Search arXiv⌕ Search

arXiv subjects

Ping Wang

Publications and source records attributed to Ping Wang.

At least 19 recordsLinked to original sources
arXiv2026

Testimony from Timelines: Evidence-Grounded Significance Testing of Temporal Clinical Hypotheses

Ask a language model whether sales tend to dip after a product recall, or whether one side effect tends to follow another after a vaccine, and it answers in a fluent sentence that reads like a finding, with no test behind it. Assertions about how events unfold across many cases fill the Web, and each is a temporal hypothesis that only a significance test over the right records can settle. The verifier must specify the null, select the test and decide which records bear on the hypothesis, and any of these choices can go wrong while the conclusion still comes out right. Yet benchmarks for language-model data analysis grade only the conclusion, with the relevant data handed over. We study the problem in health, where a wrong verdict is costly, and present STRATA, a benchmark that grades every decision on the way to a verdict: 8,735 hypotheses over the clinical timelines of vaccine adverse-event reports, with gold plans, evidence sets, p-values and verdicts derived under a released codebook and reproduced by a deterministic oracle. We also propose ART (articulate, retrieve, test), a staged paradigm that exposes each decision as an inspectable output. Extensive experiments with five model configurations show that systems fail mostly at choosing which records count, a verdict-evidence gap that accuracy alone conceals. ART closes most of this gap and brings a 31B open model to within 0.01 of the frontier models under the same paradigm; the frontier models succeed once given the codebook.

cs.CL↗
arXiv2026

Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents

Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own data against few baselines, so it is unknown whether this design beats letting a capable model investigate on its own. We compare three simple harnesses that prescribe none of the model's calls (one call over an evidence package, a SQL agent and the Codex coding agent) with five published LLM RCA agents and with statistical and causal methods on RCAtlas, 90 validated cases from eight public datasets, across six models and three reasoning efforts. The simple harnesses are the most accurate (PR@1 65-77% on three mid-tier models), ahead of the published agents (16-53%) and the non-LLM methods (6-39%), on every model on which both families were run. The published agents fix from a tenth to all of their model calls in the program, and a case study shows how these prescriptions skip the decisive evidence. A stronger model mainly improves reliability, a multi-turn harness mainly improves aptitude, and more reasoning effort changes accuracy by a few points at most while multiplying the time by up to seven. Among runs more accurate than the best non-LLM method, every Pareto-optimal run in cost or time uses a simple harness.

cs.AI↗
arXiv2026

Stochastic Geometry Analysis and Optimization for Multi-LEO Satellite-Assisted Communications

Low Earth orbit (LEO) satellites are vital in providing seamless connectivities to ground users (GUs). However, complex satellite-to-ground propagation and non-negligible satellite failure probabilities make single-satellite transmission unreliable. To address this issue, we consider a multi-LEO-satellite communication network (mLEO-CN), where a typical GU is served by multiple LEO satellites. The satellite locations are modeled as a binomial point process on a sphere and ordered according to their distances to the GU. To improve communication reliability, a serial communication scheme is adopted, in which the subsequent satellite is activated only when all preceding satellites fail to satisfy the target signal-to-noise ratio threshold. By employing the tool of stochastic geometry, we derive key performance metrics, including overall transmission success probability, average transmission rate, and end-to-end delay under the serial communication scheme by incorporating both shadowed Rician (SR) fading and satellite failure probabilities. To improve analytical tractability, we derive asymptotic expressions for the end-to-end transmission success probability in two special cases by leveraging the asymptotic expression of the SR fading model and a Gamma-distribution, and further propose a cluster-based approximation approach for the overall transmission success probability. Building on these analyses, we formulate an optimization problem to maximize the ratio of the overall transmission success probability to the end-to-end delay, and obtain its solution using a one-dimensional search approach. Numerical results validate the analysis, reveal the impact of key parameters, and identify the optimal number of serving LEO satellites under different constellation altitudes.

