arXiv subjects

Pu Zhang

Publications and source records attributed to Pu Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Exceptional model structures and the induced extriangulated categories

A Hovey triple $(\mathcal{C}, \mathcal{F}, \mathcal{W})$ is {\it exceptional}, if $(\mathcal{C} \cap \mathcal{F}, \ \mathcal{C} \cap \mathcal{F} \cap \mathcal{W})$ is not a Frobenius pair. One has a disjoint union $\{\text{Hovey triple}\} = \{\text{Hereditary Hovey triple}\} \ \dot\bigcup \ \{\text{Exceptional Hovey triple}\}$ \ $\dot\bigcup \ \{\text{non-hereditary and non-exceptional Hovey triple}\}.$ Exceptional Hovey triples appear widely. For a selfinjective Nakayama algebra $A= kC_n/J^t$, $A\mbox{-}{\rm mod}$ admits exceptional Hovey triples if and only if $\gcd (n, t) \ge 2$ and $t \geq 3$. Their homotopy categories reveal new phenomena. Nakaoka-Palu's Theorem implies that there is a triangulation on $\frac{\mathcal C\cap\mathcal F}{\mathcal C\cap\mathcal F\cap\mathcal W}.$ It is proved that a Hovey triple in a weakly idempotent complete extriangulated category $(\mathcal A, \mathbb E, \mathfrak s)$ is exceptional if and only if the induced extriangulated structure $\bigl(\frac{\mathcal C\cap\mathcal F}{\mathcal C\cap\mathcal F\cap\mathcal W}, \ \overline{\mathbb E}, \ \overline{\mathfrak s}\bigr)$ is not {\it canonically triangulated}. Between this extriangulated structure and the one arising from the triangulation, the intermediate extriangulated structures are in one-to-one correspondence with Serre subcategories of $\mathrm{fp}((\frac{\mathcal P(\mathcal C\cap\mathcal F)}{\mathcal C\cap\mathcal F\cap\mathcal W})^{\mathrm{op}}, \mathrm{Ab})$.

math.RT↗

arXiv2026

Beyond a Single Judge: The Evidence-Grounded, Social-Weighted Persona Panel for Generative UI Evaluation

Generative UI (GenUI) lets large language models synthesize a complete, renderable interface directly from a natural-language instruction, but evaluating the quality of what they generate remains an open problem. Human evaluation is costly and rater-variant, while LLM-as-a-judge is scalable but reflects only a single implicit viewpoint, unable to capture how different populations of real users actually perceive the same interface. We propose the Evidence-Grounded, Social-Weighted Persona Panel (ESPP), a three-stage GenUI evaluation method in which a panel of psychologically diverse, evidence-grounded personas independently rates a screenshot, exchanges opinions under a trait-derived, semantically-gated bounded-confidence mechanism, and is aggregated via Delphi-inspired social weighting into a single judgment. ESPP tracks human judgment substantially more closely than a naive single-pass judge, raising Pearson $r$ from $0.716$ to $0.922$, and a prompt-ensemble control recovers only about a third of this gap, isolating genuine persona and evidence grounding as the dominant source of improvement. Beyond this fidelity gain, retaining each panelist's individual rating further reveals that user subgroups agree on overall model rankings yet diverge sharply on specific rating dimensions, a structural disagreement a single homogeneous judge would systematically erase. The codes are available at https://github.com/Wuzheng02/ESPP.

cs.CL↗

arXiv2026

Complete Hierarchy of Nonrelativistic Odd-Parity Spin Splitting in Collinear Magnets

