Searcharxiv⌕ Search

arXiv subjects

Quan Wang

Publications and source records attributed to Quan Wang.

At least 37 records · Page 2Linked to original sources

A center manifold reduction approach to the Darcy-Bénard convection problem with non-zero Prandtl number

We study the bifurcation of two-dimensional Darcy-Bénard convection (DBC) in a rectangular domain, a canonical model for thermal convection in porous media with applications in geophysics and engineering. The momentum equation lacks advection and viscous dissipation, being regularized solely by a linear Darcy damping term. As a result, the linearized operator generates a semigroup that is neither analytic nor compact and the nonlinear term fails to be Lipschitz. The system is thus placed outside the scope of the standard center-manifold theorem. To overcome these obstructions, we develop a center-manifold reduction adapted to DBC system. Our main result is a constructive proof of the existence of the center manifold function h and local attractivity of the center manifold-the exponential convergence of small solutions toward it-without relying on analyticity of the full linear semigroup and Lipschitz nonlinearity. We circumvent these difficulties by exploiting the partially dissipative structure: the temperature equation is governed by the Laplacian, which generates an analytic semigroup and provides the smoothing needed to compensate for the lack of regularity in the velocity and the absence of global Lipschitz bounds. Through carefully designed inequalities, we establish both the construction of the center manifold function h and the exponential convergence of nearby solutions. Explicit approximations for the center manifold are derived in two scenarios-one simple eigenvalue and two distinct eigenvalues-yielding reduced systems of ordinary differential equations whose analysis determines the bifurcation type. Numerical simulations are presented to corroborate the theoretical results.

math.AP↗

TransPhy: Visual In-Context Learning for Physically Grounded Image Editing

Visual demonstrations provide a natural interface for specifying image transformations that are difficult to describe exhaustively with text. However, existing visual in-context learning (VICL) methods primarily focus on appearance-level relation transfer and provide limited support for physically grounded transformations, whose outcomes depend on material properties, geometry, object interactions, and environmental conditions. Given a source--target exemplar pair and a query image, physically grounded VICL requires a model to infer the demonstrated transformation, adapt its effects to the query-specific scene context, and preserve rule-irrelevant content. We introduce PhysVICL-74, comprising 74 physically grounded transformation rules and 5,240 source--target image pairs that form nearly 75K training and evaluation contexts. Its benchmark split separately evaluates novel-instance transfer and unseen-rule generalization. We further propose TransPhy, a framework that decomposes physically grounded VICL into physical-rule induction and transition-aligned rendering. TransPhy first predicts the demonstrated rule and an explicit query-specific target-state description, and then synthesizes the target image through token-wise mixture-of-experts adaptation, with expert routing guided by localized transition cues. Experiments show that TransPhy improves physical-rule adherence, query consistency, and unseen-rule generalization over existing visual in-context editing methods.

cs.CV↗

SPARGen: Unifying Spatial Perception and Reasoning through Native Multimodal Generation

Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations. Existing approaches typically address these capabilities separately using task-specific architectures or external geometric modules, limiting knowledge transfer among complementary representations of the same physical scene. We introduce SPARGen, a unified multimodal framework that casts 3D reconstruction, dense correspondence, and spatial reasoning as instruction-conditioned generation tasks. SPARGen serializes compact structured and linguistic outputs as token sequences while generating dense geometric fields in image-aligned forms, enabling spatial supervision to jointly shape shared representations within a native multimodal generative model. Experiments across benchmarks for 3D reconstruction, correspondence, and spatial reasoning show that SPARGen achieves competitive performance across heterogeneous spatial tasks within a single native multimodal generative framework.

cs.CV↗

Distribution of magnetic helicity and energy with height in solar atmosphere

Magnetic helicity and magnetic energy are key to understanding the solar dynamo and eruptions, and their three-dimensional distributions are of great significance. However, how these quantities vary with height remains poorly understood. Moreover, because the three-dimensional distribution depends on magnetic field extrapolation, determining the optimal extrapolation height from physical rather than empirical criteria remains an open problem. To address this issue, this work investigates the vertical distributions of magnetic helicity and magnetic energy in the solar corona within active regions. We analyze 150 active regions observed by the Solar Magnetic Field Telescope (SMFT) from 1988 to 2019, grouped by absolute magnetic flux, perform nonlinear force-free field (NLFFF) extrapolations, and compute the relative magnetic helicity with a finite volume method. It is found that an extrapolation height of at least 81 Mm retains 97% of the total magnetic helicity and energy while reducing computational costs by approximately 38% under the adopted configuration. This work provides important parameter constraints for the long-term statistical study of magnetic helicity in solar active regions.

