arXiv subjects

Yu Wang

Publications and source records attributed to Yu Wang.

At least 91 records · Page 5Linked to original sources

arXiv2026

Positional Encoding via Token-Aware Phase Attention

We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scores that limits RoPE's ability to model long-context. RoPE extension methods may alleviate this issue, but they typically require post-hoc adjustments after pretraining, such as rescaling or hyperparameters retuning. This paper introduces Token-Aware Phase Attention (TAPA), a new positional encoding method that incorporates a learnable phase function into the attention mechanism. TAPA preserves token interactions over long range, extends to longer contexts with direct and light continual pretraining, extrapolates to unseen lengths, and attains substantially lower perplexity and stronger retrieval performance in the long-context regime than RoPE-style baselines.

cs.CL↗

arXiv2026

ZhuLong: Execution-Grounded LLM Agent for EDA Scripting with Offline API Self-Exploration

EDA scripting with tool-specific, often undocumented APIs remains a long-tail bottleneck that existing LLMs fail to address. This paper presents ZhuLong, an execution-grounded LLM coding agent for PyAether and SKILL that combines API retrieval, documentation inspection, and sandbox execution via unified MCP tools, augmented by an offline API self-exploration mechanism that infers undocumented API behaviors through counterfactual experimentation. We evaluate ZhuLong on EDA-Eval-PyAether, a benchmark of 158 real-world tasks with assertion-based execution, where the complete system achieves 78.5% Pass@1 in the commercial Empyrean Aether environment, substantially outperforming a pure LLM baseline (23.6%). Ablation studies identify sandbox execution as the dominant performance driver (41.2 pp drop when removed), with the self-exploration mechanism contributing an additional 3.2 pp accuracy gain and a 22.1% reduction in per-task tool calls. On 20 interactive tasks involving unsaved layouts and schematics, ZhuLong achieves 60.0% Pass@1 for PyAether and 50.0% for SKILL.

cs.AI↗

arXiv2026

Carleman Estimates for Wave Equations on the Half-Line: AI-Assisted Weights and Applications

We develop an AI-assisted search-and-certification workflow for constructing Carleman weights for wave equations on semi-infinite domains. Starting from a weighted cross-term identity used to derive the Carleman estimate, we derive explicit analytical screening conditions and use an AI system to propose symbolic candidate weights subject to those conditions. The search identifies a logarithmic weight structure with concrete parameter values; the subsequent human verification by the authors then retains this structure, derives the admissible parameter range, and rigorously certifies the selected weight by verifying the required quantitative conditions. Based on the identified and certified Carleman weight, the subsequent proofs, analysis, and applications are carried out entirely by the authors: we establish a global Carleman estimate for the wave operator on the half-line and derive a weighted conditional lateral Cauchy stability result. The proposed weight is further used in a finite-depth one-sided reconstruction problem for semilinear wave equations on the half-line, where the initial-time flux induces an endpoint graph stabilizer and a contractive frozen nonlinear reconstruction map. Numerical experiments support the predicted contraction behavior and show improved robustness to noisy data from the Carleman weighting, with the induced endpoint graph term providing further stabilization at higher noise levels.

math.AP↗

arXiv2026

Early-stage memory effect on the dephasing charger-mediated quantum battery

We investigate the performance of the charger-mediated quantum battery modeled by a two-qubit system. One of the qubits acts as the battery and the other acts as the charger which is subjected to a reservoir. We derived the time-local master equation in Lindblad form with a time-dependent dephasing rate. The dephasing rate may be negative in the early-stage of the charging process and thus indicate the presence of the memory effect. We find that such early-stage memory effect could increase the maximal ergotropy of the battery compared with the one under Markovian approximation with the corresponding asymptotic dephase rate. The enhancement of the performance is explained by means of the non-Markovian quantum jumps. Moreover, a discrete time scheme of the measurement-enhanced quantum battery is proposed in a quantum circuit with global and random local operations.

