arXiv subjects

Peng Wang

Publications and source records attributed to Peng Wang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Exact branch-transfer criterion for common-mode Thomson heat cancellation in thermoelectric couples

Thermoelectric p- and n-type legs are commonly paired by matching their Seebeck magnitudes, although a cooler responds to heat transported through its complete electrical and thermal network. We decompose the leg coefficients into differential thermopower $α=S_p-S_n$ and common thermopower $M=(S_p+S_n)/2$. In a connected steady-state scalar thermoelectric network, a temperature-independent co-shift applied to every electrically active segment is an exact terminal null. A temperature-dependent perturbation of the legs relative to fixed leads is instead physical. At fixed current and shared isothermal endpoints, its first-order cold-port response is the action of $Γ_m=T\,dm/dT$ on the difference between the p- and n-branch oriented collection measures. We prove that every continuous $Γ_m$ cancels if and only if these measures are equal. In the constant-property, linear-common-mode limit, matching $R_i/K_i^{\rm leg}$ is sufficient and does not require identical legs. One- and two-dimensional calculations confirm the analytic reductions within their stated domains. For split thermal pads, the analysis gives the exact array law $ΔQ_{c,Σ}=\sum_j C_jI_jΔT_{c,j}$ and, for series elements with isothermal hot pairs, $IΔV_Σ=-ΔQ_{c,Σ}$. A representative seven-pair model gives corresponding increments of 7.87 mW and $-2.80$ mV. Branch transfer and endpoint topology therefore provide distinct material-pairing and device-test criteria for common-mode Thomson heat.

cond-mat.mtrl-sci↗

arXiv2026

Giant bulk photovoltaic effect driven by interfacial symmetry breaking in MoS2/Ta2NiSe5 heterostructures

Van der Waals (vdW) heterostructures offer a versatile platform for engineering unconventional bulk photovoltaic (BPV) effect through interfacial symmetry breaking. However, the coexistence of multiple photophysical mechanisms, driven by structural complexity, spontaneous charge transfer, and strong interlayer coupling, often obscures the microscopic origin of the BPV response and hinders its rational optimization. Here, we demonstrate a pronounced BPV effect localized at the overlap region of a cross-bar MoS2/Ta2NiSe5 vdW heterostructure, where symmetry breaking induced by vertical stacking lifts the inversion center of MoS2. The orthogonal device geometry enables the independent probing of intralayer and interfacial photoresponse pathways, facilitating clear separation of competing mechanisms. Spontaneous interfacial charge transfer between MoS2 and Ta2NiSe5 further establishes a strong interlayer electronic coupling. By modulating the interlayer potential landscape through gate voltage and vertical electric fields, we achieve an optimized zero-bias photocurrent density of 247 A/cm2 and a BPV coefficient of 0.99 V-1. Supported by theoretical modelling, our results illustrate how minimalist device geometry can transform complex heterostructures into experimentally tractable platforms. This strategy paves the way for analyzing and optimizing interface-driven BPV effect, with implications for self-powered optoelectronics, broadband photodetection, and energy-harvesting nanodevices.

cond-mat.mes-hall↗

arXiv2026

TAGR: Temporally Adaptive Generative Recommendation for Industrial Live-Streaming Advertising

Live-streaming advertising is an important monetization channel on short-video and e-commerce platforms, where rapidly changing live content, promoted products, and user feedback impose strong freshness requirements on recommendation models. Existing generative recommenders designed for static domains fail at three levels: static semantic IDs (SID) cannot track evolving live ads; single-scale behavior modeling misses shifting intent; preference optimization conflicts between fresh on-policy feedback and training stability. We propose TAGR, a generative recommendation framework with temporal adaptation at three levels: live-ad tokenization, user intent modeling, and preference alignment. At the token level, Live Semantic-Collaborative ID (LSID) periodically refreshes each active ad's SID based on its current live scene and promoted products, while retaining a stable hierarchical token vocabulary for autoregressive generation. At the intent level, Intent-Aware Generation (IAG) models live-room entry histories at multiple temporal granularities as the primary intent sequence, keeps auxiliary behaviors as separate inputs, and weights next-token prediction (NTP) using post-request intent evidence and business value. At the alignment level, Intermittent On-Policy Preference Optimization (IOPO) periodically samples fresh candidate groups from the current policy and performs behavior- and value-aligned preference updates interleaved with supervised NTP maintenance to preserve learned behavior distribution. Deployed on a large-scale e-commerce live-stream advertising platform, TAGR improves live-room entry and shopping-cart click rates by 8.5% and 7.4%, respectively, and achieves a 16.1% revenue lift over the production baseline. These results demonstrate the effectiveness and industrial viability of temporally adaptive generative recommendation for live-stream advertising.

