arXiv subjects

Yue Yang

Publications and source records attributed to Yue Yang.

At least 73 records · Page 4Linked to original sources

arXiv2026

DreamHome-Pano: Design-Aware and Conflict-Free Panoramic Interior Generation

In modern interior design, the generation of personalized spaces frequently necessitates a delicate balance between rigid architectural structural constraints and specific stylistic preferences. However, existing multi-condition generative frameworks often struggle to harmonize these inputs, leading to "condition conflicts" where stylistic attributes inadvertently compromise the geometric precision of the layout. To address this challenge, we present DreamHome-Pano, a controllable panoramic generation framework designed for high-fidelity interior synthesis. Our approach introduces a Prompt-LLM that serves as a semantic bridge, effectively translating layout constraints and style references into professional descriptive prompts to achieve precise cross-modal alignment. To safeguard architectural integrity during the generative process, we develop a Conflict-Free Control architecture that incorporates structural-aware geometric priors and a multi-condition decoupling strategy, effectively suppressing stylistic interference from eroding the spatial layout. Furthermore, we establish a comprehensive panoramic interior benchmark alongside a multi-stage training pipeline, encompassing progressive Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Experimental results demonstrate that DreamHome-Pano achieves a superior balance between aesthetic quality and structural consistency, offering a robust and professional-grade solution for panoramic interior visualization.

cs.CV↗

arXiv2026

FloorplanVLM: A Vision-Language Model for Floorplan Vectorization

Converting raster floorplans into engineering-grade vector graphics is challenging due to complex topology and strict geometric constraints. To address this, we present FloorplanVLM, a unified framework that reformulates floorplan vectorization as an image-conditioned sequence modeling task. Unlike pixel-based methods that rely on fragile heuristics or query-based transformers that generate fragmented rooms, our model directly outputs structured JSON sequences representing the global topology. This 'pixels-to-sequence' paradigm enables the precise and holistic constraint satisfaction of complex geometries, such as slanted walls and curved arcs. To support this data-hungry approach, we introduce a scalable data engine: we construct a large-scale dataset (Floorplan-2M) and a high-fidelity subset (Floorplan-HQ-300K) to balance geometric diversity and pixel-level precision. We then employ a progressive training strategy, using Supervised Fine-Tuning (SFT) for structural grounding and quality annealing, followed by Group Relative Policy Optimization (GRPO) for strict geometric alignment. To standardize evaluation on complex layouts, we establish and open-source FPBench-2K. Evaluated on this rigorous benchmark, FloorplanVLM demonstrates exceptional structural validity, achieving $\textbf{92.52%}$ external-wall IoU and robust generalization across non-Manhattan architectures.

cs.CV↗

arXiv2026

Integrated laser heating stage with active geometry modulation for simultaneous in-situ X-ray transmission and evolved gas analysis of molten liquids

We report the design and development of a compact, integrated laser heating stage tailored for in situ high-temperature X ray transmission studies of molten oxides. In horizontal beam geometries, widely used in both laboratory and synchrotron facilities, the natural spreading (wetting) of molten samples on substrates significantly reduces the effective vertical optical path length, detrimental to signal quality in transmission-mode measurements. To overcome this limitation, we introduced a thermocouple assisted active geometry modulation technique. This method mechanically lifts the spreading melt into a liquid bridge via surface tension, optimizing the transmission path length while simultaneously enabling in situ temperature monitoring. The device features a triple fiber coupled laser head with high power density, a precision closed loop Proportional Integral Derivative temperature control system, and an atmosphere controlled vacuum chamber coupled with a mass spectrometer. This integration allows for simultaneous evolved gas analysis, enabling the correlation of structural phase transitions with chemical volatilization or reaction dynamics. Validated by tracking the melting kinetics of a multicomponent glass precursor, this versatile setup provides a comprehensive solution for high quality data acquisition in X ray transmission experiments across various sources.

physics.app-ph↗

arXiv2026

Multimodal Feedback for Handheld Tool Guidance: Combining Wrist-Based Haptics with Augmented Reality

We investigate how vibrotactile wrist feedback can enhance spatial guidance for handheld tool movement in optical see-through augmented reality (AR). While AR overlays are widely used to support surgical tasks, visual occlusion, lighting conditions, and interface ambiguity can compromise precision and confidence. To address these challenges, we designed a multimodal system combining AR visuals with a custom wrist-worn haptic device delivering directional and state-based cues. A formative study with experienced surgeons and residents identified key tool maneuvers and preferences for reference mappings, guiding our cue design. In a cue identification experiment (N=21), participants accurately recognized five vibration patterns under visual load, with higher recognition for full-actuator states than spatial direction cues. In a guidance task (N=27), participants using both AR and haptics achieved significantly higher spatial precision (5.8 mm) and usability (SUS = 88.1) than those using either modality alone, despite having modest increases in task time. Participants reported that haptic cues provided reassuring confirmation and reduced cognitive effort during alignment. Our results highlight the promise of integrating wrist-based haptics into AR systems for high-precision, visually complex tasks such as surgical guidance. We discuss design implications for multimodal interfaces supporting confident, efficient tool manipulation.

