arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 145 records · Page 8Linked to original sources

arXiv2026

Effects of Soret diffusion on the intrinsic instability of premixed hydrogen/air flames

Hydrogen flames exhibit multiple intrinsic instabilities. The low molar masses of H and H2 lead to significant Soret diffusion near the flame front; however, its influence on hydrogen flame instabilities remains to be quantified. This study investigates the effect of Soret diffusion on instability evolution dynamics via one-dimensional counterflow analysis and two-dimensional, high-fidelity direct numerical simulations covering both the linear growth regime and the fully developed nonlinear regime over a wide range of equivalence ratios (phi). In the linear regime, Soret diffusion increases the perturbation growth rate at phi < 1.7, especially under lean conditions, but reduces the growth rate at phi > 1.7. A similar sensitivity reversal is observed in the Markstein length near the peak equivalence ratio of unstretched laminar flame speed. In the nonlinear regime, Soret diffusion accelerates the formation of small-scale wrinkles in lean hydrogen flames and reduces the characteristic size of large-scale finger structure by one-third. An interesting observation is that, although Soret diffusion promotes preferential diffusion and increases the local flame displacement speed, the global fuel consumption rate decreases due to a reduction in the overall flame surface area. In addition, curvature-based flame segment analysis reveals a synergistic effect between Soret diffusion and Fickian diffusion that enhances/reduces the local equivalence ratio in positively/negatively curved regions of the flame front. The probability distributions of the Karlovitz number and the density-weighted displacement speed are also analyzed; results suggest that, for lean hydrogen flames, Soret diffusion broadens the distributions for both parameters, particularly on the positive side. These findings promise to advance the fundamental understanding of hydrogen flame dynamics under complex differential transport.

physics.flu-dyn↗

arXiv2026

Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling

Scaling modern large language models (LLMs) to long contexts is limited by the quadratic computation cost, and poor length extrapolation of dense attention. Chunk-wise sparse attention offers a promising alternative, but all existing methods fall short of full attention because of their inaccurate chunk selection. We propose Hierarchical Landmark Sparse (HiLS) Attention, a chunk-wise sparse attention mechanism that learns chunk selection end-to-end under the language-modeling (LM) loss. HiLS factorizes attention hierarchically: each query performs attention independently with each retrieved chunk to extract chunk-specific information, and the resulting outputs are fused according to chunk retrieval scores. By incorporating retrieval scores into the forward attention computation, HiLS optimizes them directly with the LM loss, enabling end-to-end retrieval learning and native sparse training. Experimental results show that HiLS-Attention achieves performance comparable to, and in some cases better than, full attention at in-domain context lengths. Meanwhile, HiLS-Attention extrapolates more than $64\times$ the training context length with 90% retrieval accuracy, far beyond full attention. Moreover, existing full-attention models can be converted to HiLS-Attention with lightweight continued pretraining, preserving in-domain performance while acquiring ultra-long-context extrapolation. Together with its sparse KV access and computation, HiLS-Attention breaks the usual efficiency-performance trade-off, enabling long-context LLMs that are both more efficient and more effective on general long-context tasks than their full-attention counterparts.

cs.CL↗

arXiv2026

Teaching Vision-Language-Action Models What to See and Where to Look

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing VLAs' training relies heavily on text-centric visual question answering and chain-of-thought reasoning data, which emphasizes linguistic reasoning rather than action-grounded planning. As a result, the learned representations capture semantic knowledge but lack spatial dependencies crucial for reliable trajectory prediction. We propose DriveTeach-VLA, a framework that explicitly teaches VLAs what to see and where to look. Driving-aware Vision Distillation (DVD) injects driving-specific perceptual priors into the vision encoder, while 2D Trajectory-Guided Prompts (2D-TGP) provide spatial conditioning aligned with feasible driving trajectories. Together, they form a vision-guided learning pipeline: what to see (DVD pretraining) - where to look (TGP-guided SFT) - how to act (TGP-guided GRPO). DriveTeach-VLA achieves the state-of-the-art performance on NAVSIM and nuScenes. Our code is available at: https://github.com/ShivaTeam/DriveTeach-VLA.