cs.IR↗

arXiv2026

Observational Evidence for the Kinematic Memory of Cosmic Filaments from Satellite Orbital Orientations

We present an observational study of the kinematic coherence between satellite orbital planes and the cosmic web. Using the SDSS DR12 galaxy sample combined with the Bisous filament catalogue, we investigate whether the orbital motion of satellites preserves the memory of filamentary accretion. For each satellite system, we define a projected orbital-normal vector using galaxy sky positions and line-of-sight velocity offsets. By measuring the angle $θ$ between this vector and the local projected filament direction, we detect a distinctive preferred orientation: satellite orbital planes tend to contain or lie parallel to the filament axis. This signal deviates from the isotropic expectation at a high significance level of $12.8σ$. The strength of this kinematic connection depend strongly on environment and host properties. The preference for orbital planes to track the filament direction is most pronounced for groups in close distance to the filament spine and for more massive hosts. Conversely, at intermediate distances from the filament and at large group-centric radii, the signal reverses, indicating a tendency for orbital planes to be oriented perpendicular to the filament. Our findings provide direct observational evidence for the two-phase model of filamentary accretion, where a transition from initial perpendicular collapse toward the filament spine to subsequent parallel streamwise infall into dark matter haloes governs the orientation of satellite orbital angular momentum and galaxy spin. The observed transition may further trace the characteristic radial scale of filaments, offering a dynamical perspective on the internal structure and assembly of the cosmic filament.

astro-ph.GA↗

arXiv2026

Whose readiness counts? Disagreement within and between sectors in perceived AI and robotics preparedness

AI and Industry 4.0 readiness assessments often summarise preparedness using a single score for an organisation, application domain or sector. Those summaries can conceal disagreement about the same technology and variation among applications grouped under one sector label. We test how much information is lost through this aggregation using a card-based survey in which 982 respondents provided 15,200 readiness evaluations across 17 named AI and robotics challenges. Readiness is perceived community preparedness and available resources, not personal willingness or audited organisational capability. Respondents frequently disagreed about identical challenges, with card-level readiness standard deviations of $1.03$-$1.26$ on a five-point scale. A crossed decomposition attributes 32.7% of observed variation to stable respondent differences, 7.3% to differences among challenges, and 60.0% to response-level variation that also contains measurement error. Differences among challenge-family means account for only about 2% of variation, with substantially more variation among people, applications and person-family judgements. Manufacturing has the highest mean readiness, yet shop-floor robotics, process-optimisation AI and general decision-support applications are judged differently. Computer-science and AI/ML respondents report higher readiness than non-technical respondents across challenge families, whereas engineering respondents do not report higher Manufacturing readiness. Sector rankings are therefore best used as portfolio summaries rather than evidence that an industry is uniformly ready or behind. Readiness reporting should retain application-level disagreement, disclose whose judgements form the average, and consider ethics, cyber security, literacy and capability needs without collapsing them into a single score.

cs.CY↗

arXiv2026

From a Static Multi-Level Small Semantic Codebook to a Dynamic Single-Level Large Semantic Codebook for Generative Recommendation