quant-ph↗

arXiv2026

An Exact Engine for Black-Hole Jets

For fifty years the Blandford--Znajek mechanism has been a mechanism and not an exact solution: force-free electrodynamics on a prescribed metric, with the jet's own field carrying no weight. Here that field gravitates. A split monopole weighs as much as a magnetic monopole, so its self-gravity is the magnetic Reissner--Nordström geometry; two copies glued across an equatorial current sheet put hole, disk and jet-driving flux into one spacetime, and force-free plasma makes a magnetosphere of it. Three things then follow that no test-field calculation can see. First, a steady jet is impossible. A stationary horizon cannot be heated but a slipping magnetosphere necessarily heats it, so the only stationary state is a dead one corotating with the hole, and a working jet is a black hole in decay at rates the field equations fix rather than assume. Second, flux enters the laws of black-hole mechanics as a charge, sharing one extremality budget with spin. That budget caps the jet power at $c^5/48G$ whatever the mass. Third, the lifetime output is finite: a maximally spinning hole delivers $1-e^{1/4}/\sqrt2=9.2\%$ of its mass and grows its horizon area by exactly $\sqrt e$. The horizon's own moment of inertia vanishes with the irrational exponent $(\sqrt{17}-1)/2$ set by the near-horizon throat, and what is left is a rotating hole whose angular momentum has passed to its own field.

astro-ph.HE↗

arXiv2026

SCoP: Structured Constraint Parsing for Evidence-Space Control in Temporal Knowledge Graph Question Answering

Temporal Knowledge Graph Question Answering (TKGQA) requires answer inference from evidence that is both structurally valid and temporally admissible. Existing methods often leave anchor-event binding, temporal admissibility, and ordinal selection implicit in model reasoning, task-specific training, or similarity-driven retrieval, allowing locally relevant but invalid facts to enter the answer context. We formulate complex TKGQA as evidence-space control and propose SCoP (Structured Constraint Parsing), a constraint-centric framework that externalizes temporal decisions before answer inference. Instead of treating retrieved facts as admissible evidence by default, SCoP separates answer-seeking event patterns from temporal anchor events, conservatively grounds them to canonical TKG entities and relations, and translates temporal intent into executable constraints with optional ranking requirements. These constraints operate over normalized point and interval ranges, enabling deterministic filtering of structurally compatible candidates and producing a compact evidence space for generation. Experiments on MultiTQ and TimelineCronQ-R assess SCoP across timestamped point-fact and interval-oriented settings with richer temporal relations and ordering dependencies. Without task-specific parameter updates, SCoP achieves 0.825 Hits@1 on MultiTQ and 0.761 Hits@1 on TimelineCronQ-R, with gains on constraint-intensive question types. These results support explicit evidence-space control over unconstrained retrieval or implicit temporal reasoning.

cs.CL↗

arXiv2026

Energy Loss of Newborn Magnetars by Schwinger Process

We investigate electron--positron pair creation through the Schwinger process in newborn magnetars with millisecond spin periods and surface dipole fields close to or above the QED critical field, $B_{\rm Q} = 4.414\times10^{13}\,\mathrm{G}$. In the unscreened field scenario, we derive the analytical global pair creation flux and recast it into a compact form with accurate analytic approximations. For a fiducial model with $B_{\rm p} = 10^{14}\,\mathrm{G}$ and $P_0 = 1\,\mathrm{ms}$, the Schwinger channel exceeds the classical Goldreich--Julian particle supply by many orders of magnitude and becomes the dominant source of charges at the earliest stage of the magnetar. The associated discharge removes about $90\%$ of the initial rotational energy within 30 ms, suppresses the gravitational-wave loss channel, and implies that the observable millisecond phase is extremely short in this unscreened scenario. The rapid energy release over such a short timescale may also provide a viable power source for astrophysical transients. Extending the same fiducial model to $10^4\,\mathrm{yr}$ gives spin periods of order seconds, linking newborn millisecond magnetars to the mature magnetar population.

astro-ph.HE↗

arXiv2026

DualDiff3D: Dual Structure-Appearance Diffusion Priors for Reliability-Enhanced 3D Gaussian Splatting

