution. SkillWiki is a living knowledge infrastructure that supports the organization, grounding, and continuous evolution of agent skills by transforming heterogeneous knowledge into reusable skill assets linked to their originating evidence. Our demonstration presents the complete skill lifecycle, from knowledge ingestion and skill production to provenance-aware exploration, governance, and execution-driven evolution. SkillWiki highlights a future in which knowledge, skills, and execution experience co-evolve within a shared infrastructure. The live demonstration and source code are publicly available at https://github.com/Huangdingcheng/SkillWiki.

cs.CL↗
arXiv2026

OmniTraffic: A Controllable Generation Pipeline and Benchmark for Spatio-Temporal Traffic Reasoning

Traffic scene understanding requires models to reason beyond object recognition, including lane topology, multi-view geometry, temporal evolution, and signal-phase semantics. However, existing traffic-oriented multimodal benchmarks largely emphasize passive visual recognition or isolated video understanding, offering limited support for evaluating structure-aware traffic reasoning under controlled conditions. We introduce OmniTraffic, a controllable generation pipeline and benchmark for spatio-temporal traffic reasoning. Built around 12 real-world intersections reconstructed into editable 3D traffic environments and complemented by surveillance footage from two countries, OmniTraffic supports both controlled and natural-condition evaluation. It defines a three-level task hierarchy spanning scene perception, multi-view and temporal reasoning, and decision support. Using structured traffic metadata, OmniTraffic generates synchronized multi-view VQA samples covering vehicle states, lane functions, view--BEV correspondence, temporal dynamics, and signal-phase analysis, resulting in 8M VQA samples and a 3K human-verified test set. Evaluation of eleven frontier MLLMs reveals a large human--model gap, with the most pronounced failures in topology-grounded and spatio-temporal reasoning tasks. Fine-tuning a lightweight MLLM on simulated OmniTraffic data further improves performance on real-world traffic scenes, demonstrating the value of simulation-generated supervision for traffic-specific multimodal reasoning. Beyond a fixed dataset, OmniTraffic provides an extensible pipeline with configurable intersections, camera views, traffic demands, signal phases, visual conditions, and rare events.

cs.CV↗
arXiv2026

ReportQA: QA-Based Radiology Report Evaluation

Radiology report evaluation is essential for advancing automated report generation. Natural language generation metrics have limited clinical relevance. Clinical efficacy (CE) metrics evaluate important medical findings, but focus mainly on presence and cover only a limited set of entities. Due to heavy reliance on manual annotations, it is difficult for CE metrics to extend clinical entities or attributes. In clinical practice, radiology reports serve as a medium for information transfer. Clinicians use them to perform downstream diagnostic tasks without directly inspecting images. Based on this insight, we propose ReportQA, a clinical-related and flexible radiology report evaluation framework, supporting detailed quantitative analysis of radiology report generation systems. We first collect datasets covering multiple imaging modalities and anatomical regions. We then construct knowledge trees of clinical entities and attributes with radiologist guidance, and use large language models (LLMs) to extract structured information from raw reports. Next, we generate QA pairs from predefined templates and apply quality control through self-filtering and report-based filtering. During evaluation, the report is treated as context, and an LLM acts as a judge model to answer the QA pairs. Based on the resulting QA accuracy, we introduce QAScore metric. Compared with existing metrics, QAScore shows better alignment with radiologist judgments. Experiments on multiple state-of-the-art vision-language models reveal that current report-based inference paradigms struggle to learn fine-grained clinical representations and exhibit strong negative prior biases. In contrast, question-driven inference provides a more effective alternative. For reproducibility and extensibility, we release the knowledge trees, structured reports, and QA pairs, along with the pipeline code for QA construction and evaluation.

cs.CL↗
arXiv2026

Vorticity-dynamical analysis of Richtmyer-Meshkov instability based on orbital-spin vorticity decomposition

The present study provides a detailed vorticity-dynamical analysis of shock-driven hydrodynamic physics in canonical Richtmyer-Meshkov instability (RMI) flows: shock interaction with a single-mode perturbed interface, and a cylindrical air bubble immersed in Krypton. These findings provide insights into vortical flow physics beyond the conventional vorticity paradigm, and the DVD approach holds promise for the diagnosis of practical instability-induced flows.

physics.flu-dyn↗
arXiv2026

Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation

Speech-to-speech translation (S2ST) systems have achieved impressive progress in semantic accuracy and speech naturalness. However, the cross-lingual transfer of lexical stress, a vital cue for emphasis and speaker intent, remains heavily underexplored, compounded by a lack of reliable automatic evaluation metrics for tonal languages like Chinese. We investigate English-to-Chinese S2ST stress transfer by constructing a stress-annotated Chinese dataset and an XLS-R-based Mandarin stress detector. Integrating this with the English EmphAssess system, we propose a novel objective metric for cross-lingual stress evaluation. Furthermore, we fine-tune CosyVoice3 to build a stress-aware S2ST system. Experiments demonstrate that our proposed S2ST architecture significantly outperforms existing systems in stress translation capability while maintaining competitive translation quality. Furthermore, our evaluation metric exhibits a strong correlation with human subjective judgments.