Generative recommendation represents each item with a sequence of discrete Semantic IDs (SIDs) and predicts the sequence to retrieve the next item. Typical systems use multi-level residual quantization, which increases autoregressive decoding cost and creates a large hierarchical space that may be sparsely occupied. Static codebooks also become misaligned with current traffic as new items arrive and exposure distributions change. We propose a single-level large semantic codebook that replaces multiple residual semantic codes with one semantic token while retaining a separate collaborative disambiguation token to reduce item collisions. We further introduce an exposure-aware dynamic update mechanism based on temporal weight decay, exponential moving-average center updates, and an exposure-weighted penalty on SID changes. We also develop an offline evaluation framework covering representation quality, code utilization, cluster load, full-SID collision, and temporal stability. On two public datasets, the two-level SID improves mean Recall@10 by 5.0%-8.8% and mean NDCG@10 by 4.1%-5.1% for OneRec-V1, and by 7.1%-8.7% and 3.8%-8.5%, respectively, for OneRec-V2. Dynamic updating provides further gains on KuaiRec. Across three serving architectures, the shorter SID reduces estimated autoregressive-decoding FLOPs by 47.93%-48.70% and increases single-card QPS by 28.57%-47.0%. A five-day online A/B test serving 2.5% of production traffic improves the primary consumption metric by 0.792%.

cs.IR↗

arXiv2026

Minimal isometric immersions of flat n-tori into spheres

In 1985, Bryant established that a flat $2$-torus admits a minimal isometric immersion into some round sphere if and only if a certain rationality condition is satisfied. We show that when $n\geq 3$, the rationality criterion is no longer a necessary, but a sufficient condition for a flat $n$-torus to admit minimal isometric immersions into spheres. We also derive an upper bound for the algebraic irrationality degree of such immersions. When $n=3$, this bound is sharp and explicit embedded examples are provided respectively for each possible degree. Moreover, by constructing a family of non-homogeneous minimal flat $3$-tori, we show that minimal isometric immersions (embeddings) of flat $n$-tori are not necessarily homogeneous when $n \geq 3$. In addition, we establish a deformation theorem that every flat $n$-torus admitting a minimal isometric spherical immersion can be isometrically, minimally and homogeneously immersed into a sphere of dimension at most $n^2+n-1$.

math.DG↗

arXiv2026

Ready for What? Rethinking AI and Robotics Preparedness for Adoption and Policy

Efforts to accelerate AI and robotics adoption require evidence about where communities are ready to act and where support is still needed. Yet averages across stakeholder groups can obscure relationships that emerge when the same person evaluates different challenges. We analyse a repeated card-based survey in which 982 participants provided 15,200 evaluations of 17 AI and robotics challenges. Each challenge was rated on 1-5 measures of significance, complexity and readiness, where readiness refers to perceived community preparedness and available resources rather than personal competence or realised adoption. Because participants evaluated multiple challenges, the design separates stable between-person differences from challenge-specific within-person deviations. Within the same respondent, a challenge rated one point more complex than usual is associated with about 0.21 points lower readiness (p less than 0.001). By contrast, respondents who generally rate challenges as more complex do not systematically report lower readiness (p=0.29). Significance is positively associated with readiness, while unusually high complexity modestly weakens this alignment. These relationships vary across challenge families, and professional background remains associated with adjusted preparedness. On applied cards, confidence, trust and related perceptions add substantial information about readiness, including for held-out participants. For policymakers and organisations, averaging across stakeholders can hide challenge-specific barriers. Readiness assessments should preserve both differences between stakeholder groups and variation within the same stakeholders across challenges. Effective adoption and literacy strategies should ask not only who appears ready, but which challenges they find unusually difficult and whether the likely constraint concerns implementation, capability, assurance or resources.

cs.CY↗

arXiv2026

Neutron skin thickness and its volume and surface contributions in berkelium isotopes

