arXiv subjects

Zhiyuan Huang

Publications and source records attributed to Zhiyuan Huang.

At least 19 recordsLinked to original sources

arXiv2026

Control Synthesis against LTL Specifications with Long-Run Visit Proportion Objectives

This paper investigates the path-planning problem for systems required to satisfy a linear temporal logic (LTL) specification while achieving a desired long-run visit proportion. For a path represented in prefix-suffix structure, the long-run visit proportion quantifies the asymptotic occurrence proportion of an atomic proposition (AP) sequence of interest in the suffix trace. Such a quantitative requirement generally cannot be expressed by standard LTL specifications. Furthermore, we develop a planning approach that synthesizes an LTL-satisfying path whose long-run visit proportion remains within a prescribed tolerance of a desired value while satisfying an overall cost constraint. By adjusting the desired proportion, the synthesized path can allocate more or less long-run attention to the atomic proposition sequence of interest, thereby improving the flexibility and efficiency of the task execution. Finally, experiments on a quadruped robot demonstrate the practical significance of the proposed long-run visit proportion and the effectiveness of the proposed planning approach.

eess.SY↗

arXiv2026

Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights

The vanilla self-attention mechanism in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically induced by inputs and whose hidden dimension is equal to the sequence length $N$. As the context extends, the expressive capacity of such an $N$-width MLP increases, but it becomes unscalable for extremely long sequences. Recently, this fast-weight perspective has motivated the Mixture-of-Experts (MoE) attention mechanism, which partitions the sequence into rigid blocks, treats them as fast-weight experts, and sparsely routes the tokens to them. In this paper, we elevate this perspective to a unifying framework for efficient attention mechanisms, interpreting them as making fast weights scalable through either routing or compression, and organizing them into a five-dimensional taxonomy. Then, we propose Mixture-of-Top-$k$ Attention (MiTA), which employs a small set of landmark queries to gather top-$k$ attended key-value pairs as query-aware and deformable routed experts, while compressing the $N$-width MLP into a narrower shared expert. Consequently, our MiTA improves the flexibility of prior MoE attention from rigid to deformable fast-weight experts, as well as the scalability of prior top-$k$ attention from query-specific set to reusable top-$k$ set. We conduct extensive experiments on vision tasks showing the superior effectiveness and efficiency of our MiTA, and also uncovering intriguing properties such as an emergent token-pruning effect and easy generalization from standard attention. Code is available at https://github.com/QishuaiWen/MiTA.

cs.LG↗

arXiv2026

ChemVTS-Bench: Evaluating Visual-Textual-Symbolic Reasoning of Multimodal Large Language Models in Chemistry

Chemical reasoning inherently integrates visual, textual, and symbolic modalities, yet existing benchmarks rarely capture this complexity, often relying on simple image-text pairs with limited chemical semantics. As a result, the actual ability of Multimodal Large Language Models (MLLMs) to process and integrate chemically meaningful information across modalities remains unclear. We introduce \textbf{ChemVTS-Bench}, a domain-authentic benchmark designed to systematically evaluate the Visual-Textual-Symbolic (VTS) reasoning abilities of MLLMs. ChemVTS-Bench contains diverse and challenging chemical problems spanning organic molecules, inorganic materials, and 3D crystal structures, with each task presented in three complementary input modes: (1) visual-only, (2) visual-text hybrid, and (3) SMILES-based symbolic input. This design enables fine-grained analysis of modality-dependent reasoning behaviors and cross-modal integration. To ensure rigorous and reproducible evaluation, we further develop an automated agent-based workflow that standardizes inference, verifies answers, and diagnoses failure modes. Extensive experiments on state-of-the-art MLLMs reveal that visual-only inputs remain challenging, structural chemistry is the hardest domain, and multimodal fusion mitigates but does not eliminate visual, knowledge-based, or logical errors, highlighting ChemVTS-Bench as a rigorous, domain-faithful testbed for advancing multimodal chemical reasoning. All data and code will be released to support future research.

cs.AI↗

arXiv2026

Hierarchical Control for Continuous-time Systems via General Approximate Alternating Simulation Relations

