Searcharxiv⌕ Search

arXiv subjects

Shuai Wu

Publications and source records attributed to Shuai Wu.

At least 19 recordsLinked to original sources

Verbal tics in frontier language models: A critical review of current releases, research evidence, and public discussion

Repeated praise, canned reassurance, formulaic contrasts, and conspicuous vocabulary figure prominently in discussions of large language models. Context governs how these habits should be read. A conventional phrase can orient a reader, whereas a fluent answer can reinforce a false belief. This critical review examines linguistic habits and sycophancy across eight developer families. We verify public offerings from OpenAI, Anthropic, Google DeepMind, xAI, ByteDance, Moonshot AI, DeepSeek, and Xiaomi against official release and API documentation through 1 October 2026. We then synthesize empirical research on lexical overrepresentation, stylistic variation, social warmth, and agreement alongside benchmark methods and dated public discussions in English and Chinese. Published studies document recurring linguistic patterns and agreement that distorts human judgment, but comparable measurements for the newest releases remain sparse in the retrieved material. Current user accounts report both persistent complaints and clearer prose, and experiences vary by task and prompt design. We propose separate measures for recurrence, contextual appropriateness, and belief distortion paired with exact service records and language-specific annotation. This framework keeps claims about writing quality and conversational reliability testable as model services change.

cs.CL↗

Seeing Is No Longer Believing: Frontier Image Generation Models, Synthetic Visual Evidence, and Real-World Risk

Image generation systems can produce plausible photographs, readable documents, and consistent depictions of people and places. Presented as records of real events, these outputs can influence decisions in news, finance, identity verification, medicine, and law. This narrative review examines public model documentation, incident reports, empirical studies, governance materials, and illustrative English and Chinese practitioner commentary available through 1 October 2026. We separate vendor capability claims, documented incidents, experimental findings, and prospective harm pathways. Realism, text rendering, reference consistency, conversational editing, search grounding, and low generation cost shape the conditions under which synthetic images acquire evidentiary weight. Documented episodes show how fabricated visuals enter public and institutional workflows, although public reporting cannot measure misuse prevalence for current releases. Comparing provider safeguards, provenance credentials, watermarks, platform labels, and statutory duties shows that origin signals do not verify a depicted event or transaction. Our framework matches artifact types and decision stakes to specific controls. Consequential decisions require authenticated source records, independent channel corroboration, and proportionate review before action.

cs.CL↗

An Inspectable LLM Council for Multi-Model Research Answer Aggregation

Long-form research questions often require answers that combine complementary details, reconcile conflicting estimates, and retain qualifications across several large language model outputs. We present Standard Council, a two-stage synthesis workflow in which an analyst organizes three independent candidate answers into a structured textual state and a separate writer composes the final response from the question and that state. We evaluate the workflow on 100 closed-book tasks from the Deep Research Accuracy, Completeness, and Objectivity benchmark, DRACO, retaining 600 final answers, 100 analyst states, and 720 whole-answer judgments. Under the primary rubric judge, Council scores 70.98, exceeding GPT-5.6 Sol by 6.18 points and Gemini 3.8 Flash by 8.34 points; its 0.47-point difference from Claude Opus 5 has a 95% paired interval of $[-0.69,1.61]$. In the four-arm fusion comparison, Council scores 1.87 points above direct fusion, with a 95% paired interval of $[0.33,3.48]$. It covers 51.1% of positive criteria met by exactly one candidate, compared with 43.7% for direct fusion. On an exploratory 68-task subset with matching returned model labels, the Council-minus-direct-fusion difference is $-1.69$ points, with a 95% interval of $[-2.80,-0.62]$. The full comparison characterizes workflows that differ in structure and generation budget; estimating the analyst stage's effect requires a controlled component study. Traced cases show how selected estimates, provenance qualifications, and selection decisions pass through the saved state into final answers.

cs.CL↗

From language-model stock rankings to testable economic rules: A computational audit