Accurate determination of the neutron skin thickness ($ΔR_{\rm np}$) in finite nuclei is essential for constraining the density dependence of the nuclear symmetry energy. This work presents a systematic investigation of $ΔR_{\rm np}$ for the transuranium berkelium (Bk) isotopes within the framework of the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc). The results indicate an overall increase in neutron skin thickness with $N$, which exhibits antikinks at the shell closures $N = 184, 258$ due to the shell effects. A decomposition of $ΔR_{\rm np}$ into volume and surface terms, based on two-parameter Fermi (2pF) fits to angle-averaged DRHBc densities, demonstrates that the volume term dominates as much as $60\%$--$70\%$ in most nuclei, consistent with the $65\%$ found in $^{208}$Pb, thereby validating the volume-surface decomposition for deformed nuclei and confirming its correlation with the symmetry energy slope $L$. The surface term prevails only near the proton drip line, where the volume fraction drops below $50\%$ due to the reduced neutron-to-proton ratio. Deformation is found to slightly reduce the central radius $R_c$ but markedly enhance the surface diffuseness $a$, leading to a notable increase in $ΔR_{\rm np}$, primarily driven by the surface term. Furthermore, we extend the decomposition to a directional analysis by extracting 2pF parameters along the symmetry axis ($θ=0^\circ$) and perpendicular to it ($θ=90^\circ$). In prolate deformed nuclei, a strong directional dependence is observed: although the nucleus is elongated along the symmetry axis, $ΔR_{\rm np}$ is significantly larger in the perpendicular direction. This anisotropy is weak for oblate nuclei around the shell closures.

nucl-th↗

arXiv2026

HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam

Humanity's Last Exam (HLE) has become a widely used benchmark for evaluating frontier large language models on challenging, multi-domain questions. However, community-led analyses have raised concerns that HLE contains a non-trivial number of noisy items, which can bias evaluation results and distort cross-model comparisons. To address this challenge, we introduce HLE-Verified, a verified and revised version of HLE with a transparent verification protocol and fine-grained error taxonomy. Our construction follows a two-stage validation-and-repair workflow resulting in a certified benchmark. In Stage I, each item undergoes binary validation of the problem and final answer through domain-expert review and model-based cross-checks, yielding 668 verified items. In Stage II, flawed but fixable items are revised under strict constraints preserving the original evaluation intent, through dual independent expert repairs, model-assisted auditing, and final adjudication, resulting in 1,143 revised-and-certified items. The remaining 689 items are released as a documented uncertain set with explicit uncertainty sources and expertise tags for future refinement. We evaluate eight state-of-the-art language models on HLE and HLE-Verified, observing an average absolute accuracy gain of 7--10 percentage points on HLE-Verified. The improvement is particularly pronounced on items where the original problem statement and/or reference answer is erroneous, with gains of 30--40 percentage points. Our analyses further reveal a strong association between model confidence and the presence of errors in the problem statement or reference answer, supporting the effectiveness of our revisions. Overall, HLE-Verified improves HLE-style evaluations by reducing annotation noise and enabling more faithful measurement of model capabilities. Data is available at: https://huggingface.co/datasets/skylenage/HLE-Verified

cs.CL↗

arXiv2026

Intent-Driven Situation Tracking for User-Centric Multi-Turn Agents

User-centric multi-turn agents must act on an evolving task situation shaped by changing user intents, accumulated tool-grounded facts, missing information, and execution constraints. Existing context-management methods improve the use of past interaction history, but rarely maintain an explicit situation state that separates grounded facts from task-state judgments. As a result, agents often need to infer fine-grained attributes, task dependencies, and constraint satisfaction implicitly from dialogue traces. We propose Intent-Driven Situation States (IDSS), a training-free framework that maintains an explicit situation state alongside the dialogue. IDSS parses tool returns into provenance-aware entities and attributes, tracks user intents, required variables, constraints, and execution status, and propagates new facts to task constraints to update action executability. This allows agents to avoid infeasible actions, advance dependent goals, and reuse relevant information without repeatedly searching raw history. Experiments on three interactive benchmarks across eight LLMs show that IDSS improves task completion, preference elicitation, and interaction efficiency, with clear gains on tasks involving multi-entity coordination, evolving user constraints, and constraint-aware replanning. Ablations and error analyses show that these improvements come from the interaction between fact persistence, intent-centered state tracking, and constraint modeling. These results suggest that explicit situation tracking offers an effective alternative to history-centric context management for reliable user-centric multi-turn agents.