While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor reconstruction quality and artifacts in rendered novel views. Recent efforts attempt to utilize powerful diffusion priors, yet they typically process rendered and reference views concatenated along an additional dimension in a single network. These methods overlook an inherent nature that different views should maintain appearance similarity but differ in structure due to view shifts, leading to blur caused by conflicts between the two properties. In this paper, we propose DualDiff, a novel pipeline that leverages dual diffusion priors with a Structure-Appearance Attention (SAA) module to introduce reference guidance for refining low-quality novel views rendered from flawed 3D representations. Specifically, we retain one diffusion branch to focus on extracting structural information from the low-quality novel views, while introducing another branch to ensure appearance consistency with reference views. Furthermore, we present a 3D reconstruction framework named DualDiff3D, which integrates a reliability-enhanced Render-Refine-Optimize (RRO) loop to progressively and robustly incorporate the refined novel views, yielding more accurate 3DGS. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods even in the inference-only setting, with further performance gains achievable through training. Our code and pre-trained weights are available at https://github.com/Akaneqwq/DualDiff3D.

cs.CV↗

arXiv2026

ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams

Multimodal Large Language Models (MLLMs) excel at recognizing individual visual elements and reasoning over simple linear diagrams. However, when faced with complex topological structures involving branching paths, converging flows, and cyclic dependencies, their reasoning capabilities degrade sharply, even on tasks as basic as counting endpoints. Existing benchmarks fail to probe this gap, focusing on semantic comprehension rather than structural reasoning. We introduce ReactBench, a benchmark that reveals fundamental limitations in structural reasoning through chemical reaction diagrams. These real-world scientific diagrams offer an ideal testbed because they naturally span diverse structures from linear chains to cyclic graphs, while requiring both precise local recognition and coherent global reasoning. Our benchmark comprises 1,618 expert-annotated QA pairs across four hierarchical task dimensions. Extensive evaluation across 24 MLLMs reveals a significant performance gap exceeding 30% between anchor-based tasks and holistic structural reasoning tasks. Controlled ablations confirm this bottleneck lies in reasoning, not perception. These findings expose a fundamental deficit in structural understanding and establish directions for advancing visual reasoning.

cs.AI↗

arXiv2026

Human-Anchored Factuality Evaluation with Strategic Annotation

LLM-based factuality judges provide scalable evaluation signals, but their metrics are often systematically biased relative to human judgments. We study human-anchored factuality evaluation under limited annotation budgets, where judge predictions on the full dataset are combined with human labels on a small selectively sampled subset to obtain statistically valid estimates. The efficiency of this approach depends critically on which examples receive human annotation: in factuality evaluation, judge-human misalignment is not driven solely by low confidence, but also by structured failure modes such as incomplete evidence, temporal mismatch, unverifiable claims, and rubric misalignment. To exploit this structure, we introduce a factuality-specific annotation policy design pipeline that uses failure-space analysis (FSA) to derive diverse predictive signals for modeling human-judge misalignment. On an internal reference-based factuality evaluation system (AutoFA) and RAGTruth, where judge-predicted estimates substantially underestimate human-annotated factual accuracy, our FSA-guided policy improves annotation efficiency over uniform sampling and uncertainty-driven baselines, achieving effective-sample-size gains of 40.3% on AutoFA and 27.1% on RAGTruth.

cs.CL↗

arXiv2026

Target-Aware State-Adaptive $p$-Dirichlet Graph Neural Regression for Non-Invasive Body-Composition Estimation

Accurate estimation of body-composition outcomes, including body fat percentage (BFP), bone mineral density (BMD), and appendicular lean mass (ALM), is important for evaluating metabolic, skeletal, and muscular health. Direct assessment using dual-energy X-ray absorptiometry (DXA), however, requires specialized equipment and involves ionizing radiation. We propose a target-aware, state-adaptive $p$-Dirichlet energy-flow graph neural regression ($p$SADE-GNR) framework for estimating these outcomes from non-invasive anthropometric measurements. A neural encoder maps participant representations to hidden states that are propagated over an outcome-specific participant-similarity graph by a state-adaptive forward-Euler discretization of the graph $p$-Dirichlet energy flow. Graph distances weight each original or latent coordinate by its normalized absolute training-fold correlation with the outcome. Using clinical data from the Pennington Biomedical Research Center and five-fold cross-validation, the correlation-weighted model using the original standardized measurements achieved the lowest root mean squared error in all nine primary outcome-cohort combinations and outperformed previously reported support vector regression or least-squares support vector regression reference values in eight of nine comparisons. Autoencoder, variational-autoencoder, and Gaussian-mixture variational-autoencoder representations generally did not improve primary-outcome prediction or reduce computational cost. In an exploratory age-prediction analysis including ALM, BMD, and BFP as predictors, the correlation-weighted GMVAE model achieved the lowest mean error in all three cohorts. These results support target-aware, state-adaptive $p$-Dirichlet graph neural regression for non-invasive body-composition estimation.