We test the stability, reproducibility and investment outcomes of language-model stock rankings. Four models and five numerical comparators share a portfolio engine over 72 monthly holding periods in the Shanghai Stock Exchange (SSE) 50, China Securities Index (CSI) 300 and CSI 500. Rankings use nine characteristics, and five repeated SSE 50 runs measure variation under identical inputs. Linear rules fitted to development-period model preferences are frozen before unseen-month, larger-pool and controlled-intervention tests. Their mean Spearman agreement with model rankings is 0.923-0.984 in the SSE 50 and 0.795-0.985 after transfer. Aggregate rank-change error falls relative to a zero-change prediction in twelve archived feature-group comparisons and eight matched single-feature comparisons, with Holm adjustments applied in separate nine-plus-three and six-plus-two families. Prediction of individual entries and exits remains weak (event Jaccard 0.000-0.125). Historical mean model compound annual growth rates range from 6.26% to 11.17%. At 10 basis points per side and six-month blocks, the twelve-comparison model-minus-rule return family and factor-controlled associations yield no adjusted finding. Three higher-cost, twelve-month-block comparisons favor a Terra rule within their twelve-test slices, with no adjusted finding across the full 144-test sensitivity grid. Two input-intervention batches totaling 5,184 responses supply paired intervention-return tests. The three-model batch has no bootstrap-adjusted finding at the primary block length; a Luna row-order effect appears under heteroskedasticity- and autocorrelation-consistent (HAC) adjustment within its three-test family but not in a pooled 24-test adjustment. Compact rules approximate aggregate rankings; return conclusions depend on comparison families, uncertainty methods and tie priorities.

cs.CE↗

Patch correctness in automated program repair: A five-dimensional evidence framework and cross-benchmark audit from classical repair to coding agents

Tests guide automated program repair and determine which candidate patches are reported as successful. Repository-level coding agents extend this feedback loop by generating tests and revising code after observing execution results. This technical report introduces a five-dimensional evidence profile and reporting protocol to audit how test observations support patch-correctness claims across classical repair systems and coding agents. We assemble an audit dataset of 39 benchmark and evaluation artifacts: 32 primary empirical studies, one institutional technical audit, and six prior taxonomic baselines. We code the 33 primary contributions along five dimensions: test provenance and exposure, behavioral scope, oracle basis and dependence, execution integrity, and label adjudication. The central distinction separates checks visible during repair search from evidence reserved for final assessment. Four worked comparative audits show how changed candidate populations, oracle rules, or execution budgets alter reported detection rates. Additional tests can expose missed faults while rejecting valid alternatives or reducing correct-repair yield under a fixed budget. Repository-level audits separate issue reproduction from candidate-patch discrimination and distinguish automated discrepancy detection from requirements-based adjudication. An evidence matrix links each coded decision to supporting passages and records shared benchmark ancestry. We specify a reporting protocol for repair benchmarks and maintenance pipelines that retains uncertain judgments and records validation cost alongside fault detection and valid-patch retention.

cs.SE↗

Phase calibration of quantum oscillations in the magnetostrictive coefficient using the topological antiferromagnet YbMnBi$_2$

The Berry phase accumulated along a cyclotron orbit encodes important information about electronic band topology and is commonly inferred from the phase of quantum oscillations. Measurements of the ac magnetostrictive coefficient have recently emerged as a sensitive thermodynamic probe of quantum oscillations, but the phase offset has not been experimentally calibrated. Here, using the topological antiferromagnet YbMnBi$_2$, we calibrate this offset by directly comparing quantum oscillations in magnetization with those in the ac magnetostrictive coefficient. Measurements of both responses on the same single crystal reveal a single fundamental frequency of approximately 160 T in fields up to 14 T, enabling a direct phase comparison free from ambiguities associated with multiple frequencies. We observe an approximately $π/2$ relative phase shift between the two oscillatory responses, consistent with the Maxwell relation linking the magnetostrictive coefficient to the stress derivative of magnetization. Our results establish the appropriate phase needed to extract cyclotron-orbit phase information from quantum oscillations in the ac magnetostrictive coefficient.