This paper introduces a general approximate alternating simulation relation (\emph{$\varepsilon$-gAAS relation}) for continuous-time systems, which relaxes existing simulation relations to tolerate larger mismatches between abstract and concrete models. The definition of gAAS for continuous-time systems is first proposed, and its properties are investigated. Then, a control refinement method is developed to enable hierarchical control for the gAAS relation. Finally, case studies demonstrate the effectiveness of the proposed approach, highlighting its advantages over existing methods.

eess.SY↗

arXiv2026

Existential Opacity for Discrete-Event Systems with State Observations

Opacity is a fundamental system property for confidentiality in discrete-event systems (DES). Classical opacity is typically defined under event-based observations, requiring that any secret system behavior remains indistinguishable from some non-secret behavior to an external intruder. However, in many applications such as path planning or opacity-preserving tasks, the intruder observes system states rather than events. Moreover, it often suffices that the system exhibits secret behaviors that can be exploited for opacity-preserving task execution, but such a system property cannot be fully captured by existing notions of state-observation-based opacity. Motivated by this limitation, we propose a relaxed notion of existing state-observation-based opacity, called existential opacity (EO), which only requires the existence of secret behaviors (instead of all secret behaviors) that are indistinguishable from a non-secret behavior under the state observations of the intruder. We show that the notion of EO is more expressive than existing state-observation-based opacity notions. In addition, a class of EO properties together with their corresponding verification approaches are developed, enabling the analysis of existential opacity in discrete-event systems and providing a new criterion for determining the feasibility of opacity-preserving problems.

eess.SY↗

arXiv2026

SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics

The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains challenging, as existing protocols often struggle to provide comparable scores across architectures or rely on uncalibrated judgments. In this paper, we introduce SlidesGen-Bench, a benchmark designed to evaluate slide generation through a lens of three core principles: universality, quantification, and reliability. First, to establish a unified evaluation framework, we ground our analysis in the visual domain, treating terminal outputs as renderings to remain agnostic to the underlying generation method. Second, we propose a computational approach that quantitatively assesses slides across three distinct dimensions - Content, Aesthetics, and Editability - offering reproducible metrics where prior works relied on subjective or reference-dependent proxies. Finally, to ensure high correlation with human preference, we construct the Slides-Align1.5k dataset, a human preference aligned dataset covering slides from nine mainstream generation systems across seven scenarios. Our experiments demonstrate that SlidesGen-Bench achieves a higher degree of alignment with human judgment than existing evaluation pipelines. Our code and data are available at https://github.com/YunqiaoYang/SlidesGen-Bench.

cs.CL↗

arXiv2026

Learning Deep Modality-Shared Self-Expressiveness for Image Clustering with Textual Information

Leveraging textual information for image clustering has emerged as a promising direction, largely owing to the powerful representations learned by Vision-Language Models (VLMs). Existing approaches typically retrieve a textual counterpart for each image and then refine multimodal representations by directly enforcing cross-modal agreement, e.g., maximizing image-text similarity inherited from pretrained VLMs. However, such a strategy aligns heterogeneous representations across modalities without explicitly modeling the intrinsic structure within each modality and thus might yield unreliable alignment or distort modality-specific structures that are crucial for clustering. In this paper, we propose a simple but principled approach, termed deep modality-shared self-expressive model (DeepMORSE), which discovers cross-modal structures via a modality-shared self-expressive model and simultaneously learns structured representations that conform to a union of modality-specific subspaces. Moreover, we theoretically justify that the modality-shared self-expressive coefficients suppress inter-class noise towards a subspace-preserving solution, and show that mini-batch optimization procedure introduces an implicit regularization onto the self-expressive model. We evaluate our DeepMORSE on six widely used image clustering benchmarks and observe performance improvements exceeding 3% on the UCF-101, DTD-47, and ImageNet-Dogs datasets. In addition, we demonstrate the strong transferability of the learned representations by achieving state-of-the-art performance on downstream tasks such as image retrieval and zero-shot classification---without requiring any task-specific losses or post-processing. The code is available at: https://github.com/mengxianghan123/DeepMORSE.