astro-ph.SR↗

New Statistical Topology Theory Predicts Turbulent Magnetic Emergence from the Sun's Interior

We propose and verify a new statistical topology framework to study the complex magnetic field evolution of Sun-like stars. The Sun, as the star we are most familiar with, exhibits chaotic behaviors such as solar flares and mass ejections that are crucial to the Earth. While these phenomena are mainly driven by the magnetic field, it has been challenging to understand the complex magnetic field. In this paper, we propose a new model to understand the helicity behavior of magnetic loops before their emergence from the interior by advancing the loop ensemble theory from statistical physics. We derive several new power-law scalings that are essential to the Sun's magnetic field, including magnetic flux, magnetic helicity, and linking number. We examine our prediction by a large data analysis through long-term continuous observation over 32 yr. These results not only provide evidence for the new statistical topology framework but also systematically explain the intrinsic unpredictability on the emergence of extreme solar activities. This new discovery on the critical structure of loop ensemble can also be applied to a wide range of turbulence systems.

astro-ph.SR↗

WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editing

Recent one-step text-to-image (T2I) models enable efficient image synthesis and provide new opportunities for real-time image editing. However, existing one-step editing methods primarily rely on text conditioning for semantic transformation, lacking explicit spatial control over \textit{where} to edit. More importantly, even when spatial constraints are introduced, these methods often struggle to achieve strong and stable semantic modifications within the target regions. In this work, we revisit one-step image editing from a spatially controlled perspective and identify two key challenges: discovering editable regions and achieving effective localized semantic transformation. We reveal that existing methods perform global semantic transport, which limits high-intensity local editing under the one-step setting. To address this issue, we propose \textbf{WhereEdit}, a framework that reformulates one-step editing as localized adaptive editing. WhereEdit automatically identifies semantically relevant regions from internal model features and applies adaptive local modulation to enhance target-region editing while preserving non-target areas and structural consistency. Experiments on the PIE-Bench benchmark demonstrate that WhereEdit consistently outperforms existing one-step image editing methods, achieving superior editing quality while maintaining the efficiency of one-step generation. Additional experiments with region-level supervision further highlight the importance of explicit spatial reasoning for high-quality one-step image editing.

cs.CV↗

MEDN: Motion-Emotion Feature Decoupling Network for Micro-Expression Recognition

Unlike macro-expression, micro-expression does not follow a strictly consistent mapping rule between emotions and Action Units (AUs). As a result, some micro-expressions share identical AUs yet represent completely opposite emotional categories, making them highly visually similar. Existing microexpression recognition (MER) methods mostly rely on explicit facial motion cues (e.g., optical flow, frame differences, AU features) while ignoring implicit emotion information. To tackle this issue, this paper presents a Motion Emotion Feature Decoupling Network (MEDN) for MER. We design a dual-branch framework to separately extract motion and emotion features. In the motion branch, an AU-detection task restricts features to the explicit motion domain, and orthogonal loss is adopted to reduce motion emotion feature coupling. For implicit emotion modeling, we propose a Sparse Emotion Vision Transformer (SEVit) that sparsifies spatial tokens to highlight local temporal variations with multi-scale sparsity rates. A Collaborative Fusion Module (CoFM) is further developed to fuse disentangled motion and emotion features adaptively. Extensive experiments on three benchmark datasets validate that MEDN effectively decouples motion and emotion features and achieves superior recognition performance, offering a new perspective for enhancing recognition accuracy and generalization.

cs.CV↗

Vision as Unified Multimodal Generation

We formulate computer vision as unified multimodal generation, where heterogeneous visual tasks are expressed in the native text and image generation spaces of a unified multimodal model, without task-specific architectures. Under this formulation, SenseNova-Vision uses natural-language instructions and optional visual prompts to specify tasks, target regions or views, and decoding conventions, and generates responses as text for symbolic outputs, images for dense spatial predictions, or mixed text-and-image outputs for compositional tasks. To support large-scale training, we convert diverse computer vision annotations into instruction-response examples compatible with these generation spaces, resulting in the SenseNova-Vision Corpus, a computer-vision instruction-response corpus spanning text, image, and mixed targets. Starting from an off-the-shelf pretrained unified multimodal model, SenseNova-Vision is trained primarily on this corpus, with auxiliary multimodal data used as a capability-preserving mixture, and requires no task-specific prediction heads or architectural modifications. The resulting model covers a broad range of vision tasks, including detection, OCR, keypoint estimation, segmentation, depth estimation, surface normal prediction, point maps, and camera pose estimation, while supporting language-defined variants that combine category, color, region, and other visual cues. Experiments show that a single unified model can match leading task-specialized systems across structured visual understanding, dense geometric prediction, segmentation, and multi-view visual geometry. These results suggest unified multimodal generation as a scalable route for integrating computer vision capabilities into general-purpose foundation models. The model and corpus are publicly available.

