arXiv subjects

Yong Hu

Publications and source records attributed to Yong Hu.

At least 19 recordsLinked to original sources

arXiv2026

On the canonical degree of a Gorenstein minimal threefold of general type

Let $X$ be a Gorenstein minimal $3$-fold of general type whose canonical map is generically finite. We prove that if $p_g(X)> 243$, then the degree of the canonical map is at most $72$. Moreover, equality holds only if the general fibre $F$ of the Albanese morphism of $X$ is a smooth minimal surface of general type satisfying $p_g(F)=3,q(F)=0$ and $K_F^2=36$, and the canonical map of $F$ has degree $36$. This result improves the lower bound on $p_g(X)$ previously obtained by Jin-Xing Cai~\cite{Cai08}. As a consequence, we show that if the canonical degree is bigger than $64$, then the general fibre of the Albanese morphism of $X$ is a surface with irregularity zero.

math.AG↗

arXiv2026

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

Agent skills extend language-model agents with task-specific procedures, scripts, and references, but the tasks and environments they target continually change. Existing methods improve skills in bounded runs and retain only the final artifact, discarding the decision history that later agents need to interpret prior revisions, evaluations, and rejected alternatives. We introduce SkillHone, a harness for continual agent skill evolution grounded in persistent decision history. SkillHone pairs skill revisions with evaluation-side evidence that supplies practice feedback, recording structured histories of diagnoses, revisions, evidence, and outcomes. Role-separated subagents run candidate skills on practice probes with redacted reporting and propose revisions informed by prior decisions, enabling cross-session refinement without rediscovering past rationale. On deep-research benchmarks, SkillHone runs without a pre-integrated search stack and outperforms the commercially backed deep-research agent by 15.8 points on GAIA and 3.2 points on WebWalkerQA-EN, while also exceeding prior skill-evolution methods. We further deploy SkillHone on internal tool-mediated analysis scenarios, where it improves accuracy by an average of 18.8 points across seven settings.

cs.LG↗

arXiv2026

SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States

Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can process millions of token contexts end-to-end, but they suffer from high token consumption and attention dilution. In parallel, specialized LTU agents often sacrifice fidelity through task-agnostic abstractions like graph construction or indexing. We identify a key insight for LTU: query-relevant information is typically sparse relative to the full document, so effective reasoning should rely on a query-sufficient subset rather than the entire context. To address this, we propose SCOUT, a new paradigm for LTU that shifts from passive processing to active information foraging. It treats the document as an explorable environment and answers from a compact, provenance-grounded epistemic state. Guided by state-level gap diagnosis, SCOUT adaptively alternates between coarse-to-fine exploration and anchored state updates that progressively contract its epistemic state toward query sufficiency. Experiments show that SCOUT matches state-of-the-art proprietary models while reducing token consumption by up to 8x. Moreover, SCOUT remains stable as context length scales, substantially alleviating the practical cost-performance trade-off.

cs.CL↗

arXiv2026

Scale-Free Response with Directional Amplification in Critical Non-Hermitian Systems

The non-Hermitian skin effect can lead to directional amplification of response, with the associated end-to-end Green's function generally exhibiting size dependence. Any deviation in length or local disorder can drastically alter the amplification factor, rendering the response fragile in practical implementations. In this work, we identify a new type of scale-free, topological, and directionally amplified response in a Hatano-Nelson model under perturbed open boundary conditions. The scale-free response can be attributed to the first order boundary effect and characterized by a winding number defined on a continuous generalization of the finite-size Brillouin zone-a concept introduced in this work. Such scale-free behavior endows the end-to-end Green's function with significant robustness and making it promising for practical applications.

quant-ph↗

arXiv2026

Learning to Seek Help: Dynamic Collaboration Between Small and Large Language Models

Large language models (LLMs) offer strong capabilities but raise cost and privacy concerns, whereas small language models (SLMs) facilitate efficient and private local inference yet suffer from limited capacity. To synergize the complementary strengths, we introduce a dynamic collaboration framework, where an SLM learns to proactively decide how to request an LLM during multi-step reasoning, while the LLM provides adaptive feedback instead of acting as a passive tool. We further systematically investigate how collaboration strategies are shaped by SLM and LLM capabilities as well as efficiency and privacy constraints. Evaluation results reveal a distinct scaling effect: stronger SLMs become more self-reliant, while stronger LLMs enable fewer and more informative interactions. In addition, the learned dynamic collaboration strategies significantly outperform static pipelines and standalone inference, and transfer robustly to unseen LLMs.