eess.SP↗
arXiv2026

Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers

Diffusion Transformers (DiTs) have become a common backbone for high-quality text-to-image and text-to-video generation, but repeated dense self-attention remains a major inference bottleneck as token sequences grow and the same operator is invoked across many denoising steps. Our study suggests that dense attention in pretrained DiTs contains reusable layer/head-specific high-mass structure that can be identified from a small offline calibration set and reused across future generations. This leads to Sink-Sparse Hybrid Attention, a train-free attention replacement that reuses static sink masks and supplements them with a lightweight pooled-KV branch, while leaving model weights and sampling schedules unchanged. On Wan2.1-T2V-1.3B, the method attains 1.54$\times$ end-to-end speedup while maintaining generation quality. On Z-Image-Turbo, it attains 1.57$\times$ end-to-end speedup with competitive GenEval2 performance. These results indicate that reusable importance-aware sparse support can provide an effective train-free acceleration path for both T2V and T2I DiTs.

cs.CV↗
arXiv2026

Rubric-Based Optimization for Text-to-Music Generation

Post-training text-to-music generation requires reward signals that capture multiple aspects of musical quality beyond what any single automatic metric can measure. We study structured, rubric-based rewards from pretrained audio-language models (ALMs) as training signals for both autoregressive and diffusion-based music generators. An ALM scores each generated clip against the rubric; we rank candidates generated for the same text prompt by their scores and convert these rankings into preference pairs for DPO on both MusicGen-small and ACE-Step v1, and additionally use the rubric scores directly as scalar rewards for DiffusionNFT on ACE-Step v1. On MusicCaps, rubric-based optimization improves CLAP, SongEval, and Audiobox-Aesthetics simultaneously, with the strongest gains obtained by DiffusionNFT on ACE-Step. By contrast, on MusicGen-small, building preferences from any one of these automatic evaluators produces clear cross-metric trade-offs: the targeted evaluator improves while other independent evaluators deteriorate. We further study tempo, key, and instrumentation, where precise objective rewards are available. Directly optimizing these specialized rewards reliably improves the target attributes, whereas ALM rubrics provide only partial transfer for tempo and instrumentation and no measurable improvement for key. Together, these results suggest a practical division of labor: ALM rubrics are effective for broad perceptual qualities that are difficult to formalize, while specialized objective rewards remain preferable when reliable measurements are available.

cs.SD↗
arXiv2026

Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case

Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is enough to close the case. We study this decision for LLM investigators, which request evidence from a case file, revise their hypotheses, and either close the case with a conclusion grounded in what they read or leave it open and name what is missing. This judgment does not come with capability: an untrained 9B model overstates its evidence in 97% of its answers, and a frontier model that identifies the right cause in 84% of cases still overstates in 91% and closes 17 of the 41 cases whose official finding is "cause undetermined". Measuring it is also non-trivial: the source of a case largely predicts its label, and a rule that reads only the source reaches 83.0 balanced accuracy on our test cases. We therefore evaluate closure with three tests: closure accuracy, reported against this rule and within each source; evidence dependence, which removes the grounds of a conclusion and checks whether the model stops closing; and conclusion and gap quality, a judged checklist of what the model asserts and what it says is missing. We build Nautil, 731 audited cases from aviation, rail, maritime, chemical-safety and vehicle-defect reports and production server incidents, with teacher trajectories, an out-of-distribution test set and counterfactual evidence versions. Fine-tuning a 9B model on these trajectories makes its closures follow the evidence: removing the grounds lowers its closure rate by 26 points relative to a matched control, overstatement falls from 97% to 35%, and correct, non-overstated conclusions rise from 3% to 43%. Reinforcement learning that rewards only the closure decision then raises balanced accuracy from 69.2 to 83.3, on par with the teacher, and within-source accuracy from 60.4 to 74.1, at some cost in evidence dependence.