cs.CV↗

Training-Free Open-Vocabulary Visual Grounding for Remote Sensing Images and Videos

Remote sensing visual grounding (RSVG) aims to localize a referred target in a remote sensing image or video according to a natural language expression. Existing RSVG methods usually rely on task-specific manual annotations, which are costly to collect and inevitably limited in covering the diversity of real-world geospatial scenarios. As a result, they often struggle to generalize to open-vocabulary queries involving novel objects, fine-grained attributes, complex spatial relationships, and functional semantics. In this paper, we propose RSVG-ZeroOV, a training-free framework that leverages frozen generic foundation models for zero-shot open-vocabulary RSVG. RSVG-ZeroOV follows an Overview-Focus-Evolve paradigm, which exploits the distinct yet complementary attention patterns of vision-language models (VLMs) and diffusion models (DMs) to progressively generate precise grounding results. Specifically, (i) Overview utilizes a VLM to extract cross-attention maps that capture semantic correlations between the referring expression and visual regions; (ii) Focus leverages the fine-grained modeling priors of a DM to compensate for object structure and shape information often overlooked by VLM attention; and (iii) Evolve introduces a simple yet effective attention evolution module to suppress irrelevant activations, yielding purified object masks. To handle video inputs, we further present Video RSVG-ZeroOV, which extends image-level grounding to spatio-temporal grounding through a query-relevant key-frame selector and a temporal propagator, enabling efficient and temporally coherent video grounding without video annotations or fine-tuning. Extensive experiments on six image and video grounding benchmarks show that RSVG-ZeroOV consistently outperforms existing zero-shot baselines and achieves competitive or superior performance compared with weakly- and fully-supervised methods.

cs.CV↗

Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants

Quadruped robots are capable of traversing a wide range of complex terrains with high flexibility. As highly mobile ground-based intelligent platforms, they can be equipped with modules for navigation control, environmental perception, and intelligent interaction, thereby serving as real-world mobile deployment platforms for various algorithms. In this paper, we introduce Y-BotFrame, an extensible embodied platform that turns a robot into an intelligent ground assistant. Y-BotFrame integrates multimodal perception capabilities, including speech, vision, and LiDAR, and employs a large language model as the cognitive core for environmental understanding, contextual reasoning, and task planning. The system maps user natural-language instructions into executable embodied task units that can be carried out by the robot. Y-BotFrame supports natural interaction through voice commands and visual feedback, removing the need for a remote controller and enabling efficient human-robot collaboration. With a highly extensible framework, Y-BotFrame supports plug-and-play integration of new functional modules as well as modular upgrades and iterative development, offering a reference implementation for the real-world deployment of general-purpose, instruction-driven embodied agents.The supplementary video is available at https://xdei-group.github.io/Y-BotFrame/.

cs.RO↗

AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents

Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring, and emergency response. However, most UAV applications still rely on pre-defined command sequences or task-specific pipelines, where developers manually connect perception, planning, flight control, simulation, logging, and safety modules. This limits the flexibility, reproducibility, and extensibility of autonomous aerial systems. This paper presents AerialClaw, an open-source software framework that enables UAVs to operate as decision-making aerial agents rather than merely command-following platforms. Given a natural-language mission, AerialClaw allows an LLM-based agent to understand the task, maintain context, invoke executable aerial skills, observe perception and runtime feedback, and iteratively update its decisions in a closed loop. The framework adopts a modular brain-skill-runtime architecture, combining hard skills for atomic UAV operations, Markdown-based soft skills for reusable task strategies, document-driven agent state and capability boundaries, memory-driven reflection, safety-oriented runtime validation, and platform-agnostic execution adapters. AerialClaw supports lightweight mock execution, PX4 SITL with Gazebo, and AirSim-based simulation, together with a web console, pluggable model backends, example missions, simulation assets, and staged deployment scripts. By combining standardized aerial skills, document-driven agent state, memory, and closed-loop LLM decision-making, AerialClaw provides a reproducible and extensible open-source framework for building UAV systems that can interpret missions, make decisions, execute skills, and adapt their behavior from feedback.