cs.CV↗

arXiv2026

Causal-Invariant Cross-Domain Out-of-Distribution Recommendation

Cross-Domain Recommendation (CDR) aims to leverage knowledge from a relatively data-richer source domain to address the data sparsity problem in a relatively data-sparser target domain. While CDR methods need to address the distribution shifts between different domains, i.e., cross-domain distribution shifts (CDDS), they typically assume independent and identical distribution (IID) between training and testing data within the target domain. However, this IID assumption rarely holds in real-world scenarios due to single-domain distribution shift (SDDS). The above two co-existing distribution shifts lead to out-of-distribution (OOD) environments that hinder effective knowledge transfer and generalization, ultimately degrading recommendation performance in CDR. To address these co-existing distribution shifts, we propose a novel Causal-Invariant Cross-Domain Out-of-distribution Recommendation framework, called CICDOR. In CICDOR, we first learn dual-level causal structures to infer domain-specific and domain-shared causal-invariant user preferences for tackling both CDDS and SDDS under OOD environments in CDR. Then, we propose an LLM-guided confounder discovery module that seamlessly integrates LLMs with a conventional causal discovery method to extract observed confounders for effective deconfounding, thereby enabling accurate causal-invariant preference inference. Extensive experiments on two real-world datasets demonstrate the superior recommendation accuracy of CICDOR over state-of-the-art methods across various OOD scenarios.

cs.IR↗

arXiv2026

Dissipative surface solitons in two-dimensional truncated lattices with linear gain and loss

Dissipative solitons constitute a robust class of self-localized nonlinear states sustained by the dynamic balance between nonlinearity and gain-loss, possessing an intrinsic stability that stems from their fundamental attractor nature. When combined with lattice truncation, this balance gives rise to dissipative surface solitons (DSSs), whose existence and stability are jointly dictated by boundary-induced confinement and non-Hermitian dynamics. In two-dimensional truncated lattices with linear gain and loss, surface localization emerges within gap regimes, where families of DSSs bifurcate from linear surface localized gain modes as the nonlinearity increases. Increasing the number of waveguide rows at the interface enriches the diversity of supported surface modes in both linear and nonlinear regimes. Although multiple DSS families with distinct phase configurations may coexist within the same gap, their dynamical stability is strongly phase selective. These insights establish linear gain-loss engineering as a powerful mechanism for controlling nonlinear surface localization and provide practical guidelines for realizing robust nonlinear surface states in gain-loss-tailored photonic platforms.

nlin.PS↗

arXiv2026

Multipartite quantum resource distillation through local measurement programs

Distributed quantum resources in practical multi-user quantum networks are inevitably degraded by environmental noise, channel loss, and device-induced imperfections. To address these issues, quantum resource distillation offers a fundamental approach to recovering stronger resources from imperfect states. However, conventional implementations often require additional copies, dedicated physical filtering elements, or restrict to bipartite systems, posing challenges for scalable multipartite networks. Here, we introduce the method of quantum resource distillation based on the local measurement program (LMP), which transfers completely positive maps into programmable measurement processes. We experimentally demonstrate the performance of resource distillation through LMP in both bipartite and tripartite photonic systems, including the activation and enhancement of multipartite steering configurations. To demonstrate the flexibility and extensibility of the LMP framework, we also show that virtual resource distillation can be naturally reformulated within it. Our results establish a programmable and experimentally economical approach for distilling quantum resources in multipartite and higher-dimensional systems, thereby providing a practical route toward scalable quantum networks.