Momentum-dependent nonrelativistic spin splitting provides a symmetry fingerprint of collinear magnets and can govern unconventional electronic, magnonic, and transport phenomena. Whereas even-parity $s$-, $d$-, $g$-, and $i$-wave splittings in collinear magnets have been extensively studied, odd-parity counterparts remain unexplored beyond the $p$-wave and $f$-wave classes. Here, using group theory, we establish the complete classification of odd-parity spin splitting in collinear magnets. We show that, in addition to the $p$-wave and $f$-wave forms, $h$- and $k$-wave splittings with $\ell=5$ and $7$ are allowed, while $m$-wave splitting with $\ell=9$ constitutes the upper bound. We derive a complete mapping from crystallographic point-group irreducible representations to the lowest-order odd-parity basis functions and formulate the coupling rule between a symmetry-breaking axial field and the parent N\'eel order that selects the induced odd-parity class. We further construct minimal lattice models that realize $h$-, $k$-, and $m$-wave splitting. Guided by this classification, we screen the MAGNDATA database and show that circularly polarized light can drive the $\mathcal{PT}$-symmetric antiferromagnets Fe$_2$TeO$_6$ and MgFe$_6$Ge$_6$ into $h$-wave and $k$-wave phases, respectively, exhibiting the hallmark spin splittings in both electronic bands and magnon spectra. Symmetry analysis and Berry-curvature calculations show that collinear odd-parity magnets of both $h$- and $k$-wave allow an anomalous Hall response, whereas the $m$-wave class forbids it. Together, these results complete the partial-wave hierarchy of odd-parity spin splitting in collinear magnets and establish symmetry criteria for anomalous transport in the high-partial-wave classes.

cond-mat.mtrl-sci↗

arXiv2026

nuTruck: Benchmarking Autonomous Driving Planning for Distributed Electric-drive Trucks

The dominance of traditional rule-based methods in autonomous driving has gradually been replaced by learning-based approaches. While learning-based planners have achieved considerable success in passenger vehicles, their performance on heavy-duty trucks, particularly modern distributed electric-drive trucks (DETs), remains largely unexplored. To facilitate research and application of learning-based planners in DETs, this letter presents the first high-fidelity benchmark, called nuTruck, designed to support large-scale neural network training and closed-loop evaluation. Given the complex dynamics and high rollover susceptibility of DETs, we first incorporate a highly accurate nonlinear truck dynamical model into the simulation, which enables independent driving and steering of all wheels and captures dynamic load transfer caused by acceleration, deceleration, and cornering, thereby allowing quantitative assessment of rollover risk in closed-loop simulation. Second, we adapt several rule-based and learning-based planners as baselines for DETs and evaluate their performance in closed-loop simulation. Finally, using real-world driving scenarios from the nuPlan dataset, we conduct extensive closed-loop evaluations, analyzing not only conventional collision-free planning performance, but also the dynamical safety of the planned trajectories. The proposed nuTruck benchmark is expected to serve as a new standard for fair and realistic evaluation of autonomous driving planners on DETs.

cs.RO↗

arXiv2026

Odd-Parity Magnons

Magnons, as charge-neutral spin excitations, can transport spin information without Joule heating and therefore offer a promising platform for low-power spintronics. However, in collinear magnets, the effective time-reversal symmetry forbids odd-parity magnon band splitting. Here we propose odd-parity magnons and establish a general mechanism for realizing them in collinear antiferromagnets. We provide a complete spin-point-group classification of odd-parity magnon splitting in two-dimensional collinear antiferromagnets by identifying the leading splitting types and their symmetry-allowed basis functions. This classification serves as a practical guide for searching for odd-parity magnons. We show that breaking effective time-reversal symmetry, for example by circularly polarized light or loop currents, can induce highly tunable $p$- and $f$-wave magnon splitting. In bilayer systems, the dynamical modulation can drive a topological magnon phase transition, accompanied by chiral edge modes and an abrupt jump in the magnon thermal Hall conductivity. Material-specific first-principles calculations further demonstrate the feasibility of this mechanism in real van der Waals antiferromagnets. Our study identifies the odd-parity magnons as a new class of spin excitations and provides a theoretical foundation for odd-parity magnons and ultrafast optically controlled topological magnonic devices.

cond-mat.mtrl-sci↗

arXiv2026

Homotopic morphisms and diagram theorems in extriangulated categories

Homotopic morphisms of $\mathbb E$-triangles in extriangulated categories are introduced. Any morphism of $\mathbb E$-triangles is a composition of homotopic morphisms. Any morphism $(\alpha_1, \alpha_2, \alpha_3)$ of $\mathbb E$-triangles can be modified to be homotopic, by changing one of $\alpha_i$; moreover, all the 15 cases where $\alpha_i$ is an $\mathbb E$-inflation ($\mathbb E$-deflation) are analyzed. Some diagram theorems, especially $4\times 4$ Lemma and its $14$ variants, including $3\times 3$ diagram and Horseshoe Lemma, are investigated. A relation between homotopic morphisms and (middling) good morphisms in triangulated categories are given. Weakly idempotent complete extriangulated categories are characterized.