cs.RO↗

From Pixels to Words -- Towards Native One-Vision Models at Scale

Current vision-language models (VLMs) typically stitch together separate image encoders and language decoders via multi-stage alignment, a modular framework that inevitably fragments pixel-level signals across frames and scatters early pixel-word interactions. In parallel, native VLMs, despite impressive performance on single images, remain largely unexplored in multi-image, video understanding, and spatial intelligence. Hence, we introduce NEO-ov, a native foundation model that learns cross-frame and pixel-word correspondence end-to-end, without any external encoders, auxiliary adapters, or post-hoc fusion. By eliminating module boundaries entirely, NEO-ov enables fine-grained and unified spatiotemporal modeling to emerge natively inside the model. Notably, NEO-ov largely narrows the gap to modular counterparts while excelling at fine-grained visual perception, validating that native "one-vision" architectures are not only feasible but competitive at scale. Beyond empirical performance, we unveil systematic architectural analyses and detailed training recipes to facilitate subsequent native multimodal modeling. Our code and models are publicly available at: https://github.com/EvolvingLMMs-Lab/NEO.

cs.CV↗

Data-Driven Structural Health Monitoring of Short Carbon Fiber-Reinforced Polymer Composites via Multiphysics Phase-Field Simulation

Short carbon fiber-reinforced polymer (SCFRP) composites exploit the intrinsic conductivity of the carbon fiber network for self-sensing, yet no predictive model couples their anisotropic, rate-dependent fracture to piezoresistive damage identification. This work presents a finite deformation multiphysics phase-field framework coupling a viscoelastic-viscoplastic constitutive model, an anisotropic crack resistance formulation, and a piezoresistive conductivity model. The three sub-problems are unified through the second-order fiber orientation tensor, which simultaneously defines fiber family directions, crack resistance anisotropy, and principal conduction paths of the carbon fiber network. A damage-coupled conductivity tensor captures both strain-driven geometric-kinematic resistance changes and irreversible network severance driven by the phase-field variable. The framework is coupled to an eight-electrode electrical impedance tomography configuration, and the normalized inter-electrode conductance ratios serve as inputs to a feedforward artificial neural network that infers normalized crack length and mechanical compliance without mechanical sensing. The network achieves R2 = 0.99 on held-out configurations, confirming generalization across the microstructure space. The framework establishes a physics-based, computationally efficient route for real-time structural health monitoring and inverse damage assessment in SCFRP composites.

cs.CE↗

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture

Recent large vision-language models (VLMs) remain fundamentally constrained by a persistent dichotomy: understanding and generation are treated as distinct problems, leading to fragmented architectures, cascaded pipelines, and misaligned representation spaces. We argue that this divide is not merely an engineering artifact, but a structural limitation that hinders the emergence of native multimodal intelligence. Hence, we introduce SenseNova-U1, a native unified multimodal paradigm built upon NEO-unify, in which understanding and generation evolve as synergistic views of a single underlying process. We launch two native unified variants, SenseNova-U1-8B-MoT and SenseNova-U1-A3B-MoT, built on dense (8B) and mixture-of-experts (30B-A3B) understanding baselines, respectively. Designed from first principles, they rival top-tier understanding-only VLMs across text understanding, vision-language perception, knowledge reasoning, agentic decision-making, and spatial intelligence. Meanwhile, they deliver strong semantic consistency and visual fidelity, excelling in conventional or knowledge-intensive any-to-image (X2I) synthesis, complex text-rich infographic generation, and interleaved vision-language generation, with or without think patterns. Beyond performance, we show detailed model design, data preprocessing, pre-/post-training, and inference strategies to support community research. Last but not least, preliminary evidence demonstrates that our models extend beyond perception and generation, performing strongly in vision-language-action (VLA) and world model (WM) scenarios. This points toward a broader roadmap where models do not translate between modalities, but think and act across them in a native manner. Multimodal AI is no longer about connecting separate systems, but about building a unified one and trusting the necessary capabilities to emerge from within.

cs.CV↗

Real-time diffuse correlation spectroscopy with a chip-based correlator for measuring human cerebral blood flow and brain function