cs.AI↗

arXiv2026

Spectator Leakage Suppression via Invariant Subspace Engineering for CZ Gates in Superconducting Quantum Circuits

Spectator leakage poses a fundamental challenge to scalable quantum computing, particularly as frequency collisions become unavoidable in multi-qubit processors. We introduce a leakage mitigation strategy based on dynamically reshaping the system Hamiltonian. Our technique utilizes a tunable coupler to enforce a block-diagonal structure on the effective Hamiltonian governing near-resonant spectator interactions, confining the gate dynamics to a two-dimensional invariant subspace and thus preventing leakage by construction. On a multi-qubit superconducting processor, we experimentally demonstrate that this dynamic control scheme suppresses leakage rates to the order of $10^{-4}$, across a wide near-resonant detuning range and with up to three simultaneous spectator qubits. These results demonstrate a robust and scalable method that resolves the critical trade-off between dense frequency packing and high-fidelity gate operation. Our work establishes dynamic Hamiltonian engineering as an essential technology for building fault-tolerant quantum computers.

quant-ph↗

arXiv2026

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

A prevailing narrative in LLM post-training holds that supervised finetuning (SFT) memorizes while reinforcement learning (RL) generalizes. We revisit this claim for reasoning SFT with long chain-of-thought (CoT) supervision and find that cross-domain generalization is not absent but conditional, jointly shaped by optimization dynamics, training data, and base-model capability. Some reported failures are under-optimization artifacts: cross-domain performance first degrades before recovering and improving with extended training (a dip-and-recovery pattern), so shorttraining checkpoints can underestimate generalization. Data quality and structure both matter: low-quality solutions broadly hurt generalization,while verified long-CoT traces yield consistent cross-domain gains. Model capability is essential: stronger models internalize transferable procedural patterns (e.g., backtracking) even from a toy arithmetic game, while weaker ones imitate surface verbosity. This generalization is asymmetric, however: reasoning improves while safety degrades, reframing the question from whether reasoning SFT generalizes to under what conditions and at what cost.

cs.AI↗

arXiv2026

Constraints On New Theories Using Rivet : CONTUR version 3 release note

The CONTUR toolkit exploits RIVET and its library of more than a thousand energy-frontier differential cross-section measurements from the Large Hadron Collider to allow rapid limit-setting and consistency checks for new physics models. In this note we summarise the main changes in the new CONTUR 3 major release series. These include additional statistical treatments, efficiency improvements, new plotting utilities and many new measurements and Standard Model predictions.

hep-ph↗

arXiv2026

BashCoder-R1: Towards Robust and Explainable Bash Code Generation with Robustness-Aware Group Relative Policy Optimization

Bash scripts are critical for system administration, DevOps, and CI/CD, where code quality affects stability and security. However, LLM-generated scripts often lack reasoning and contain robustness flaws such as mishandled edge cases and unchecked failures. This is particularly critical in production environments where even minor errors can lead to service disruptions. We propose BashCoder-R1, a framework that jointly addresses both issues by treating explainability as a design goal. The pipeline has three stages. Continual Pre-training adapts to Bash syntax. Long Chain-of-Thought Supervised Fine-Tuning on expert-validated samples teaches risk-averse reasoning before code generation. Robustness-Aware Group Relative Policy Optimization optimizes a weighted reward for syntax correctness, robustness (verified by shellcheck), and format adherence. This staged design ensures that the model progressively acquires syntax knowledge, reasoning capability, and robust decision-making. On our BashBench benchmark (952 real-world tasks, 773 single-line and 179 multi-line), BashCoder-R1 achieves SyntaxPass of 100.00/94.97, RobustWarnRate of 4.01/16.47, RobustPass of 95.99/79.33, FuncRate of 93.01/93.85, and FullRate of 90.04/73.18 for single-line and multi-line tasks, respectively. These are relative FullRate improvements of 37.82 and 20.18 percent over the strongest baseline, DeepSeek-V3.2 (Reasoning). Human evaluation confirms its reasoning chains are highest in quality.