cs.CL↗
arXiv2026

SkillSeek: Revisiting Agent Skill Retrieval at Marketplace Scale

Anthropic's Agent Skills package reusable procedural know-how for an LLM agent into SKILL.md directories, and open-source aggregations have grown past 230,000 skills, making selection rather than authoring the bottleneck. The standing answer in the literature outsources selection to the agent itself: an LLM-mediated retrieval loop that rewrites queries and refines candidates inside the agent's decision loop, paying LLM tokens on every task. We present SkillSeek, an open-source two-stage skill retriever built from the standard IR recipe (a BGE-base bi-encoder feeding a small cross-encoder, exposed over MCP). Across a $4 \times 11$ grid of pool, backbone, and method on the 89-task SkillsBench benchmark, SkillSeek reaches observed parity with the LLM-mediated loop of Liu et al. at essentially no extra cost: plain bm25 alone records a pass rate at or above their refined loop on three of four settings, and a small cross-encoder covers the remaining difference on the fourth. A first-stage recall ceiling explains the pattern, and total per-trial spend drops from USD 51.30 to USD 27.54 (within fifty cents of the no-skill baseline). Under the SkillsBench tasks and OpenHands harness we tested, this positions the standard IR recipe as a strong default for agent-skill retrieval, with LLM-mediated alternatives a natural fit for cases where deterministic methods fall short.

cs.IR↗
arXiv2026

Fast-Convergent Meta-RL via Gradient-Clustered BS Sampling for Edge Caching

Wireless edge caching networks typically consist of many independent Base Stations (BSs), each facing its own request rate and content popularity profile. Training a Reinforcement Learning (RL) caching agent from scratch at every BS forces each agent to relearn, through slow trial and error, a decision problem that is structurally identical across the network. Meta-reinforcement learning removes this redundancy by learning a shared initialization that adapts to any BS in a few local updates; however, meta-training itself becomes the bottleneck at scale: the meta-gradient must be estimated from a small subset of BSs at each meta-iteration, and sampling this subset uniformly at random yields a high-variance estimate, an issue existing meta-RL caching frameworks leave unaddressed. This paper proposes a meta-reinforcement learning framework for caching across independent, non-overlapping BSs that directly targets this bottleneck. Each BS runs a local Proximal Policy Optimization (PPO) agent, formulated as a Semi-Markov Decision Process (SMDP) over content popularity, size, lifetime, and importance, while a shared meta-policy is learned via a Model-Agnostic Meta-Learning (MAML)-style loop. To scale meta-training and accelerate convergence, we introduce gradient-based clustering, which groups BSs by local gradient similarity and draws from every cluster, in proportion to its size, at each meta-iteration. We prove, via an Analysis of Variance (ANOVA)-style decomposition of gradient variance, that this strategy yields a strictly lower-variance meta-gradient estimator than uniform random sampling under BS heterogeneity.

cs.NI↗
arXiv2026

Study of dynamical dark energy using DESI DR2 BAO, CMB, and Type Ia Supernovae data

Dark Energy Spectroscopic Instrument (DESI) Collaboration reported an evidence for dynamical dark energy model using baryon acoustic oscillation (BAO) measurements from DESI Data Release 2 (DR2), cosmic microwave background (CMB), and three Type Ia Supernovae (SNe) data (Pantheon+, Union3, and DES-SN5YR) recently. The significances are from $2.8\sim4.2σ$ depending on which SNe sample is used, and the highest significance is obtained based on the DES-SN5YR data. But more recently, Dark Energy Survey (DES) Collaboration recalibrated the DES-SN5YR data, and a significance of only $3.2σ$ is obtained based on the calibrated data, which is called DES-Dovekie. In this work, we perform a comprehensive analysis of five representative dynamical dark energy parametrization models, including Chevallier-Polarski-Linder (CPL), Barboza-Alcaniz (BA), exponential (EXP), logarithmic (LOG), and Jassal-Bagla-Padmanabhan (JBP), using DESI DR2 BAO, Planck CMB, ACT DR6, and SNe data from Pantheon+, Union3, and DES-Dovekie. Similarly, a significance of around $3σ$ is obtained based on the DES-Dovekie data. And the significances are $2.1\sim3.7σ$ for different SNe samples and different parametrization models, indicating an evolutionary dark energy dynamics. Furthermore, a phantom-like behavior in the past and has transitioned into quintessence-like behavior today for the dynamical dark energy is preferred.