cs.CL↗

arXiv2026

From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue

Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maximize cumulative performance in multi-turn dialogue due to interaction dynamics and delayed rewards. To address this challenge, we move from myopic, single-turn selection to long-horizon sequential routing for multi-turn dialogue. Accordingly, we propose DialRouter, which first performs MCTS to explore dialogue branches induced by different LLM selections and collect trajectories with high cumulative rewards. DialRouter then learns a lightweight routing policy from search-derived data, augmented with retrieval-based future state approximation, enabling multi-turn routing without online search. Experiments on both open-domain and domain-specific dialogue tasks across diverse candidate sets of both open-source and closed-source LLMs demonstrate that DialRouter significantly outperforms single LLMs and existing routing baselines in task success rate, while achieving a superior performance-cost trade-off when combined with a cost-aware reward.

cs.CL↗

arXiv2026

Cohomological invariants of hermitian forms that detect hyperbolicity

By using unramified cohomology groups, we construct a full sequence of cohomological invariants for hermitian forms of any (orthogonal, symplectic or unitary) type that can be used to detect hyperbolicity. The base central simple algebra can have arbitrary degree and the base field can have arbitrary characteristic. In the orthogonal case, we work with hermitian pairs, and we apply our construction to show that over fields of separable dimension 3, hermitian pairs over quaternion algebras with trivial classical invariants are hyperbolic. This last result extends a result of Berhuy to arbitrary characteristic.

math.RA↗

arXiv2026

Not All Frames Are Equal: Complexity-Aware Masked Motion Generation via Motion Spectral Descriptors

Masked generative models have become a strong paradigm for text-to-motion synthesis, but they still treat motion frames too uniformly during masking, attention, and decoding. This is a poor match for motion, where local dynamic complexity varies sharply over time. We show that current masked motion generators degrade disproportionately on dynamically complex motions, and that frame-wise generation error is strongly correlated with motion dynamics. Motivated by this mismatch, we introduce the Motion Spectral Descriptor (MSD), a simple and parameter-free measure of local dynamic complexity computed from the short-time spectrum of motion velocity. Unlike learned difficulty predictors, MSD is deterministic, interpretable, and derived directly from the motion signal itself. We use MSD to make masked motion generation complexity-aware. In particular, MSD guides content-focused masking during training, provides a spectral similarity prior for self-attention, and can additionally modulate token-level sampling during iterative decoding. Built on top of masked motion generators, our method, DynMask, improves motion generation most clearly on dynamically complex motions while also yielding stronger overall FID on HumanML3D and KIT-ML. These results suggest that respecting local motion complexity is a useful design principle for masked motion generation. Project page: https://xiangyue-zhang.github.io/DynMask

cs.CV↗

arXiv2026

Clinical-Prior Guided Multi-Modal Learning with Latent Attention Pooling for Gait-Based Scoliosis Screening

Adolescent Idiopathic Scoliosis (AIS) is a prevalent spinal deformity whose progression can be mitigated through early detection. Conventional screening methods are often subjective, difficult to scale, and reliant on specialized clinical expertise. Video-based gait analysis offers a promising alternative, but current datasets and methods frequently suffer from data leakage, where performance is inflated by repeated clips from the same individual, or employ oversimplified models that lack clinical interpretability. To address these limitations, we introduce ScoliGait, a new benchmark dataset comprising 1,572 gait video clips for training and 300 fully independent clips for testing. Each clip is annotated with radiographic Cobb angles and descriptive text based on clinical kinematic priors. We propose a multi-modal framework that integrates a clinical-prior-guided kinematic knowledge map for interpretable feature representation, alongside a latent attention pooling mechanism to fuse video, text, and knowledge map modalities. Our method establishes a new state-of-the-art, demonstrating a significant performance gap on a realistic, non-repeating subject benchmark. Our approach establishes a new state of the art, showing a significant performance gain on a realistic, subject-independent benchmark. This work provides a robust, interpretable, and clinically grounded foundation for scalable, non-invasive AIS assessment.