cs.CV↗

arXiv2026

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges beyond raw interconnect bandwidth. While these systems provide unified global address spaces and high-bandwidth fabrics, their full potential for sparse MoE communication is hindered by three fundamental bottlenecks: (1) Strict execution serialization imposed by coarse-grained Bulk Synchronous Parallel (BSP) orchestration of interdependent communication phases; (2) Prohibitive synchronization overhead that fails to scale alongside high interconnect bandwidth; and (3) Severe load imbalance resulting from distance-agnostic scheduling of irregular token traffic. To eliminate these bottlenecks, we introduce UBEP (Unified-Bus Expert Parallelism), a production-ready communication library that rethinks MoE's All-to-All primitives for modern superpod architectures. Through large scale experiments, UBEP reduces All-to-All latency by up to 52.4% and MoE inference Time Per Output Token (TPOT) by up to 11.1%.

cs.DC↗

arXiv2026

Low-threshold efficient N${_2^+}$ lasing driven by sub-cycle soliton dynamics in a hollow waveguide

The phenomenon of N${_2^+}$ lasing, observed in femtosecond-laser filamentation, attract considerable interests in recent several years, with great application potentials in fields of remote sensing and ultrafast spectroscopy. Efficient N${_2^+}$ lasing at relatively-low pump energies and with high beam quality, while being highly-demanded for applications, remains, however, quite challenging in practical experiments. Here, we demonstrate a new route of generating low-threshold N${_2^+}$ lasing with unprecedently-high efficiency, which is enabled by soliton dynamics in a gas-filled hollow-tapered-capillary system. High-order-soliton compression of a 12-fs, 10-$μ$J-level pump pulse forms a sub-cycle asymmetric transient that tunnel-ionizes N${_2}$ to N${_2^+}$ and, through direct, single-photon resonant excitation, creates population inversion between the ground state ${X^2Σ_g^+}$ and the excited state ${B^2Σ_u^+}$${-}$a dynamic process distinct from the widely adopted three-state coupling picture${-}$and remarkably at unexpectedly low pump energy. In the experiments, we obtained 100-nJ-level N${_2^+}$ lasing pulses at 391 nm with conversion efficiencies up to 3.3$\times$10$^{-3}$, at pump energies of less than 50 $μ$J. These results represent improvement of more than one orders of magnitude in both generation efficiency and lasing threshold, compared with prevailing filamentation-based schemes. Our study bridges two generally-disparate fields (sub-cycle soliton dynamics and N${_2^+}$ lasing), and paves the way for narrow-band, high-beam-quality lasing pulses that may find wide applications in advanced spectroscopy and nonlinear pump-probe experiments.

physics.optics↗

arXiv2026

Jointly Learning Structured Representations and Stabilized Affinity for Human Motion Segmentation

Human Motion Segmentation (HMS), which aims to partition a video into non-overlapping segments corresponding to different human motions, has recently attracted increasing research attention. Existing HMS approaches are predominantly based on subspace clustering, which are grounded on the assumption that the distribution of high-dimensional temporal features well aligns with a Union-of-Subspaces (UoS). For videos in the real world, however, the raw frame-level features often violate the UoS assumption and yield unsatisfactory segmentation performance. To address this issue, we propose an efficient and effective approach for HMS, named Temporal Deep Self-expressive subspace Clustering (TDSC), which jointly learns temporally consistent structured representations and stabilized affinity for accurate and robust HMS. Specifically, in TDSC, we alternately learn structured representations of the input frame features and self-expressive coefficients via a properly regularized self-expressive model, in which a coding-rate maximization regularizer is incorporated to avoid representation collapse and conform the learned representations to span a desired UoS distribution, and meanwhile, temporal constraints are incorporated to promote temporally adjacent frames to be partitioned into the same groups. Moreover, we develop a temporal momentum averaging mechanism to stabilize affinity evolution and design a reparameterization strategy to enable efficient optimization. We conduct extensive experiments on five benchmark HMS datasets using both conventional (HoG) and up-to-date deep features (i.e., CLIP, DINOv2) to validate the effectiveness of our approach.