cs.LG↗

arXiv2026

Think-at-Hard: Dynamic Looped Transformers for Improved Reasoning

Improving the reasoning abilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Looped transformers address this by performing multiple latent iterations to refine each token beyond a single forward pass. However, we identify a latent overthinking phenomenon: most token predictions are already correct after the first pass, but are sometimes revised into errors in later iterations. We ask whether selectively skipping latent iterations can improve accuracy, and reveal significant potential with an oracle iteration policy that boosts performance by up to 7.3%. Motivated by this, we propose Think-at-Hard (TaH), a looped transformer optimized for selective iteration. TaH employs a lightweight neural decider to trigger latent iteration, only at tokens likely to be incorrect after the standard forward pass. During latent iterations, depth-aware Low-Rank Adaptation (LoRA) modules shift the objective from general next-token prediction to focused hard-token refinement. A duo-causal attention mechanism extends attention from the token sequence dimension to an additional iteration depth dimension, enabling cross-iteration information flow with full sequential parallelism. Experiments on nine benchmarks show consistent gains across math, QA, and coding tasks. With identical parameter counts, TaH outperforms always-iterate baselines by 3.8-4.4% while skipping iterations on 93% of tokens, and exceeds single-iteration Qwen3 baselines by 3.0-3.8%. When allowing <3% more parameters from LoRA and decider, the gains further increase to 5.3-6.2% and 6.1-6.8%, respectively. Our code is available at https://github.com/thu-nics/TaH.

cs.CL↗

arXiv2026

When Tool Outputs Become Commands: Separating Action Induction from Runtime Authorization in Tool-Augmented LLM Agents

Tool-augmented LLM agents must rely on untrusted runtime Observations to complete open-ended tasks; however, when tool outputs no longer merely provide data but begin to specify concrete actions, they effectively become ``commands'' that can drive real-world side effects beyond user intent. We argue that this risk arises from conflating action induction with execution authorization. To address this distinction, we propose SARA, which treats action induction and execution authorization as distinct runtime roles and separates action provenance from execution authority. On the Observation side, a context-isolated Action Probe exposes action-inducing semantics and persistently records action-origin provenance across steps as a review signal; on the execution side, actual tool calls are authorized only against the user objective and audited evidence from authorized successful executions, while satisfying goal, execution-chain, and argument-level support. To preserve this separation across multi-step execution, SARA applies No-History-Promotion to prevent historical recurrence from laundering action origins into execution authority. Across AgentDojo and AgentDyn, SARA limits ASR to no more than $0.63\%$ across four primary evaluation settings while maintaining competitive task utility, and consistently reduces ASR across additional Agent backbones.

cs.AI↗

arXiv2026

PolyMemDB: A Polyglot Database System for AI Memory Management

With the widespread adoption of personal intelligent agents, users generate massive, heterogeneous data during long-term interactions. Leveraging this data as long-term memory helps reduce token overhead and deliver personalized experiences. However, existing memory systems face two primary limitations: they rely on single-storage paradigms that fragment multi-dimensional data, and they lack fine-grained data provenance to resolve long-term factual conflicts, thereby worsening LLM hallucinations. In this demonstration, we introduce PolyMemDB, a novel system tailored for managing agent memory. PolyMemDB has a polyglot storage architecture designed to track and manage various memory types, including graph, vector, probability and spatial-temporal data. To ensure factual consistency and reduce hallucinations, it features a probabilistic inference engine that integrates temporal decay with semiring aggregation, resolving long-term factual conflicts, providing detailed data provenance, and enabling users to trace reasoning chains transparently.

cs.DB↗

arXiv2026

Upper Hölderian with Explicit Exponent of Solution Mapping with Applications to Ball Constrained Least Squares Problems

In this paper, we propose an extension of the well-known Robinson implicit function theorem for generalized equations from the upper Lipschitzian case to the upper Hölderian case. Explicit exponents dependence between the generalized equation and its linearization is determined. Applications to ball constrained least squares problems, including linear least squares and separable nonlinear least squares, are studied. In particular, we establish that the solution mapping of ball constrained linear least squares under linear perturbation is locally upper Hölder continuous with exponent $1/3$, which is of independent interest. Ultilizing the upper Hölderian version of the implicit function theorem, we show the local upper Hölderian of the solution mapping of parametric ball constrained linear least squares.