cs.CV↗

arXiv2026

Common sublattice-pure van Hove singularities in the kagome superconductors $\textit{A}$V$_{3}$Sb$_{5}$ ($\textit{A}$ = K, Rb, Cs)

Kagome materials offer a versatile platform for exploring correlated and topological quantum states, where van Hove singularities (VHSs) play a pivotal role in driving electronic instabilities, exhibiting distinct behaviors depending on electron filling and interaction settings. In the recently discovered kagome superconductors $\textit{A}$V$_{3}$Sb$_{5}$ ($\textit{A}$ = K, Rb, Cs), unconventional charge density wave order, superconductivity, and electronic chirality emerge, yet the nature of VHSs near the Fermi level ($\textit{E}$$_{F}$) and their connection to these exotic orders remain elusive. Here, using high-resolution polarization-dependent angle-resolved photoemission spectroscopy, we uncover a universal electronic structure across $\textit{A}$V$_{3}$Sb$_{5}$ that is distinct from density-functional theory predictions that show noticeable discrepancies. We identify multiple common sublattice-pure VHSs near $\textit{E}$$_{F}$, arising from strong V-$\textit{d}$/Sb-$\textit{p}$ hybridization, which significantly promote bond-order fluctuations and likely drive the observed charge density wave order. These findings provide direct spectroscopic evidence for hybridization-driven VHS formation in kagome metals and establish a unified framework for understanding the intertwined electronic instabilities in $\textit{A}$V$_{3}$Sb$_{5}$.

cond-mat.supr-con↗

arXiv2025

SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels

Large Language Models (LLMs) have shown significant progress, but understanding long and complex documents remains challenging. Many long-context benchmarks have been proposed, but they face several limitations, including task realism, data scalability, and data quality. To this end, we introduce SagaScale, a realistic, scalable, and high-quality long-context benchmark built from full-length novels. The entire benchmark is constructed using an automated data collection pipeline that utilizes external resources (e.g., Wikipedia pages) to curate question-answer pairs. Critically, these external resources are provided only for benchmark construction and not during evaluation, which allows LLMs to curate complex questions that go beyond what they can answer during evaluation. SagaScale is also bilingual and offers the largest context length to date, with average token counts exceeding 250K for English novels and 320K for Chinese novels. Our evaluation across 12 frontier LLMs and three long-context methods -- Na\"ive RAG, Agentic RAG, and Long Context -- yields key insights, including: (1) Directly supplying the full context to the LLM can outperform other methods by a large margin; (2) Most LLMs still struggle with lengthy contexts, but Gemini-2.5-Pro stands out as an exception; and (3) Agentic RAG effectively addresses the retrieval bottleneck in Na\"ive RAG. Finally, we publicly release the SagaScale benchmark and our data collection codebase to facilitate future research.

cs.CL↗

arXiv2025

Anomalous Nodal Gap in a Doped Spin-1/2 Antiferromagnetic Mott Insulator

Many emergent phenomena appear in doped Mott insulators near the insulator-to-metal transition. In high-temperature cuprate superconductors, superconductivity arises when antiferromagnetic (AFM) order is gradually suppressed by carrier doping, and a $\textit{d}$-wave superconducting gap forms when an enigmatic nodal gap evolves into a point node. Here, we examine electron-doped Sr$_{2}$IrO$_{4}$, the 5$\textit{d}$-electron counterpart of cuprates, using angle-resolved photoemission spectroscopy. At low doping levels, we observe the formation of electronic states near the Fermi level, accompanied by a gap at the AFM zone boundary, mimicking the AFM gap in electron-doped cuprates. With increasing doping, a distinct gap emerges along the (0,0)-($\pi$,$\pi$) nodal direction, paralleling that observed in hole-doped cuprates. This anomalous nodal gap persists after the collapse of the AFM gap and gradually decreases with further doping. It eventually vanishes into a point node of the reported $\textit{d}$-wave gap. These observations replicate the characteristic features in both electron- and hole-doped cuprates, indicating a unified route toward nodal metallicity in doped spin-1/2 AFM Mott insulators.