cond-mat.str-el↗

Spin nematic liquid crystal and scalar spin chirality in tetragonal lattice YbMnBi$_2$

A spin nematic order, analogous to the nematic liquid crystal, characterizes the spontaneous breaking of spin-space rotational symmetry while preserving time-reversal ($T$) symmetry. In contrast, scalar spin chirality (SSC), a composite three-spin order, breaks $T$ symmetry and is known to induce an anomalous Hall effect (AHE). Although a spin nematic phase has been suggested in frustrated magnets and the square-lattice iridate, how it might affect magnetotransport properties is unknown. Here we use polarized neutron scattering to show that tetragonal $A$MnBi$_2$ ($A$ = Ca, Yb) is a strictly $c$-axis-aligned collinear antiferromagnet (C-type), with $T_N \approx 270$ K and 290 K, respectively. On cooling from 450 K to $T_N$, low-energy spin excitations in YbMnBi$_2$ spontaneously change from isotropic to anisotropic in spin space within the tetragonal plane, forming a dynamic spin nematic phase around 400 K due to heavy Yb-induced spin-orbit coupling, before gapping out below $T_N$. Similar measurements on CaMnBi$_2$ reveal isotropic paramagnetic scattering without a spin nematic phase above $T_N$. Under an in-plane magnetic field, the Yb$^{3+}$ moments may interact with the dynamic spin nematic phase to induce nonzero SSC, giving rise to AHE and an anomalous Nernst effect (ANE) in YbMnBi$_2$ that are absent in CaMnBi$_2$ above $T_N$. A symmetry-based Ginzburg-Landau analysis shows that coupling terms between the nematic order and SSC are allowed under an external magnetic field, which could explain the rapid increase of AHE with field in YbMnBi$_2$. Our results provide compelling evidence for dynamic SSC-induced AHE and ANE in the paramagnetic phase of a compensated collinear antiferromagnet, opening a new avenue for the physics of composite spin orders and room-temperature spintronics without magnetic order.

cond-mat.str-el↗

SNR-Adaptive Unified Diffusion for Multi-Task Medical Image Segmentation

Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding knowledge sharing across anatomically related tasks. Consolidating semi-supervised learning, unsupervised domain adaptation, and domain generalisation into one model is therefore a practical necessity, yet naive joint training exposes a fundamental barrier: conflicting label semantics between datasets collapse LA Dice from 90.31\% to 83.38\%, while gradient imbalance across tasks of unequal complexity suppresses the weaker tasks throughout training. We present UniT-Diff, a unified diffusion segmentation framework that resolves these conflicts through three targeted mechanisms. An 11-channel task-specific output space physically partitions label categories, eliminating cross-task gradient sign reversal by construction. SNR-Adaptive Task Conditioning (SATC) scales the task token by the log signal-to-noise ratio of the current diffusion timestep, suppressing domain-specific bias during coarse denoising and restoring full task guidance as the signal clears. Task-Type-Aware Conditional Dropout (TTACD) permanently removes the task token for domain-generalisation inputs, routing them through a shared neutral pathway that draws on cross-dataset cardiac anatomy rather than source-vendor statistics. Under a single parameter set, UniT-Diff surpasses independently trained task-specific baselines on all three benchmarks simultaneously: +0.87\% on LA, +1.77\% on MMWHS, and +0.88\% on MNMS.

cs.CV↗

An Adaptive Log-Laguerre Spectral Method for the Radial Dirac Equation: Resolving Asymptotic Decay and Core Singularities in Atomic Calculations