math.CT↗

arXiv2026

Physics-informed Deep Mixture-of-Koopmans Vehicle Dynamics Model with Dual-branch Encoder for Distributed Electric-drive Trucks

Advanced autonomous driving systems require accurate vehicle dynamics modeling. However, identifying a precise dynamics model remains challenging due to strong nonlinearities and the coupled longitudinal and lateral dynamic characteristics. Previous research has employed physics-based analytical models or neural networks to construct vehicle dynamics representations. Nevertheless, these approaches often struggle to simultaneously achieve satisfactory performance in terms of system identification efficiency, modeling accuracy, and compatibility with linear control strategies. In this paper, we propose a fully data-driven dynamics modeling method tailored for complex distributed electric-drive trucks (DETs), leveraging Koopman operator theory to represent highly nonlinear dynamics in a lifted linear embedding space. To achieve high-precision modeling, we first propose a novel dual-branch encoder which encodes dynamic states and provides a powerful basis for the proposed Koopman-based methods entitled KODE. A physics-informed supervision mechanism, grounded in the geometric consistency of temporal vehicle motion, is incorporated into the training process to facilitate effective learning of both the encoder and the Koopman operator. Furthermore, to accommodate the diverse driving patterns of DETs, we extend the vanilla Koopman operator to a mixture-of-Koopman operator framework, enhancing modeling capability. Simulations conducted in a high-fidelity TruckSim environment and real-world experiments demonstrate that the proposed approach achieves state-of-the-art performance in long-term dynamics state estimation.

cs.RO↗

arXiv2026

MetaDAT: Generalizable Trajectory Prediction via Meta Pre-training and Data-Adaptive Test-Time Updating

Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an offline pre-trained predictor that lacks online learning flexibility. Moreover, they depend on fixed online model updating rules that do not accommodate the specific characteristics of test data. To address these limitations, we first propose a meta-learning framework to directly optimize the predictor for fast and accurate online adaptation, which performs bi-level optimization on the performance of simulated test-time adaptation tasks during pre-training. Furthermore, at test time, we introduce a data-adaptive model updating mechanism that dynamically adjusts the predefined learning rates and updating frequencies based on online partial derivatives and hard sample selection. This mechanism enables the online learning rate to suit the test data, and focuses on informative hard samples to enhance efficiency. Experiments are conducted on various challenging cross-dataset distribution shift scenarios, including nuScenes, Lyft, and Waymo. Results demonstrate that our method achieves superior adaptation accuracy, surpassing state-of-the-art test-time training methods for trajectory prediction. Additionally, our method excels under suboptimal learning rates and high FPS demands, showcasing its robustness and practicality.

cs.CV↗

arXiv2026

Homotopy categories of admissible model structures on extriangulated categories

The extriangulated category is a simultaneous generalization of exact categories and triangulated categories. H. Nakaoka and Y. Palu have proved that the homotopy category of an admissible model structure on a weakly idempotent complete extriangulated category is a triangulated category. Using the classic construction of distinguished triangles given by A. Heller and D. Happel, this paper provides an alternative proof of Nakaoka - Palu Theorem. In fact, the class $\Delta$ of distinguished triangles in the present paper and the class $\widetilde{\Delta}$ of distinguished triangles in \cite{NP} have the relation $\Delta = - \widetilde{\Delta}$, and hence the two triangulated structures on the homotopy category are isomorphic.

math.RT↗

arXiv2025

High efficiency and compact lithium niobate non-resonant recirculating phase modulator and its applications

High modulation efficiency and a compact footprint are critical for next-generation electro-optic (EO) modulators. We introduce a new class of non-resonant recirculating phase modulators (PMs) that boosts modulation efficiency by repeatedly modulating the optical field within a single, non-resonant waveguide, while fundamentally removing the loop-length matching constraint that has limited prior recirculating schemes. This architectural breakthrough simultaneously enables a much smaller device footprint and an extended low-V$\pi$ bandwidth, without relying on narrowband resonances. Building on this concept, we experimentally demonstrate both a Mach-Zehnder modulator (MZM) and a cascaded PM, and verify their versatility in finite impulse response (FIR) filtering and optical frequency comb (OFC) generation. The recirculating MZM operates as a 4-tap rectangular-window FIR filter with 110 GHz bandwidth in a compact 2.889$\times$0.58 mm$^2$ footprint. The cascaded PM achieves a 3.40 GHz low-V$\pi$ bandwidth, a 110 GHz resonant EO bandwidth, and a V$\pi$L of 0.7 V$\cdot$cm, and generates 20 OFC lines under a 33 dBm microwave drive. These results demonstrate, for the first time, a practical and highly efficient non-resonant recirculating modulation platform, laying the groundwork for scalable high-order mode recirculating modulators (RMs) and opening new opportunities in optical communications, sensing, and microwave photonics.