quant-ph↗

arXiv2026

Bipartite Gaussian Boson Sampling for Hamiltonian Cycles in Directed Graphs

Bipartite Gaussian boson sampling (BipartiteGBS) produces output probabilities governed by squared permanents of submatrices of arbitrary complex matrices, matching the nonsymmetric structure of directed graphs. Most GBS-based graph algorithms, however, rely on symmetric hafnian structure and are formulated for undirected problems. Here we propose a BipartiteGBS-based framework for directed-graph heuristic optimization. We introduce Max-Perm as a canonical optimization task for BipartiteGBS and derive a closed-form sampling enhancement factor relative to uniform classical sampling in this idealized setting. We then use permanent-biased BipartiteGBS samples to guide a genetic algorithm for the celebrated directed Hamiltonian cycle problem. Numerical experiments on Erdős--Rényi random directed graphs show that the resulting BipartiteGBS-enhanced algorithms improve success rates over a standard genetic algorithm and yield longer valid paths when no Hamiltonian cycle is found, while ablation tests indicate that BipartiteGBS-guided initialization is the dominant contributor. These results show how permanent-based photonic sampling can provide useful algorithmic guidance for asymmetric combinatorial search.

quant-ph↗

arXiv2026

Efficient Spatio-Temporal Grounding with Multimodal Large Models via Second-Level Tracking and RL Verification

Spatio-temporal grounding in long videos requires precise temporal localization and robust object tracking conditioned on natural-language queries. While recent vision-language models (VLMs) show strong reasoning ability, directly applying frame-by-frame inference to long sequences is computationally expensive and unstable. We propose a practical pipeline that shifts from frame-level to second-level tracking and performs cross-second smoothing to preserve continuity while reducing sequence length. To improve reasoning supervision, we synthesize chain-of-thought style trajectories using advanced multimodal models for temporal localization and target selection, and replace generated spatio-temporal coordinates with ground-truth annotations to avoid noisy supervision. We further optimize the policy with reinforcement learning using a verifier based on $t\_\mathrm{IoU}+mv\_\mathrm{IoU}$. Experiments across multiple FPS settings show that our method achieves a strong trade-off between efficiency and localization quality.

cs.CV↗

arXiv2026

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of multimodal large language models purpose-built for content and AI safety, with both instruction-tuned and reasoning-oriented variants. Yuvion VL addresses this gap by treating safety as an inherently adversarial and multimodal problem and designing the entire pipeline around adversarial robustness. For data construction, we develop an automated pipeline integrating adversarial-aware data synthesis with multi-stage quality control, producing large-scale, high-quality multimodal samples augmented with domain knowledge and reasoning annotations. For training, we adopt a three-stage pipeline that includes continued pretraining for risk-concept cross-modal alignment, instruct post-training for production-grade safety tasks, and reasoning post-training for enhanced interpretability and performance in complex tasks. We further introduce Confuse-then-Contrast Fine-Tuning, a contrastive framework that mines model-specific confusions and constructs multi-image contrastive groups to enforce explicit discrimination of fine-grained visual-semantic elements, enabling the model to distinguish between visually similar cases with different safety implications in adversarial safety tasks. To support rigorous evaluation, we further introduce Yuvion VL RiskEval (YVRE), a collection of benchmarks covering diverse open and internal evaluations, with a focus on content and AI safety, adversarial robustness, and real-world capability requirements. Experiments show that Yuvion VL-32B achieves industry-leading safety performance, surpassing comparably sized open-source models and best closed-source commercial models, while maintaining comparable general capabilities.

cs.CV↗

arXiv2026

Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrary scales. However, treating this ill-posed inverse problem as unconstrained residual-based regression risks hallucinating anatomically implausible structures or altering the originally observed data. To address both concerns, this paper presents the Dual-Prior Null-space Learning (DP-NSL) framework, which reformulates the task as a constrained recovery process guided by two complementary priors. A Measurement-Consistent Projection (MCP) enforces a Deterministic Observation Prior: the reconstruction undergoes an exact orthogonal projection that reproduces every acquired slice with zero error, confining all learned details to the unobservable null space. Within this null space, a Mixture-of-Splines (MoS) module imposes a Geometric Continuity Prior by dynamically mixing B-spline experts of different analytic orders, allowing each anatomical region to be modeled with a content-aware level of continuity. To promote spatial coherence, a Local Spatial Consistency Decoder (LSCD) further injects local inductive bias. Experiments on three CT and one MRI benchmark show that DP-NSL outperforms existing approaches while strictly preserving measurement consistency. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