The high-precision solution of the radial Dirac equation is fundamental to relativistic quantum chemistry, essential for reliable pseudopotential generation and all-electron electronic structure methods. Capturing both the non-polynomial singularities at the origin and the state-dependent asymptotic decay on semi-infinite domains presents a significant computational challenge. In this work, we propose the Adaptive Log-Laguerre Spectral Method (ALLSM), a novel coupled spectral-element solver that seamlessly integrates three advanced mathematical methodologies into a unified framework. Specifically, Generalized Log-Orthogonal Functions (GLOFs) are deployed in the near-core region to intrinsically approximate complex $r^s$ singular behaviors without requiring prior knowledge of the exact analytical exponent $s$. Concurrently, an adaptive Laguerre spectral method is employed to dynamically capture diverse exponential tails on $[0, \infty)$, avoiding artificial domain truncation. To structurally guarantee spectral purity across this bipartite basis, the framework rigorously incorporates the Inverse Dirac Operator Method (IDOM), effectively eliminating variational collapse and spurious states. Validated across diverse physical regimes, including Coulomb, finite-nucleus, and screened potentials, the proposed solver restores exponential convergence and consistently achieves relative accuracies of $10^{-10}$. This work provides a robust, pollution-free computational kernel for atomic structure calculations, establishing a highly reliable numerical standard for complex molecular simulations.

math.NA↗

UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion

Considering efficiency, ultra-high-definition (UHD) low-light image restoration is extremely challenging. Existing methods based on Transformer architectures or high-dimensional complex convolutional neural networks often suffer from the "memory wall" bottleneck, failing to achieve millisecond-level inference on edge devices. To address this issue, we propose a novel real-time UHD low-light enhancement network based on geometric feature fusion using Clifford algebra in 2D Euclidean space. First, we construct a four-layer feature pyramid with gradually increasing resolution, which decomposes input images into low-frequency and high-frequency structural components via a Gaussian blur kernel, and adopts a lightweight U-Net based on depthwise separable convolution for dual-branch feature extraction. Second, to resolve structural information loss and artifacts from traditional high-low frequency feature fusion, we introduce spatially aware Clifford algebra, which maps feature tensors to a multivector space (scalars, vectors, bivectors) and uses Clifford similarity to aggregate features while suppressing noise and preserving textures. In the reconstruction stage, the network outputs adaptive Gamma and Gain maps, which perform physically constrained non-linear brightness adjustment via Retinex theory. Integrated with FP16 mixed-precision computation and dynamic operator fusion, our method achieves millisecond-level inference for 4K/8K images on a single consumer-grade device, while outperforming state-of-the-art (SOTA) models on several restoration metrics.

eess.IV↗

Selective Actuation Enabled Multifunctional Magneto-mechanical Metamaterial for Programming Elastic Wave Propagation

Active metamaterials are a type of metamaterial with tunable properties enabled by structural reconfigurations. Existing active metamaterials often achieve only a limited number of structural reconfigurations upon the application of an external load across the entire structure. Here, we propose a selective actuation strategy for inhomogeneous deformations of magneto-mechanical metamaterials, which allows for the integration of multiple elastic wave tuning functionalities into a single metamaterial design. Central to this actuation strategy is that a magnetic field is applied to specific unit cells instead of the entire metamaterial, and the unit cell can transform between two geometrically distinct shapes, which exhibit very different mechanical responses to elastic wave excitations. Our numerical simulations and experiments demonstrate that the tunable response of the unit cell, coupled with inhomogeneous deformation achieved through selective actuation, unlocks multifunctional capabilities of magneto-mechanical metamaterials such as tunable elastic wave transmittance, elastic waveguide, and vibration isolation. The proposed selective actuation strategy offers a simple but effective way to control the tunable properties and thus enhances the programmability of magneto-mechanical metamaterials, which also expands the application space of magneto-mechanical metamaterials in elastic wave manipulation.