cs.CV↗

arXiv2026

LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios

Long-tailed semi-supervised learning (LTSSL) presents a formidable challenge where models must overcome the scarcity of tail samples while mitigating the noise from unreliable pseudo-labels. Most prior LTSSL methods are designed to train models from scratch, which often leads to issues such as overconfidence and low-quality pseudo-labels. To address this problem, we first theoretically prove that utilizing a foundation model significantly reduces the hypothesis complexity, which tightens the generalization bound and in turn minimizes the Balanced Posterior Error (BPE). Furthermore, we demonstrate that the feature compactness of foundation models strictly compresses the acceptance region for outliers, providing a geometric guarantee for robustness. Motivated by these theoretical insights, we extend LTSSL into the foundation model fine-tuning paradigm and propose a novel framework: LoFT (Long-tailed semi-supervised learning via parameter-efficient Fine-Tuning). Furthermore, we explore a more practical setting by investigating semi-supervised learning under open-world conditions, where the unlabeled data may include out-of-distribution (OOD) samples.To handle this problem, we propose LoFT-OW (LoFT under Open-World scenarios) to improve the discriminative ability. Experimental results on multiple benchmarks demonstrate that our method achieves superior performance. Code is available: https://github.com/games-liker/LoFT

cs.LG↗

arXiv2026

Multi-Modal Representation Learning via Semi-Supervised Rate Reduction for Generalized Category Discovery

Generalized Category Discovery (GCD) aims to identify both known and unknown categories, with only partial labels given for the known categories, posing a challenging open-set recognition problem. State-of-the-art approaches for GCD task are usually built on multi-modality representation learning, which is heavily dependent upon inter-modality alignment. However, few of them cast a proper intra-modality alignment to generate a desired underlying structure of representation distributions. In this paper, we propose a novel and effective multi-modal representation learning framework for GCD via Semi-Supervised Rate Reduction, called SSR$^2$-GCD, to learn cross-modality representations with desired structural properties based on emphasizing to properly align intra-modality relationships. Moreover, to boost knowledge transfer, we integrate prompt candidates by leveraging the inter-modal alignment offered by Vision Language Models. We conduct extensive experiments on generic and fine-grained benchmark datasets demonstrating superior performance of our approach.

cs.CV↗

arXiv2026

Enhancement of vacuum-ultraviolet dispersive-wave emission using gas-filled tapered hollow-core fibers

The recent breakthroughs in laser-driving 229Th nuclear transition have created an urgent demand for coherent vacuum-ultraviolet (VUV) sources delivering high spectral brightness at the critical 148.38 nm isomer energy. However, generating sufficient photon flux to overcome the low nuclear excitation probability remains a challenge for compact setups. While resonant dispersive wave emission in gas-filled hollow-core fibers offers a promising route, standard capillaries face a fundamental trade-off: maximizing input coupling requires large core diameters, whereas efficient nonlinear VUV conversion demands the high intensities using small cores. Here, we resolve this conflict using a gas-filled tapered capillary fiber. This architecture utilizes a longitudinally decreasing core diameter to combine a large input aperture with adiabatic field concentration, thereby continuously enhancing the nonlinear interaction. Experimentally, we demonstrate a widely tunable source (135-240 nm) that achieves a twofold efficiency enhancement specifically at the 148.38 nm wavelength compared to uniform geometries. By providing a scalable route to high-flux VUV generation, this work establishes a critical tabletop tool for advancing solid-state nuclear clocks and time-resolved spectroscopy.

physics.optics↗

arXiv2026

Deep-ultraviolet Cherenkov radiation in all-normal-dispersion waveguide enabled by spatial-temporal dynamics

Nonlinear propagation of ultrashort pulses in multi-mode waveguides, featuring complex spatial-temporal dynamics, provides new degrees of freedom in the fields of nonlinear optics and ultrafast lasers. Here, we demonstrate a new scheme of ultraviolet Cherenkov (dispersive-wave) radiation in a gas-filled capillary with unprecedently-high pulse energy, enabled by spatial-temporal dynamics. We found that mJ-level, 40-fs pulses, launched into a large-core capillary filled with high-pressure noble gas, would experience self-phase-modulation and self-steepening effects in this normal-dispersion waveguide, leading to high-intensity shock wave generation and asymmetric spectral broadening. Spatial-temporal dynamics, stemming from strong nonlinear inter-mode coupling, causes spatial shrink and temporal deceleration of the pulse which dramatically alter the capillary dispersion landscape. As a result, a phase-matching point can be created in the ultraviolet, giving rise to the radiation of multi-mode dispersive waves with 100-μJ-level pulse energies and few-fs pulse widths. Our findings inspire new insights into multi-mode nonlinear optics, and the demonstrated high-energy ultraviolet light source with broadband tunability and compact set-up configuration, may find a few applications in time-resolved spectroscopy, ultrafast electronics and femtosecond chemistry.