eess.IV↗

arXiv2026

Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety

As large language models are increasingly deployed in real-world systems, safety failures can still lead to harmful outputs and dangerous misuse. We argue that the essence of safety is adversarial: many failures arise not from natural inputs alone, but from strategic attempts to evade model policies and safeguards. However, existing general-purpose model development largely overlook this adversarial nature, and often remain insufficient for realistic safety scenarios involving planning, tool use, and multi-step reasoning, causing measured safety performance to overestimate real deployment robustness. To address this gap, we present Yuvion LLM, a large language model built for adversarially robust content safety and broader AI safety. Yuvion LLM treats adversarial robustness and agentic capability as first-class objectives. Its pipeline combines adversarially aware data construction, knowledge-enhanced continued pretraining, and policy-grounded multi-task safety post-training, including risk-aware supervised fine-tuning and reinforcement learning-based policy optimization, together with safety-aware agentic reinforcement learning for tool use and multi-step reasoning in complex safety scenarios. We further introduce the Yuvion LLM RiskEval (YLRE), a collection of 93 benchmarks across four evaluation categories, covering diverse open and internal evaluations with a focus on safety, adversarial robustness, and real-world capability requirements. Across these evaluations, Yuvion LLM demonstrates clear advantages on safety-focused benchmarks and particularly strong robustness under adversarial conditions, while maintaining solid overall capability. Notably, Yuvion-8B outperforms most state-of-the-art baselines, including substantially larger models such as GPT-5.4 and Qwen3-MAX, on several safety tasks.

cs.CL↗

arXiv2026

Physics-informed sparse identification-based tube model predictive control for aerial vehicles

Autonomous aerial vehicles necessitate control strategies that balance computational efficiency with robust performance in dynamic operational environments. This paper proposes a model predictive control (MPC) framework for aerial platforms that leverages physics-informed machine learning (PIML) to achieve an optimal balance between computational tractability and robust performance. At the core of the proposed approach lies a sparse, control-affine model identified via the PIML method, which provides a parsimonious yet interpretable representation of the system dynamics by embedding first-principles knowledge and learning residual uncertainties from operational data. This model is incorporated within a robust MPC scheme that adopts a high-order Runge-Kutta discretization to ensure prediction accuracy and an adaptive tube-based mechanism to guarantee constraint satisfaction under uncertainty. The online adaptation of the tube, directly informed by the residual error of the PIML model, ensures robust stability without introducing excessive conservatism. Rigorous theoretical proofs are provided to establish recursive feasibility and stability. Numerical simulations and experiments on a quadrotor demonstrate that our method significantly reduces computational load compared to nonlinear MPC and robust MPC using a first-principles high-fidelity model, while outperforming PID, nonlinear MPC, neural-network-based MPC, and fixed-tube robust MPC in tracking performance and robustness, showcasing the practical efficiency of the proposed PIML-based control synthesis for resource-constrained aerial systems.

eess.SY↗

arXiv2026

HG-Bench: A Benchmark for Multi-Page Handwritten Answer-Region Grounding in Automated Homework Assessment