physics.app-ph↗

Magnetic Milli-spinner for Robotic Endovascular Surgery

Vascular diseases such as thrombosis, atherosclerosis, and aneurysm, which can lead to blockage of blood flow or blood vessel rupture, are common and life-threatening. Conventional minimally invasive treatments utilize catheters, or long tubes, to guide small devices or therapeutic agents to targeted regions for intervention. Unfortunately, catheters suffer from difficult and unreliable navigation in narrow, winding vessels such as those found in the brain. Magnetically actuated untethered robots, which have been extensively explored as an alternative, are promising for navigation in complex vasculatures and vascular disease treatments. Most current robots, however, cannot swim against high flows or are inadequate in treating certain conditions. Here, we introduce a multifunctional and magnetically actuated milli-spinner robot for rapid navigation and performance of various treatments in complicated vasculatures. The milli-spinner, with a unique hollow structure including helical fins and slits for propulsion, generates a distinct flow field upon spinning. The milli-spinner is the fastest-ever untethered magnetic robot for movement in tubular environments, easily achieving speeds of 23 cm/s, demonstrating promise as an untethered medical device for effective navigation in blood vessels and robotic treatment of numerous vascular diseases.

cs.RO↗

Milli-spinner thrombectomy

Blockage of blood flow in arteries or veins by blood clots can lead to serious medical conditions. Mechanical thrombectomy (MT), minimally invasive endovascular procedures that utilize aspiration, stent retriever, or cutting mechanisms for clot removal have emerged as an effective treatment modality for ischemic stroke, myocardial infarction, pulmonary embolism, and peripheral vascular disease. However, state-of-the-art MT technologies still fail to remove clots in approximately 10% to 30% of patients, especially when treating large-size clots with high fibrin content. In addition, the working mechanism of most current MT techniques results in rupturing or cutting of clots which could lead to clot fragmentation and distal emboli. Here, we report a new MT technology based on an unprecedented mechanism, in which a milli-spinner mechanically debulks the clot by densifying its fibrin fiber network and discharging red blood cells to significantly reduce the clot volume for complete clot removal. This mechanism is achieved by the spin-induced compression and shearing of the clot. We demonstrate its effective clot-debulking performance with clot volumetric reduction of up to 90% on various sizes of clots with diverse clot compositions. Milli-spinner MT in both in-vitro pulmonary and cerebral artery flow models and in-vivo swine models demonstrate high-fidelity revascularization. The milli-spinner MT is the first reported mechanism that directly modifies the clot microstructure to facilitate clot removal, which also results in markedly improved MT efficacy compared to the existing MT mechanisms that are based on clot rupturing and cutting. This technology introduces a unique mechanical way of debulking and removing clots for future MT device development, especially for the treatment of ischemic stroke, pulmonary emboli, and peripheral thrombosis.

physics.app-ph↗

AI-Olympics: Exploring the Generalization of Agents through Open Competitions

Between 2021 and 2023, AI-Olympics, a series of online AI competitions was hosted by the online evaluation platform Jidi in collaboration with the IJCAI committee. In these competitions, an agent is required to accomplish diverse sports tasks in a two-dimensional continuous world, while competing against an opponent. This paper provides a brief overview of the competition series and highlights notable findings. We aim to contribute insights to the field of multi-agent decision-making and explore the generalization of agents through engineering efforts.

cs.MA↗

Airline recovery problem under disruptions: A review

In practice, both passenger and cargo flights are vulnerable to unexpected factors, such as adverse weather, airport flow control, crew absence, unexpected aircraft maintenance, and pandemic, which can cause disruptions in flight schedules. Thus, managers need to reallocate relevant resources to ensure that the airport can return to normal operations on the basis of minimum cost, which is the airline recovery problem. Airline recovery is an active research area, with a lot of publications in recent years. To better summarize the progress of airline recovery, first of all, keywords are chosen to search the relevant studies, then software is used to analyze the existing studies in terms of the number of papers, keywords, and sources. Secondly, the airline recovery problem is divided into two categories, namely Passenger-Oriented Airline Recovery Problem (POARP) and Cargo-Oriented Airline Recovery Problem (COARP). In POARP, the existing studies are classified according to recovery strategies, including common recovery strategies, cruise speed control strategy, flexible aircraft maintenance strategy, multi-modal transportation strategy, passenger-centric recovery strategy, and clubbing of flights strategy. Moreover, the POARP is discussed from the perspectives of disruption types, recovery strategies, problem types, objective functions, and solution methods. Thirdly, POARP and COARP are compared from the perspectives of timeliness, subjectivity, flexibility, transferability, and combinability. Finally, the conclusions are drawn and future study directions are provided. For future studies, it is recommended to conduct more in-depth research on dynamic and real-time recovery, incorporating human factors into the modeling, multi-modal transportation coupling, optimization of other airport processes, combination of robust scheduling and airline recovery, and optimization algorithm improvement.