physics.gen-ph↗
arXiv2026

Contrast-Free Autonomous Navigation of Untethered Endovascular Microrobots Using Single-Plane Fluoroscopy

Reliable three-dimensional (3D) navigation of magnetically actuated untethered microrobots remains a major barrier to clinical translation. X-ray fluoroscopy is the standard real-time imaging modality for endovascular procedures, but single-plane fluoroscopy provides only a two-dimensional (2D) projection, eliminating depth information and complicating autonomous navigation. Recovering this information through biplane imaging or repeated contrast-enhanced angiography increases procedural complexity, radiation exposure, or contrast burden. Here, we introduce VISTA (Virtual Integration for Spatial Tracking and Autonomy), a digital twin framework enabling contrast-free autonomous navigation under single-plane fluoroscopy. VISTA reconstructs vascular anatomy as a 3D digital twin, discretizes the vessel centerline into navigation milestones, and assigns the detected 2D robot position to the nearest projected milestone. Consecutive milestones define the local vessel orientation used to generate magnetic actuation commands, converting single-plane fluoroscopic observations into topology-constrained navigation states without requiring contrast injection during navigation. VISTA is demonstrated across anatomically distinct vascular phantoms under continuous flow and within the inferior vena cava of a live rat in vivo. Compared with conventional fluoroscopic human-in-the-loop control, VISTA reduced navigation time by up to 62%, corrective actuation commands by up to 98%, and radiation exposure by up to 57%. These results establish VISTA as a digital twin-guided framework for contrast-free autonomous navigation of untethered endovascular microrobots using widely available single-plane fluoroscopy.

cs.RO↗
arXiv2026

From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact Perturbations

Large language models (LLMs) frequently produce confident yet factually incorrect responses when user inputs contain misleading premises, a phenomenon we attribute to fact perturbations in the input. Existing approaches to hallucination mitigation typically assume reliable user inputs, overlooking how such factual errors can actively mislead model reasoning. To address this vulnerability, we propose DEDUCE, a three-stage framework that transforms LLMs from passive responders into proactive error correctors. DEDUCE operates in three stages: (1) detect errors through fine-grained fact extraction and verification; (2) devise correction strategies via multi perspective deliberation; and (3) correct misconceptions while delivering reliable answers. We also present MisFactQA, a dataset containing factual errors of varying degrees, and propose new metrics for evaluating model robustness. Experiments on TruthfulQA, FalseQA, and our MisFactQA benchmark demonstrate that DEDUCE significantly improves both accuracy and error correction capability. Consistent gains across Qwen, LLaMA, and Gemma families confirm its effectiveness and scalability.

cs.CL↗
arXiv2026

CRAFT: LLM-Based Iterative Refinement for Temporal Reasoning over Clinical Narratives

Understanding the temporal progression of symptoms in clinical narratives is critical for disease monitoring, safety surveillance, and causality assessment. Clinical narratives, however, rarely provide explicit temporal anchors. Current approaches to temporal information reasoning focus predominantly on pairwise relation classification across multi-visit and timestamp-rich records, leaving the reconstruction of structured symptom trajectories from individual anchor-sparse reports largely unaddressed. We propose CRAFT, an LLM framework that pairs a generator with a constraint-based verifier to iteratively produce and refine stage-wise symptom timelines through targeted feedback. We conduct evaluation on MedTempo, a new benchmark of 5,347 vaccine adverse-event narratives spanning three COVID-19 vaccine types, with expert-validated temporal stage annotations for 3,166 reports. Experiments across four LLM backbones demonstrate that CRAFT consistently improves temporal ordering accuracy, with ablation analysis isolating the contribution of generator and verifier components across model capability levels.