Automated homework assessment depends not only on recognizing student answers, but also on accurately locating where each answer and each intermediate reasoning step appears in noisy, multi-page handwritten work. This paper addresses the missing evaluation setting of page-aware, two-level answer-region grounding: given a sequence of homework page images, a model must localize complete answer regions and their ordered step-level subregions. We introduce HG-Bench, a benchmark of 500 human-annotated K-12 homework samples curated from a 1,489,278-image source pool, with question-level and step-level boxes linked by a hierarchical containment constraint. HG-Bench is paired with a page-aware evaluation protocol that separately measures complete-answer localization (FA) and step-level decomposition (FSm), revealing whether models truly ground the spatial structure of student reasoning rather than merely parse visible text. Across frontier closed-source APIs and competitive open-weight VLMs, no zero-shot system exceeds 55.22% on FA or 48.22% on FSm, while a GLM-4.6V 9B reference model fine-tuned on ~10k in-domain examples reaches 74.97/72.26. These results identify step-level handwritten grounding as a concrete capability gap and provide a reproducible benchmark, evaluation protocol, and trained reference point for future work on automated homework assessment.

cs.CV↗

arXiv2026

ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving

Large language models (LLMs) can improve autonomous driving planning but are costly to query online, and existing fast-slow planners often rely on hand-designed triggering rules that either over-call the slow system or call it at the wrong times. We formulate slow-system invocation as a resource-aware sequential decision problem and propose the Adaptive Slow-System Control Gate (ASSCG), which makes frame-level Query/Cache/Drop decisions to refresh, reuse, or suppress slow guidance. ASSCG uses an RWKV backbone for efficient long-horizon gating and is trained with supervised fine-tuning followed by GRPO-style compute-aware reinforcement fine-tuning. We apply ASSCG to two different fast-slow architectures: (i) AsyncDriver on nuPlan Hard20 closed-loop evaluation, where ASSCG improves score to 67.28 (+2.28) while reducing average end-to-end inference latency by 60%; and (ii) a RecogDrive-based dual system that we build by replacing its original VLM-2B module with a lightweight ViT-based fast planner and adding an LLM slow planner, evaluated on NAVSIM, where ASSCG achieves 91.4 PDMS (+0.6) and increases average speed by 25%. The project page, including video visualizations and additional results, is available at https://williamxuanyu.github.io/asscg/.

cs.RO↗

arXiv2026

MambaRaw: Selective State Space Modeling for Efficient 4K Raw Image Reconstruction

In-camera JPEG previews are ubiquitous in raw image formats and provide an sRGB reference at negligible storage cost. Although existing metadata-based reconstruction frameworks can exploit this side information when recovering raw images, their context models often become computationally expensive especially at high resolution, eg, 4K raw image, given that attention mechanisms scale quadratically with feature maps, hindering its practical application. To address these limitations, we propose MambaRaw, a JPEG-conditioned metadata-based raw image reconstruction framework that uses State Space Models (SSMs) to estimate entropy parameters efficiently. Our key contribution comprises a Spatial-Energy Coupled Context Modeling mechanism with two lightweight modules: (1) TileMambaBlock, which performs Mamba-style selective scanning only on information-dense tiles to improve the efficiency; and (2) Energy-Aware Refinement (EAR), an identity-initialized residual module that enhance feature representation to match the long-tail energy distribution of raw signals. Extensive experiments on three camera datasets (Sony, Olympus, Samsung) show consistent improvements over strong metadata-based baselines and set a new state of the art for JPEG-guided raw reconstruction with great efficiency. Notably, at low metadata bitrates, MambaRaw increases PSNR by 1.2--1.4 dB and reduces end-to-end coding latency by about 9%. Code is released at https://github.com/Peizeli1/MambaRaw.