cs.CL↗
arXiv2026

Free-Molecular Face-Flux Preprocessing for Reduced Neutral-Continuity Modeling in Hall Thrusters: Particle-Based Reference and Deterministic SN-DFEM Realization

Neutral gas transport directly affects the ionization source, propellant utilization, and low-frequency discharge oscillations in Hall thrusters. High-fidelity particle-based neutral models or DSMC methods can describe rarefied gas transport, but they are computationally expensive; in contrast, reduced neutral-continuity models are cheaper but require a closure for the neutral velocity or face-normal flux. Under a low-pressure collisionless approximation, this work adopts a free-molecular preprocessing strategy to provide a reference density field and the mean-velocity or face-normal-flux closure used by the reduced neutral-continuity equation in a manner consistent with the underlying transport model.On this basis, a particle-based free-molecular faceflux preprocessor is used as a stochastic reference, and an SN-DFEM deterministic free-molecular preprocessor is proposed to generate the corresponding reference density, velocity moments, and face-normal fluxes within a unified free-molecular transport framework. Results show that the SN-DFEM preprocessor preserves the main neutral-density and velocity structures and reduces the statistical error in face-flux closure by about three orders of magnitude in the baseline continuity-recovery test. A prescribed moderate ionization-loss case further demonstrates the extension of the framework to free-molecular preprocessing with volumetric neutral removal.

physics.plasm-ph↗
arXiv2026

Nonadiabatic Self-Healing of Trotter Errors in Digitized Counterdiabatic Dynamics

Trotter errors in digitized quantum dynamics arise from approximating time-ordered evolution under noncommuting Hamiltonian terms with a product formula. In the adiabatic regime, such errors are known to exhibit long-time self-healing [Phys. Rev. Lett. \textbf{131}, 060602 (2023)], where discretization effects are effectively suppressed. Here we show that self-healing persists at finite evolution times once nonadiabatic errors induced by finite-speed ramps are compensated. Using counterdiabatic driving to cancel diabatic transitions and isolate discretization effects, we study both noninteracting and interacting spin models and characterize the finite-time scaling with the Trotter steps and the total evolution time. In the instantaneous eigenbasis of the driven Hamiltonian, the leading digital error maps to an effective harmonic perturbation whose dominant Fourier component yields an analytic upper bound on the finite-time Trotter error and reveals the phase-cancellation mechanism underlying self-healing. Our results establish finite-time self-healing as a generic feature of digitized counterdiabatic protocols, clarify its mechanism beyond the long-time adiabatic limit, and provide practical guidance for high-fidelity state preparation on gate-based quantum processors.

quant-ph↗
arXiv2026

Revisiting the Rules-versus-Discretion Debate: Forecasting Evidence from the Bank of England, 1870-1913

Under the classical gold standard, historians have long debated what guided the Bank of England's adjustments to Bank Rate: whether policy followed a mechanical gold-standard rule or discretion when City or exchange conditions required it, and whether domestic money-market stability or external convertibility carried greater weight. This paper revisits those questions with a London-specific monthly panel, 1870-1913, jointly testing ten domestic and external indicators the Court watched when setting the published minimum rate. The findings fit neither a single frozen channel nor unstructured ad hoc policy. Instead, the Bank appears to have drawn repeatedly on a multivariate information set-trade settlement, gold movements, City asset prices, bill-market conditions, and episodic convertibility pressure-with state-dependent weights across subperiods. In the confirmatory specification, exports, gold flow, and industrial share prices carry the clearest joint forecasting content for changes in Bank Rate. Gold flow forecasts rate changes even when reserve stock does not, separating bullion settlement from balance-sheet position. Bill-market and convertibility pressures also carry incremental forecasting content in the multivariate specification, though their prominence depends on how domestic and external indicators are modeled together. The overall pattern is most consistent with systematic discretion under the classical gold standard.

econ.EM↗
arXiv2026

Leveraging rapid sintering to retain metastable zirconia in copper

Cermets combining metastable ceramics and ductile metals promise superior toughness and strength. However, retaining metastability often requires high-temperature sintering that coarsens microstructures and relaxes matrix constraint. Here we introduce an ultrafast high-temperature sintering (UHS) strategy to overcome this trade-off in zirconia-copper cermets. By applying Joule heating at around 100 degrees C per second to 900 degrees C with only a 20 second hold, we obtained cermets containing up to 50 weight percent of metastable austenite in zirconia at room temperature within a fine-grained and homogeneous microstructure. The rapid sintering kinetically favors semi-thermal austenite formation while suppressing copper grain growth and matrix relaxation, thereby stabilizing the high-temperature phase and simultaneously preserving microstructural refinement. This approach offers significant potential for copper-based composites in applications such as transformation toughening, self-healing, and crack detection.

cond-mat.mtrl-sci↗