cond-mat.supr-con↗

arXiv2025

Diagnosing Hallucination Risk in AI Surgical Decision-Support: A Sequential Framework for Sequential Validation

Large language models (LLMs) offer transformative potential for clinical decision support in spine surgery but pose significant risks through hallucinations, which are factually inconsistent or contextually misaligned outputs that may compromise patient safety. This study introduces a clinician-centered framework to quantify hallucination risks by evaluating diagnostic precision, recommendation quality, reasoning robustness, output coherence, and knowledge alignment. We assessed six leading LLMs across 30 expert-validated spinal cases. DeepSeek-R1 demonstrated superior overall performance (total score: 86.03 $\pm$ 2.08), particularly in high-stakes domains such as trauma and infection. A critical finding reveals that reasoning-enhanced model variants did not uniformly outperform standard counterparts: Claude-3.7-Sonnet's extended thinking mode underperformed relative to its standard version (80.79 $\pm$ 1.83 vs. 81.56 $\pm$ 1.92), indicating extended chain-of-thought reasoning alone is insufficient for clinical reliability. Multidimensional stress-testing exposed model-specific vulnerabilities, with recommendation quality degrading by 7.4% under amplified complexity. This decline contrasted with marginal improvements in rationality (+2.0%), readability (+1.7%) and diagnosis (+4.7%), highlighting a concerning divergence between perceived coherence and actionable guidance. Our findings advocate integrating interpretability mechanisms (e.g., reasoning chain visualization) into clinical workflows and establish a safety-aware validation framework for surgical LLM deployment.

cs.LG↗

arXiv2025

Single crystal growth, structural and physical properties, and absence of a charge density wave in Ti_{0.85}Fe6Ge6

Kagome materials with charge density waves (CDWs) are fascinating quantum systems, offering an ideal platform to explore intertwined orders and to uncover novel mechanisms behind CDW formation. Chemical models have been developed and applied to predict CDW in $AM_6X_6$-type kagome materials, such as the rattling chain model based on ScV6Sn6 and the magnetic energy-saving model based on FeGe. In this study, we successfully synthesized Ti_{0.85}Fe6Ge6 single crystals using the vapor transport method. As predicted by the rattling chain model, these crystals are expected to exhibit kagome CDW behavior. Magnetization measurements indicate that Ti_{0.85}Fe6Ge6 is an easy-axis antiferromagnet with T_N = 488 K and transport measurements reveal metallic behavior primarily driven by electron-type carriers. However, no clear signatures of a CDW were observed in Ti_{0.85}Fe6Ge6. Density functional theory calculations demonstrate a markedly distinct electronic structure compared to related compounds: instead of a carrier-doping-induced rigid shift, the density of states shifted away from the Fermi level. Consistent with our structural investigations, the absence of a CDW and the unusual band structure can be attributed to the bonding characteristic within Ti_{0.85}Fe6Ge6. The strong covalent bonds of Ti-Ge1b, along with the solid Ge1b-Ge1b dimers, prevent the Ti-Ge1b-Ge1b-Ti chain from rattling. The presence of Fe-Fe antibonding state at the Fermi level enhances the spin polarization and depletes the electronic density around the Fermi level. Our results suggest that both the ionic radius and the bonding characteristics of the filler atom are crucial for the formation of CDWs in kagome materials. These factors can serve as supplementary terms to the rattling chain model, providing new insights for the discovery of novel kagome CDW materials.

cond-mat.mtrl-sci↗

arXiv2025

Selecting Optimal Camera Views for Gait Analysis: A Multi-Metric Assessment of 2D Projections