cs.CL↗
arXiv2026

GS$^{2}$CI: Robust Gaussian Splatting For Snapshot Compressive Imaging via Large Vision Model Priors

Snapshot Compressive Imaging (SCI) offers an efficient solution for high-speed video acquisition and, under exposure-time camera--scene relative motion, multi-view scene capture by compressing temporal or spatial information into a single 2D measurement. While recent studies have explored SCI for 3D scene reconstruction, existing methods struggle with significant challenges due to information loss, limited viewpoint diversity, and the computational burden of jointly optimizing 3D representations and camera poses. In this work, we propose a novel framework that reconstructs high-quality 3D scenes from a single SCI measurement by leveraging 3D Gaussian Splatting (3DGS) and the powerful priors of large-scale vision foundation models (VFMs). Our primary reconstruction combines measurement-derived 3D VFM initialization with SCI-aware Gaussian optimization. After coarse-stage convergence, an auxiliary 2D VFM provides pseudo-view supervision at synthesized viewpoints for local appearance refinement. To further address the instability caused by ambiguous SCI supervision during 3DGS optimization, we introduce Opacity-Guided Splitting and Growth Regulation (OSGR), an SCI-specific densification strategy that augments split candidates using local opacity statistics, discourages loss-compensating opacity inflation through mean-opacity regulation, and bounds representation growth with explicit candidate-ratio and Gaussian-count constraints. Extensive experiments across multiple benchmarks demonstrate that our method achieves the strongest overall performance, combining leading reconstruction quality and robustness to viewpoint variation with competitive computational efficiency.

cs.CV↗
arXiv2026

A Dual Evaluation for Music Transcription

Automatic music transcription systems produce sheet music that can be read and played back. We argue that these two targets call for complementary evaluations of notation similarity to a reference score and playback similarity to the original performance, respectively. Our study considers notation similarity metrics from the optical music recognition literature and a wide range of playback-similarity methods validated through a listening study across over 100 participants and 230 piano recordings covering 23 works, 30 performers, and six composers. We find, fortuitously, that the playback similarity metric that correlates best with human judgments, CLEWS, is also the cheapest to run. We also find that the two evaluation dimensions favor different systems among a collection of 24 pipelines formed by pairing eight audio-to-MIDI models with three MIDI-to-score converters, with the latter component systematically determining the favored objective. The complementarity between metrics also holds when adding to the pool Rubato, a new end-to-end system that offers substantially improved notation similarity while remaining competitive, though not the best, on playback similarity.

cs.SD↗
arXiv2026

Erodible bed turbulence modulation driven by transition between longitudinal and transverse bedforms at varying Shields numbers

The mechanism of turbulence modulation in particle-laden flow over erodible beds remains an open question. Using particle-resolved direct numerical simulations, this study realises a longitudinal-to-transverse bedform transition by varying the Shields number, revealing non-monotonic modulation of near-wall turbulence. At low Shields numbers, streamwise sediment ridges generate form-induced streaks that produce a distinct secondary peak in the premultiplied energy spectra, exceeding the conventional near-wall turbulent peak and enhancing the turbulent kinetic energy. As the Shields number increases, saltation intensifies and disrupts these structures, causing the secondary peak to vanish in the streamwise direction and weaken in the spanwise direction, thereby suppressing turbulence. Proper orthogonal decomposition of the bed surface reveals a redistribution of modal contribution from a single dominant mode to higher-order modes, with longitudinal features persisting as remnants, directly linking bedform evolution to turbulence modulation.

physics.flu-dyn↗
arXiv2026

BayesSeg: A Bayesian Optimization Framework for State Segmentation of Electricity Consumption Time Series