cs.CV↗

arXiv2026

New Extremal Ranges and Constructions of the Erdős--Kleitman Problem

For integers $n\ge s\ge2$, let $e(n,s)$ denote the maximum size of a family $\mathcal F\subseteq2^{[n]}$ with no $s$ pairwise disjoint members. The problem of determining $e(n,s)$, now called the Erdős--Kleitman problem, is the non-uniform analogue of the Erdős matching conjecture. We prove that for every fixed $m\ge3$, there exist constants $β_m$ and $δ_m$ such that for sufficiently large $s$, the extremal families for $e(ms+c,s)$ are \[ \mathcal P'(m,s,\ell;L'):=\binom{L'}m\cup\binom{[ms+c]}{\ge m+1} \] for some $L'$ with $\ell=s-c$ and $|L'|=m\ell-1$, when $β_m s^{(m-1)/m}\le c\le δ_m s$. This determines the extremal families in an unknown range when $\ell$ is large, complementing our earlier work on the range when $\ell$ is small. Moreover, for $m=3$, we sharpen this to the asymptotically optimal range. Let \[ t(s)=\frac{17-18s+\sqrt{49-852s+1284s^2}}{20}=0.8916\cdots s+O(1) \] We prove that $\mathcal P'(3,s,\ell;L')$ is the unique extremal family when $t(s)<\ell<s-((4/3)^{1/3}+o(1))s^{2/3}$. Note that the lower bound $t(s)$ of $\ell$ is exact, while the the constant $(4/3)^{1/3}$ in the upper bound of $\ell$ is best possible. Kupavskii and Sokolov introduced four candidate extremal families and conjectured that the value of $e(n,s)$ is the maximum of their sizes. We disprove this conjecture by constructing a new family $\mathcal R(m,s,\ell)$ that is larger than each of their four proposed candidates when $α_{\mathrm R}s^{1/2}\le c\le β_{\mathrm R}s^{(m-1)/m}$ for some constants $α_{\mathrm R}$ and $β_{\mathrm R}$. This also shows that the exponent $(m-1)/m$ in the first result is tight.

math.CO↗

arXiv2026

HERMAN: Hierarchical Representation Matching for CLIP-based Class-Incremental Learning

Class-Incremental Learning (CIL) aims to endow models with the ability to continuously adapt to evolving data streams. Recent advances in pre-trained vision-language models (e.g., CLIP) provide a powerful foundation for this task. However, existing approaches often rely on simplistic templates, such as "a photo of a [CLASS]", which overlook the hierarchical nature of visual concepts. For example, recognizing "cat" versus "car" depends on coarse-grained cues, while distinguishing "cat" from "lion" requires fine-grained details. Similarly, the current feature mapping in CLIP relies solely on the representation from the last layer, neglecting the hierarchical information contained in earlier layers. In this work, we introduce HiErarchical Representation MAtchiNg (HERMAN) for CLIP-based CIL. Our approach leverages LLMs to recursively generate discriminative textual descriptors, thereby augmenting the semantic space with explicit hierarchical cues. These descriptors are matched to different levels of the semantic hierarchy and adaptively routed based on task-specific requirements, enabling precise discrimination while alleviating catastrophic forgetting in incremental tasks. Extensive experiments on multiple benchmarks demonstrate that our method consistently achieves state-of-the-art performance.

cs.CV↗

arXiv2026

Reconstructing Randomly Masked Spectra Helps DNNs Identify Discriminant Wavenumbers

Nondestructive detection methods, based on vibrational spectroscopy, are vitally important in a wide range of applications including industrial chemistry, pharmacy and national defense. Recently, deep learning has been introduced into vibrational spectroscopy showing great potential. Different from images, text, etc. that offer large labeled data sets, vibrational spectroscopic data is very limited, which requires novel concepts beyond transfer and meta learning. To tackle this, we propose a task-enhanced augmentation network (TeaNet). The key component of TeaNet is a reconstruction module that inputs randomly masked spectra and outputs reconstructed samples that are similar to the original ones, but include additional variations learned from the domain. These augmented samples are used to train the classification model. The reconstruction and prediction parts are trained simultaneously, end-to-end with back-propagation. Results on both synthetic and real-world datasets verified the superiority of the proposed method. In the most difficult synthetic scenarios TeaNet outperformed CNN by 17%. We visualized and analysed the neuron responses of TeaNet and CNN, and found that TeaNet's ability to identify discriminant wavenumbers was excellent compared to CNN. Our approach is general and can be easily adapted to other domains, offering a solution to more accurate and interpretable few-shot learning.

cs.LG↗