Objective: To systematically quantify the effect of the camera view (frontal vs. lateral) on the accuracy of 2D markerless gait analysis relative to 3D motion capture ground truth. Methods: Gait data from 18 subjects were recorded simultaneously using frontal, lateral and 3D motion capture systems. Pose estimation used YOLOv8. Four metrics were assessed to evaluate agreement: Dynamic Time Warping (DTW) for temporal alignment, Maximum Cross-Correlation (MCC) for signal similarity, Kullback-Leibler Divergence (KLD) for distribution differences, and Information Entropy (IE) for complexity. Wilcoxon signed-rank tests (significance: $p < 0.05$) and Cliff's delta ($\delta$) were used to measure statistical differences and effect sizes. Results: Lateral views significantly outperformed frontal views for sagittal plane kinematics: step length (DTW: $53.08 \pm 24.50$ vs. $69.87 \pm 25.36$, $p = 0.005$) and knee rotation (DTW: $106.46 \pm 38.57$ vs. $155.41 \pm 41.77$, $p = 0.004$). Frontal views were superior for symmetry parameters: trunk rotation (KLD: $0.09 \pm 0.06$ vs. $0.30 \pm 0.19$, $p < 0.001$) and wrist-to-hipmid distance (MCC: $105.77 \pm 29.72$ vs. $75.20 \pm 20.38$, $p = 0.003$). Effect sizes were medium-to-large ($\delta: 0.34$--$0.76$). Conclusion: Camera view critically impacts gait parameter accuracy. Lateral views are optimal for sagittal kinematics; frontal views excel for trunk symmetry. Significance: This first systematic evidence enables data-driven camera deployment in 2D gait analysis, enhancing clinical utility. Future implementations should leverage both views via disease-oriented setups.

cs.CV↗

arXiv2025

CANDY: Benchmarking LLMs' Limitations and Assistive Potential in Chinese Misinformation Fact-Checking

The effectiveness of large language models (LLMs) to fact-check misinformation remains uncertain, despite their growing use. To this end, we present CANDY, a benchmark designed to systematically evaluate the capabilities and limitations of LLMs in fact-checking Chinese misinformation. Specifically, we curate a carefully annotated dataset of ~20k instances. Our analysis shows that current LLMs exhibit limitations in generating accurate fact-checking conclusions, even when enhanced with chain-of-thought reasoning and few-shot prompting. To understand these limitations, we develop a taxonomy to categorize flawed LLM-generated explanations for their conclusions and identify factual fabrication as the most common failure mode. Although LLMs alone are unreliable for fact-checking, our findings indicate their considerable potential to augment human performance when deployed as assistive tools in scenarios. Our dataset and code can be accessed at https://github.com/SCUNLP/CANDY

cs.CL↗

arXiv2025

Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning

The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent's planning capability. To address these challenges, we propose Reinforcement Learning with Tool-use Rewards (RLTR), a novel framework that decouples the training process to enable a focused, single-objective optimization of the planning module. Crucially, RLTR introduces a reward signal based on tool-use completeness to directly evaluate the quality of tool invocation sequences. This method offers a more direct and reliable training signal than assessing the final response content, thereby obviating the need for verifiable data. Our experiments demonstrate that RLTR achieves an 8%-12% improvement in planning performance compared to end-to-end baselines. Moreover, this enhanced planning capability, in turn, translates to a 5%-6% increase in the final response quality of the overall agent system.

cs.LG↗

arXiv2025

Exceptional sensitivity near the bistable transition point of a hybrid quantum system

Phase transitions can dramatically alter system dynamics, unlocking new behavior and improving performance. Exceptional points (EPs), where the eigenvalues and corresponding eigenvectors of a coupled linear system coalesce, are particularly relevant for sensing applications as they can increase sensor response to external perturbations to a range of phenomena from optical phase shifts to gravitational waves. However, the coalescence of eigenstates at linear EPs amplifies noise, negating the signal-to-noise ratio (SNR) enhancement. Here, we overcome this limitation using nonlinearity, which exhibits exceptional SNR around a bistable transition point (BP). We couple a state-of-the-art diamond quantum sensor to a nonlinear Van der Pol oscillator, forming a self-oscillating hybrid system that exhibits both a single-valued and bistable phase. The boundaries between these phases are marked by both adiabatic and deterministic non-adiabatic transitions that enable chiral state switching and state coalescence at the BP. Crucially, NV magnetometry performed near the BP exhibits a 17x enhancement in SNR, achieving a record sensitivity of 170 fT/\sqrt{Hz}. This result surpasses the sensitivity limit of an ideal, thermally-limited electron magnetometer and resolves a long-standing debate regarding EP-like physics in advanced quantum sensing.

quant-ph↗