physics.optics↗

arXiv2025

Weakly Gorensteinness of tensor algebras and Morita algebras

An algebra $A$ is left weakly Gorenstein if any semi-Gorenstein-projective left $A$-modules is Gorenstein-projective. The weakly Gorensteinness of two kinds of algebras are answered. Using the method of the monomorphism category, it is proved that the tensor algebra $A\otimes B$ with ${\rm gl.dim} B< \infty$ is left weakly Gorenstein if and only if so is $A$. For a class of Morita algebras $\Lambda=\begin{pmatrix}\begin{smallmatrix} A & N \\ M & B \\ \end{smallmatrix}\end{pmatrix}$, the (semi-)Gorenstein-projective left $\Lambda$-modules are computed and described; and then it is proved that $\Lambda$ is left weakly Gorenstein if and only if so are $A$ and $B$. As an application, the upper triangular matrix algebra $T_n(A)$ is left weakly Gorenstein if and only if so is $A$.

math.RT↗

arXiv2025

ZSPAPrune: Zero-Shot Prompt-Aware Token Pruning for Vision-Language Models

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim to reduce these costs by pruning visual tokens, existing approaches, whether based on attention or diversity, typically neglect the guidance of the text prompt and thus fail to prioritize task relevance. In this work, we propose a novel, zero-shot method that reframes the problem by introducing a prompt-aware perspective, explicitly modeling visual token pruning as a balance between task relevance and information diversity. Our hierarchical approach first selects a core set of task-relevant visual tokens and then supplements them with diversity tokens to preserve broader context. Experiments across multiple models and benchmarks show that our method achieves performance that matches or surpasses the state-of-the-art with only minimal accuracy loss, even when pruning up to 90\% of the tokens. Furthermore, these gains are accompanied by significant reductions in GPU memory footprint and inference latency.

cs.CV↗

arXiv2025

Representation of tensor functions using lower-order structural tensor set: three-dimensional theory

The representation theory of tensor functions is a powerful mathematical tool for constitutive modeling of anisotropic materials. A major limitation of the traditional theory is that many point groups require fourth- or sixth-order structural tensors, which significantly impedes practical engineering applications. Recent advances have introduced a reformulated representation theory that enables the modeling of anisotropic materials using only lower-order structural tensors (i.e., second-order or lower). Building upon the reformulated theory, this work establishes the representations of tensor functions for three-dimensional centrosymmetric point groups. For each point group, we propose a lower-order structural tensor set and derive the representations of tensor functions explicitly. For scalar-valued and second-order symmetric tensor-valued functions, our theory is indeed applicable to all three-dimensional point groups because their representations are determined by the corresponding centrosymmetric groups. The representation theory presented here is broadly applicable for constitutive modeling of anisotropic materials.

math.RT↗

arXiv2025

Claus Michael Ringel's main contributions to Gorenstein-projective modules

In this article we try to recall Claus Michael Ringel's works on the Gorenstein-projective modules. This will involve but not limited to his fundamental contributions, such as in, the solution to the independence problem of totally reflexivity conditions; the technique of $\mho$-quivers; a fast algorithm to obtain the Gorenstein-projective modules over the Nakayama algebras; the one to one correspondence between the indecomposable non-projective perfect differential modules of a quiver and the indecomposable representations of this quiver; the description of the module category of the preprojective algebras of type $\mathbb A_n$ via submodule category; semi-Gorenstein-projective modules, reflexive modules, Koszul modules, as well as the $\Omega$-growth of modules, over short local algebras; and his negative answer to the question whether an algebra has to be self-injective in case all the simple modules are reflexive.

math.RT↗

arXiv2025

Automating Security Audit Using Large Language Model based Agent: An Exploration Experiment