cs.SE↗

arXiv2026

REATS: LLM Reasoning-based Ensemble Learning for Adaptive Time Series Forecasting

Due to the diversity of real-world time series, no single forecasting model consistently dominates across all samples. Ensemble learning addresses this by combining complementary model strengths, yet existing methods rely on fixed rules or black-box models based solely on numerical inputs, failing to leverage LLM reasoning for interpretable weighting decisions. We propose REATS, which leverages LLM reasoning capabilities as an intelligent ensemble router that jointly processes textual temporal pattern descriptions and numerical features to produce interpretable, sample-adaptive ensemble weights through chain-of-thought reasoning. To enable effective LLM-based ensembling, we study its key design choices and propose: (i) a structured input pipeline that transforms raw time series into hybrid textual--numerical representations with fixed token cost, enabling rule-based chain-of-thought construction without API dependency, augmented with retrieved similar-sample priors; (ii) a diverse multi-row weight supervision scheme coupled with a token-efficient percentage-table format that reduces numerical complexity and mitigates LLM hallucinations; and (iii) a two-stage fine-tuning framework combining SFT with GRPO, where a reciprocal reward mapping transforms the continuous unbounded MSE gap into bounded signals with amplified near-oracle sensitivity, addressing the uniform sensitivity and outlier-dominated advantage compression inherent in naive reward designs for regression-based GRPO. Experiments on eight benchmarks demonstrate that REATS outperforms competitive ensemble baselines while providing natural language explanations and demonstrating strong transfer learning and out-of-domain generalization to unseen candidate models.

cs.LG↗

arXiv2026

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a challenging task. In this work, we study the local geometry of the regularized squared loss of deep linear networks around each critical point. Specifically, we obtain a closed-form characterization of the critical point set building on existing results and establish an error bound for the regularized loss under mild conditions on network width and regularization parameters. Notably, this error bound quantifies the distance from a point to the critical point set in terms of the current gradient norm, which can be used to derive linear convergence of first-order methods. To support our theoretical findings, we conduct numerical experiments and demonstrate that gradient descent converges linearly to a critical point when optimizing the regularized loss of deep linear networks.

math.OC↗

arXiv2026

MEC-Patch: Visible-Infrared Cross-Modal Adversarial Attack Driven by Intrinsic Material Emissivity Laws

With the widespread deployment of visible-infrared multimodal perception systems in safety-critical domains such as autonomous driving, evaluating their cross-modal adversarial robustness has become increasingly vital. However, existing approaches exhibit significant limitations in approximating the intrinsic laws of imaging. Most studies either focus on a single modality, failing to bypass cross-modal verification, or simplify infrared modeling into heuristic pixel-intensity distributions, neglecting the impact of ambient temperature fluctuations on adversarial stability. To bridge this gap, this paper proposes MEC-Patch, a cross-modal adversarial attack framework driven by intrinsic physical laws. By leveraging the Stefan-Boltzmann Law, we establish a physics-grounded cross-spectral mapping that explicitly links material emissivity to thermal radiation. Building on this formulation, we reveal that, under a fixed emissivity distribution, ambient temperature variations induce consistent global scaling while preserving relative emissivity-induced contrast. We exploit this property to construct temperature-robust adversarial perturbations whose discriminative patterns remain stable in the infrared modality, thereby fundamentally mitigating environmental sensitivity. Furthermore, we employ the physics-constrained NSGA-II algorithm to synergistically optimize the material-distribution-based patch parameters effective across both modalities, while enhancing generalization through a Dynamic Adversarial Resampling (DAR) strategy. Experimental results demonstrate that MEC-Patch effectively deceives state-of-the-art multimodal detectors and exhibits high robustness within high-fidelity, physically-consistent, and multi-scene simulation environments. This research provides a physical-law-driven perspective for the security assessment of multimodal perception systems.

cs.MM↗