physics.optics↗

arXiv2025

Towards Interpretable and Efficient Attention: Compressing All by Contracting a Few

Attention mechanisms have achieved significant empirical success in multiple fields, but their underlying optimization objectives remain unclear yet. Moreover, the quadratic complexity of self-attention has become increasingly prohibitive. Although interpretability and efficiency are two mutually reinforcing pursuits, prior work typically investigates them separately. In this paper, we propose a unified optimization objective that derives inherently interpretable and efficient attention mechanisms through algorithm unrolling. Precisely, we construct a gradient step of the proposed objective with a set of forward-pass operations of our \emph{Contract-and-Broadcast Self-Attention} (CBSA), which compresses input tokens towards low-dimensional structures by contracting a few representatives of them. This novel mechanism can not only scale linearly by fixing the number of representatives, but also covers the instantiations of varied attention mechanisms when using different sets of representatives. We conduct extensive experiments to demonstrate comparable performance and superior advantages over black-box attention mechanisms on visual tasks. Our work sheds light on the integration of interpretability and efficiency, as well as the unified formula of attention mechanisms.

cs.LG↗

arXiv2025

MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues

Memory extraction is crucial for maintaining coherent ultra-long dialogues in human-robot role-playing scenarios. However, existing methods often exhibit uncontrolled memory growth. To address this, we propose MOOM, the first dual-branch memory plugin that leverages literary theory by modeling plot development and character portrayal as core storytelling elements. Specifically, one branch summarizes plot conflicts across multiple time scales, while the other extracts the user's character profile. MOOM further integrates a forgetting mechanism, inspired by the ``competition-inhibition'' memory theory, to constrain memory capacity and mitigate uncontrolled growth. Furthermore, we present ZH-4O, a Chinese ultra-long dialogue dataset specifically designed for role-playing, featuring dialogues that average 600 turns and include manually annotated memory information. Experimental results demonstrate that MOOM outperforms all state-of-the-art memory extraction methods, requiring fewer large language model invocations while maintaining a controllable memory capacity.

cs.CL↗

arXiv2025

Navi-plus: Managing Ambiguous GUI Navigation Tasks with Follow-up Questions

Graphical user interfaces (GUI) automation agents are emerging as powerful tools, enabling humans to accomplish increasingly complex tasks on smart devices. However, users often inadvertently omit key information when conveying tasks, which hinders agent performance in the current agent paradigm that does not support immediate user intervention. To address this issue, we introduce a $\textbf{Self-Correction GUI Navigation}$ task that incorporates interactive information completion capabilities within GUI agents. We developed the $\textbf{Navi-plus}$ dataset with GUI follow-up question-answer pairs, alongside a $\textbf{Dual-Stream Trajectory Evaluation}$ method to benchmark this new capability. Our results show that agents equipped with the ability to ask GUI follow-up questions can fully recover their performance when faced with ambiguous user tasks.

cs.CV↗

arXiv2025

Temporal Rate Reduction Clustering for Human Motion Segmentation

Human Motion Segmentation (HMS), which aims to partition videos into non-overlapping human motions, has attracted increasing research attention recently. Existing approaches for HMS are mainly dominated by subspace clustering methods, which are grounded on the assumption that high-dimensional temporal data align with a Union-of-Subspaces (UoS) distribution. However, the frames in video capturing complex human motions with cluttered backgrounds may not align well with the UoS distribution. In this paper, we propose a novel approach for HMS, named Temporal Rate Reduction Clustering ($\text{TR}^2\text{C}$), which jointly learns structured representations and affinity to segment the sequences of frames in video. Specifically, the structured representations learned by $\text{TR}^2\text{C}$ enjoy temporally consistency and are aligned well with a UoS structure, which is favorable for addressing the HMS task. We conduct extensive experiments on five benchmark HMS datasets and achieve state-of-the-art performances with different feature extractors. The code is available at: https://github.com/mengxianghan123/TR2C.

cs.CV↗