In Non-Intrusive Load Monitoring (NILM), adaptive segmentation of electricity consumption time series is critical for appliance recognition. However, prevailing methods face challenges including heuristic parameter tuning, boundary sensitivity, and metric saturation. This paper proposes BayesSeg, a unified framework integrating time-series segmentation, multidimensional evaluation, and automatic parameter optimization. The segmentation layer employs a dual steady-state criterion based on the tail value and mean of preceding subsequences, combined with a sequential extraction and complement-set parsing strategy, to achieve precise unsupervised partitioning of steady-state and transition-state segments. The evaluation layer maps segmentation results to binary state sequences and formulates a composite metric integrating an event-level F1 score (event_F1) with Normalized Mutual Information (NMI). The event_F1 quantifies switching-event precision and recall via tolerance matching, while NMI captures global structural consistency, jointly overcoming the boundary sensitivity and limited discriminability of point-wise metrics. In the optimization layer, the composite score serves as the objective function for Bayesian optimization, which constructs a TPE surrogate model for efficient global parameter-space exploration. Experiments on the SustDataED2 dataset demonstrate that Bayesian optimization requires only ~100 objective evaluations to locate a parameter region within 0.35% deviation of the exhaustive grid-search optimum. The framework achieves a weighted composite score of 0.7149 and an event_F1 of 0.9340 while reducing optimization latency from ~5300 seconds to under 1 second, a speedup exceeding 5700x. BayesSeg automates segmentation configuration and provides a scalable, efficient solution for time-series analysis in NILM and related domains.

cs.AI↗
arXiv2026

Intelligent Multi-UAV Navigation in ITNTNs: A Hierarchical LLM Approach

The deployment of high-speed Uncrewed Aerial Vehicles (UAVs) in 3D aerial highways necessitates robust coordination of physical flight kinematics and multi-tier network handovers. While Deep Reinforcement Learning (DRL) offers rapid tactical control, it lacks the zero-shot strategic reasoning required to quickly adapt to dynamic Integrated Terrestrial and Non-Terrestrial Networks (ITNTNs). Conversely, Large Language Models (LLMs) excel at semantic reasoning but suffer from high inference latency, rendering them unsuitable for real-time aerodynamic control. To bridge this gap, we propose a novel Hierarchical LLM-driven control framework. A massive cloud-based LLM deployed on a High-Altitude Platform Station (HAPS) manages slow-timescale global load balancing, while lightweight edge-LLMs on individual UAVs translate local observations into tactical sub-goals. These sub-goals guide a fast-timescale physical DRL controller to execute collision-free, handover-aware trajectories. Simulation results demonstrate that our agentic architecture significantly reduces collision rates and improves aggregate system throughput compared to existing baselines.

cs.RO↗
arXiv2026

PolarAPP: Beyond Polarization Demosaicking for Polarimetric Applications

Polarimetric imaging enables advanced vision applications such as normal estimation and de-reflection by capturing unique surface-material interactions. However, existing applications (alternatively called downstream tasks) rely on datasets constructed by naively regrouping raw measurements from division-of-focal-plane sensors, where pixels of the same polarization angle are extracted and aligned into sparse images without proper demosaicking. This reconstruction strategy results in suboptimal, incomplete targets that limit downstream performance. Moreover, current demosaicking methods are task-agnostic, optimizing only for photometric fidelity rather than utility in downstream tasks. Towards this end, we propose PolarAPP, the first framework to jointly optimize demosaicking and its downstream tasks. PolarAPP introduces a feature alignment mechanism that semantically aligns the representations of demosaicking and downstream networks via meta-learning, guiding the reconstruction to be task-aware. It further employs an equivalent imaging constraint for demosaicking training, enabling direct regression to physically meaningful outputs without relying on rearranged data. Finally, a task-refinement stage fine-tunes the task network using the stable demosaicking front-end to further enhance accuracy. Extensive experimental results demonstrate that PolarAPP outperforms existing methods in both demosaicking quality and downstream performance. Code is available upon acceptance.

cs.CV↗