math.OC↗

Phase-field simulations of the effect of temperature and interface for zirconium $δ\mbox{-}$hydrides

Hydride precipitation in zirconium cladding materials can damage their integrity and durability.Service temperature and material defects have a significant effect on the dynamic growth of hydrides. In this study, we have developed a phase field model based on the assumption of elastic behaviour within a specific temperature range (613-653K). This model allows us to study the influence of temperature and interfacial effects on the morphology, stress, and average growth rate of zirconium hydride. The results suggest that changes in temperature and interfacial energy influence the aspect ratio and average growth rate of the hydride morphology. The ultimate determinant of hydride orientation is the loss of interfacial coherence, primarily induced by interfacial dislocation defects and quantifiable by the mismatch degree $q$. An escalation in interfacial coherence loss leads to a transition of hydride growth from horizontal to vertical, accompanied by the onset of redirection behaviour. Interestingly, redirection occurs at a critical mismatch level, denoted $q_c$, and remains unaffected by variations in temperature and interfacial energy. However, this redirection leads to an increase in the maximum stress, which may influence the direction of hydride crack propagation. This research highlights the importance of interfacial coherence and provides valuable insights into the morphology and growth kinetics of hydrides in zirconium alloys.

cond-mat.mtrl-sci↗

Physics-aware differentiable design of magnetically actuated kirigami for shape morphing

Shape morphing that transforms morphologies in response to stimuli is crucial for future multifunctional systems. While kirigami holds great promise in enhancing shape-morphing, existing designs primarily focus on kinematics and overlook the underlying physics. This study introduces a differentiable inverse design framework that considers the physical interplay between geometry, materials, and stimuli of active kirigami, made by soft material embedded with magnetic particles, to realize target shape-morphing upon magnetic excitation. We achieve this by combining differentiable kinematics and energy models into a constrained optimization, simultaneously designing the cuts and magnetization orientations to ensure kinematic and physical feasibility. Complex kirigami designs are obtained automatically with unparallel efficiency, which can be remotely controlled to morph into intricate target shapes and even multiple states. The proposed framework can be extended to accommodate various active systems, bridging geometry and physics to push the frontiers in shape-morphing applications, like flexible electronics and minimally invasive surgery.

physics.app-ph↗

Stiffness Change for Reconfiguration of Inflated Beam Robots

Active control of the shape of soft robots is challenging. Despite having an infinite number of passive degrees of freedom (DOFs), soft robots typically only have a few actively controllable DOFs, limited by the number of degrees of actuation (DOAs). The complexity of actuators restricts the number of DOAs that can be incorporated into soft robots. Active shape control is further complicated by the buckling of soft robots under compressive forces; this is particularly challenging for compliant continuum robots due to their long aspect ratios. In this work, we show how variable stiffness can enable shape control of soft robots by addressing these challenges. Dynamically changing the stiffness of sections along a compliant continuum robot can selectively "activate" discrete joints. By changing which joints are activated, the output of a single actuator can be reconfigured to actively control many different joints, thus decoupling the number of controllable DOFs from the number of DOAs. We demonstrate embedded positive pressure layer jamming as a simple method for stiffness change in inflated beam robots, its compatibility with growing robots, and its use as an "activating" technology. We experimentally characterize the stiffness change in a growing inflated beam robot and present finite element models which serve as guides for robot design and fabrication. We fabricate a multi-segment everting inflated beam robot and demonstrate how stiffness change is compatible with growth through tip eversion, enables an increase in workspace, and achieves new actuation patterns not possible without stiffening.

cs.RO↗