In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls are implemented, gaps are identified for cybersecurity risks mitigation. However, audits are usually manual, requiring much time and costs. This paper looks at the possibility of developing a framework to leverage Large Language Models (LLMs) as an autonomous agent to execute part of the security audit, namely with the field audit. password policy compliance for Windows operating system. Through the conduct of an exploration experiment of using GPT-4 with Langchain, the agent executed the audit tasks by accurately flagging password policy violations and appeared to be more efficient than traditional manual audits. Despite its potential limitations in operational consistency in complex and dynamic environment, the framework suggests possibilities to extend further to real-time threat monitoring and compliance checks.

cs.CR↗

arXiv2025

Representation of tensor functions using lower-order structural tensor set: two-dimensional point group

The representation theory of tensor functions is essential to constitutive modeling of materials including both mechanical and physical behaviors. Generally, material symmetry is incorporated in the tensor functions through a structural or anisotropic tensor that characterizes the corresponding point group. The general mathematical framework was well-established in the 1990s. Nevertheless, the traditional theory suffers from a grand challenge that many point groups involve fourth or sixth order structural tensors that hinder its practical applications in engineering. Recently, researchers have reformulated the representation theory and opened up opportunities to model anisotropic materials using low-order (i.e., 2nd-order and lower) structural tensors only, although the theory was not fully established. This work aims to fully establish the reformulated representation theory of tensor functions for all two-dimensional point groups. It was found that each point group needs a structural tensor set to characterize the symmetry. For each two-dimensional point group, the structural tensor set is proposed and the general tensor functions are derived. Only low-order structural tensors are introduced so researchers can readily apply these tensor functions for their modeling applications. The theory presented here is useful for constitutive modeling of materials in general, especially for composites, nanomaterials, soft tissues, etc.

math.RT↗

arXiv2025

Model structures on triangulated categories with proper class of triangles

In contrast with the Hovey correspondence of abelian model structures from two compatible complete cotorsion pairs, Beligiannis and Reiten give a construction of model structures on abelian categories from one hereditary complete cotorsion pair. The aim of this paper is to extend this result to triangulated categories together with a proper class $\xi$ of triangles. There indeed exist non-trivial proper classes of triangles, and a proper class of triangles is not closed under rotations, in general. This is quite different from the class of all triangles. Thus one needs to develop a theory of triangles in $\xi$ and hereditary complete cotorsion pairs in a triangulated category $\T$ with respect to $\xi$. The Beligiannis - Reiten correspondence between weakly $\xi$-projective model structures on $\T$ and hereditary complete cotorsion pairs $(\X, \Y)$ with respect to $\xi$ such that the core $\omega = \X \cap \Y$ is contravariantly finite in $\T$ is also obtained. To study the homotopy category of a model structure on a triangulated category, the condition in Quillen's Fundamental theorem of model categories needs to be weakened, by replacing the existence of pull-backs and push-outs by homotopy cartesian squares.

math.CT↗

arXiv2025

Falcon: A Remote Sensing Vision-Language Foundation Model (Technical Report)

This paper introduces a holistic vision-language foundation model tailored for remote sensing, named Falcon. Falcon offers a unified, prompt-based paradigm that effectively executes comprehensive and complex remote sensing tasks. Falcon demonstrates powerful understanding and reasoning abilities at the image, region, and pixel levels. Specifically, given simple natural language instructions and remote sensing images, Falcon can produce impressive results in text form across 14 distinct tasks, i.e., image classification, object detection, segmentation, image captioning, and etc. To facilitate Falcon's training and empower its representation capacity to encode rich spatial and semantic information, we developed Falcon_SFT, a large-scale, multi-task, instruction-tuning dataset in the field of remote sensing. The Falcon_SFT dataset consists of approximately 78 million high-quality data samples, covering 5.6 million multi-spatial resolution and multi-view remote sensing images with diverse instructions. It features hierarchical annotations and undergoes manual sampling verification to ensure high data quality and reliability. Extensive comparative experiments are conducted, which verify that Falcon achieves remarkable performance over 67 datasets and 14 tasks, despite having only 0.7B parameters. We release the complete dataset, code, and model weights at https://github.com/TianHuiLab/Falcon, hoping to help further develop the open-source community.

cs.CV↗