Diffuse correlation spectroscopy (DCS) is a noninvasive optical technique that probes microvascular blood flow in deep tissues. Here, we present and validate a new on-chip hardware correlator for high-speed DCS measurements. The correlator is embedded in a custom-built 512 x 512 single-photon avalanche diode (SPAD) array named ATLAS, which computes intensity autocorrelation functions directly on-chip at a sampling rate of 116 Hz - the fastest DCS acquisition reported to date. Unlike conventional DCS systems that suffer from low light throughput and therefore cannot resolve cardiac pulsations at source-detector separations (rho) beyond 30 mm, our massively parallel on-chip architecture computes autocorrelations within each macropixel, eliminating the data-throughput bottleneck. This enables high-SNR, real-time detection of pulsatile blood flow even at rho = 50 mm on the human forehead. In phantom experiments at rho = 25 mm, ATLAS-DCS achieves a 12-fold improvement in signal-to-noise ratio over a conventional single-channel DCS instrument while operating at 116 Hz. In human subjects, we resolve functional hyperemia during a mental arithmetic task at rho = 30 mm. Furthermore, we integrate ATLAS DCS with a frequency-domain near-infrared spectroscopy (FD-NIRS) module, enabling simultaneous monitoring of blood flow and tissue oxygenation. With this combined system, we can concurrently resolve core hemodynamic parameters. The on-chip parallelized DCS design substantially improves detection speed, depth sensitivity, and real-time capability, paving the way for wearable, high-speed cerebral blood flow monitoring in both clinical and research settings.

physics.ins-det↗

VideoAgent: Personalized Synthesis of Scientific Videos

The technical complexity of research papers often limits their reach, necessitating more accessible formats like scientific videos to disseminate key insights through engaging narration. However, existing automated methods primarily focus on static posters or slide presentations that remain template-bound and linear. Shifting to audience-adaptive video synthesis requires addressing non-linear narrative orchestration and the joint synchronization of disparate multimodal assets. We introduce VideoAgent, a modular framework that redefines scientific video synthesis as an intent-driven planning problem. By decoupling content understanding from multimodal synthesis, VideoAgent adaptively interleaves static slides with dynamic animations to match the semantic density of the narration. We further propose SciVidEval, a benchmark evaluating multimodal quality and pedagogical utility through automated metrics and human knowledge transfer studies. Extensive experiments demonstrate that VideoAgent effectively conveys complex technical logic with high narrative fidelity and communicative impact.

cs.AI↗

Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) by incorporating retrieved documents and/or generated context. However, LLMs often exhibit a stylistic bias when presented with mixed contexts, favoring fluent but hallucinated generated content over factually grounded yet disorganized retrieved evidence. This phenomenon reveals that the utility of retrieved information is bottlenecked by its presentation. To bridge this gap, we propose QREAM, a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts, better for LLM readers to utilize. Our framework consists of two stages: (1) QREAM-ICL, which uses stylistic seeds to guide iterative rewriting exploration; and (2) QREAM-FT, a lightweight student model distilled from denoised ICL outputs. QREAM-FT employs dual-criteria rejection sampling, filtering based on answer correctness and factual consistency to ensure high-quality supervision. QREAM seamlessly integrates into existing RAG pipelines as a plug-and-play module. Experiments demonstrate that QREAM consistently enhances advanced RAG pipelines, yielding up to 8% relative improvement with negligible latency overhead, effectively balancing question relevance with factual grounding.

cs.CL↗

A Major Geomagnetic Storm in 2024 October Linked to Sympathetic CME--Prominence Eruptions

Improving predictions of the geomagnetic impact of coronal mass ejections (CMEs) requires understanding how solar source properties relate to in-situ measurements at Earth. However, major geomagnetic storms frequently arise from interacting CMEs, complicating the link back to their solar origins. We analyze a CME interaction event that caused a major geomagnetic storm in 2024 October 10-11 (D$_{st}$ $\sim$-333 nT). Multiviewpoint observations reveal that the storm was related to a sympathetic eruption involving a quiescent filament and an active-region CME. The coronagraph on board the Advanced Space-based Solar Observatory clearly shows that this sympathetic eruption resulted in two distinct CMEs. Due to the overlap of the CMEs in the coronagraph field of view (FOV), a spheroid shock model was used to fit the observed shock. Kinematic analysis indicates that the interacting CMEs had completed their impulsive acceleration phase before entering the coronagraph FOV, with a slow deceleration continuing beyond 100 R$_\odot$. In-situ measurements indicate that the enhanced southward magnetic fields, arising from compression during CME interactions, were the primary driver of the storm. Compared to photospheric fields, the in-situ magnetic fields suggest that the trailing CME maintained flux-rope-like signatures consistent with the source region. In contrast, the compressed leading CME displayed varying magnetic configurations between Wind and STEREO-A, featuring distorted flux-rope signatures and inconsistent inferred axis orientations. Our study bridges solar source dynamics to in-situ multipoint measurements, providing key insights for space weather prediction. Nevertheless, the direct linkage between source-region magnetic field configurations and these measurements remains tentative and requires further investigation.

astro-ph.SR↗