math.OC↗

arXiv2026

GRB 220101A: a most energetic $10^{54}$ erg long GRB triggered by two supernovae 3.5 seconds apart

GRB 220101A is a long GRB, with a total energy exceeding $10^{54}$ erg with a redshift $z = 4.61$ and one of the largest ever high-quality multi-wavelength observational coverage, from a large number of space-based and ground-based telescopes. We interpret this source in a doubly Binary driven peta nova (BdP-N) model. The progenitor is composed of a massive CO core of $\sim 10\,M_\odot$, highly magnetized with $B \sim 10^{6}$ G, associated to a neutron star (NS) and a white dwarf (WD) with orbital periods from minutes to hours. The large GRB luminosity is explained by a sequence of 7 episodes: episode 1 is triggered by a new kind of pair supernova (HB) which originates from the collapse of the strongly magnetized CO core. Accretion of the HB supernova ejecta (the ejecta) onto the white dwarf companion triggers after 3.5 sec the episode 2: the second supernova emitting neutrinos and creating a new neutron star ($ν$NS). The ejecta, interacting with the magnetosphere of the binary NS companion originate the episode 3: the Ultra relativistic Prompt Emission (UPE) emission by far the most energetic episode of this GRB, with the formation of a powerful jet normal to the plane of the GRB. Following the UPE energy loss, the accretion of the ejecta on the NS companion leads to the episode 4: the formation of a black hole (BH) of $2.3 \ M_\odot$ leading to the observed GeV afterglow emission. Further accretion of the ejecta spin up the $ν$NS to a period of $1.3$ ms which gives origin to the episode 5: the birth of a pulsar. The interaction of this milli-second pulsar with the remnants lead to the Episode 6: the synchrotron emission observed in the X-ray, optical and radio, The episode 7 is a 56.7 ms pulsar, as observed $10^{10}$ s after the first burst in the crab nebula.

astro-ph.HE↗

arXiv2026

An Accurate Lanczos Method for the Matrix Product State Representation

We improve the convergence of the Lanczos algorithm using the matrix product state representation. As an alternative to the density matrix renormalization group (DMRG), the Lanczos algorithm avoids local minima and can directly find multiple low-lying eigenstates. However, its performance and accuracy are affected by the truncation required to maintain the efficiency of the tensor network representation. In this work, we propose the modified thick-block Lanczos method to enhance the convergence of the Lanczos algorithm with MPS representation. We benchmark our method on one-dimensional instances of the Fermi-Hubbard model and the Heisenberg model in an external field, using numerical experiments targeting the first five lowest eigenstates. Across these tests, our approach attains the best possible accuracy permitted by the given bond dimension. This work establishes the Lanczos method as a reliable and accurate framework for finding multiple low-lying states within a tensor-network representation

cond-mat.str-el↗

arXiv2026

MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports

Semi-structured information extraction (IE) from OCR-derived clinical reports is crucial for efficiently reconstructing patients' longitudinal medical histories. In practice, this scenario commonly involves three tasks: (i) field-header (key) discovery, (ii) key-conditioned question answering (QA), and (iii) end-to-end key-value pair extraction. However, existing evaluations often under-model two factors: heterogeneous and incompletely known key representations, and OCR-induced noise. This makes it difficult to assess model robustness in real-world settings. We present MedStruct-S, a benchmark specifically designed to evaluate these tasks under unknown keys and OCR noise. MedStruct-S contains 3,582 annotated real-world clinical report pages. Using MedStruct-S, we benchmark two representative paradigms: encoder-only sequence labeling with post-processing and decoder-only structured generation, covering four encoder-only and five decoder-only models spanning 0.11B to 103B parameters. Our results show that encoder-only models achieve the best performance for non-null-value key-conditioned QA despite being substantially smaller than decoder-only models. When comparing models of similar order of magnitude, encoder-only models still perform better overall. Without controlling for model scale, fine-tuned decoder-only models deliver the strongest overall results. These findings show that the benchmark provides a reliable and practical basis for selecting and comparing models across different semi-structured IE settings.

cs.CL↗