cs.HC↗

arXiv2026

Milestones over Outcome: Unlocking Geometric Reasoning with Sub-Goal Verifiable Reward

Multimodal Large Language Models (MLLMs) struggle with complex geometric reasoning, largely because "black box" outcome-based supervision fails to distinguish between lucky guesses and rigorous deduction. To address this, we introduce a paradigm shift towards subgoal-level evaluation and learning. We first construct GeoGoal, a benchmark synthesized via a rigorous formal verification data engine, which converts abstract proofs into verifiable numeric subgoals. This structure reveals a critical divergence between reasoning quality and outcome accuracy. Leveraging this, we propose the Sub-Goal Verifiable Reward (SGVR) framework, which replaces sparse signals with dense rewards based on the Skeleton Rate. Experiments demonstrate that SGVR not only enhances geometric performance (+9.7%) but also exhibits strong generalization, transferring gains to general math (+8.0%) and other general reasoning tasks (+2.8%), demonstrating broad applicability across diverse domains.

cs.LG↗

arXiv2025

GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations, including the risk of test data contamination from textbook-based benchmarks, overemphasis on final answers over reasoning processes, and insufficient diagnostic granularity. To address these issues, we present GeoBench, a hierarchical benchmark featuring four reasoning levels in geometric problem-solving: Visual Perception, Goal-Oriented Planning, Rigorous Theorem Application, and Self-Reflective Backtracking. Through six formally verified tasks generated via TrustGeoGen, we systematically assess capabilities ranging from attribute extraction to logical error correction. Experiments reveal that while reasoning models like OpenAI-o3 outperform general MLLMs, performance declines significantly with increasing task complexity. Key findings demonstrate that sub-goal decomposition and irrelevant premise filtering critically influence final problem-solving accuracy, whereas Chain-of-Thought prompting unexpectedly degrades performance in some tasks. These findings establish GeoBench as a comprehensive benchmark while offering actionable guidelines for developing geometric problem-solving systems.

cs.CV↗

arXiv2025

Non-Euclidean interfaces decode the continuous landscape of graphene-induced surface reconstructions

Interfacial reconstruction between two-dimensional (2D) materials and metal substrates fundamentally governs heterostructure properties, yet conventional flat substrates fail to capture the continuous crystallographic landscape. Here, we overcome this topological limitation using non-Euclidean interfaces-curved 2D graphene-copper surfaces as a model system-to traverse the infinite spectrum of lattice orientations. By integrating multimodal microscopy with a deep-learning-enhanced dimensional upscaling framework, we translate 2D scanning electron microscopy (SEM) contrast into quantitative three-dimensional (3D) morphologies with accurate facet identification. Coupling these observations with machine-learning-assisted density functional theory, we demonstrate that reconstruction is governed by a unified thermodynamic mechanism where high-index facets correspond to specific local minima in the surface energy landscape. This work resolves the long-standing complexity of graphene-copper faceting and establishes non-Euclidean surface topologies as a generalizable paradigm for decoding and controlling interfacial reconstruction in diverse metal-2D material systems.

cond-mat.mes-hall↗

arXiv2025

Modeling Noise in Quantum Computing of Scalar Convection

Quantum computing holds potential for accelerating the simulation of fluid dynamics. However, hardware noise in the noisy intermediate-scale quantum era significantly distorts simulation accuracy. Although error magnitudes are frequently quantified, the specific physical effects of quantum noise on flow simulation results remain largely uncharacterized. We investigate the influence of gate noise on the quantum simulation of one-dimensional scalar convection. By employing a quantum spectral algorithm where ideal time advancement affects only Fourier phases, we isolate and analyze noise-induced artifacts in spectral magnitudes. We derive a theoretical transition matrix based on Hamming distances between computational basis states to predict spectral decay, and then validate this model against density-matrix simulations and experiments on a superconducting quantum processor. Furthermore, using data-driven sparse regression, we demonstrate that quantum noise manifests in the effective partial differential equation primarily as artificial diffusion and nonlinear source terms. These findings suggest that quantum errors can be modeled as deterministic physical terms rather than purely stochastic perturbations.

quant-ph↗

arXiv2025

Formation of external particle jets on a spherical particle bed subjected to strong explosive loading

We report the mechanism for the formation of external particle jets on a spherical particle bed subjected to strong explosive loading, revealing a critical dependence on particle size. Under strong explosive loading, the formation of external particle jets is primarily driven by a drag-coupled mechanism. We conducted Eulerian-Lagrangian simulations, with up to $2048^3$ effective cells and $1.8$ million tracked parcels on an adaptive mesh, for both small- and large-particle cases. Pronounced jets are observed only with small particles, alongside accelerated bed thickening. By defining characteristic inner and outer radii, the particle bed thickness evolution is quantified, showing an initial linear growth followed by a nonlinear deceleration. Particle dynamics analysis indicates that drag force dominates particle motion and jet formation during the nonlinear stage. The initial angular non-uniformity of the particle bed induces a non-uniform gas radial velocity. Through drag coupling, this flow asymmetry generates a radial velocity difference in small particles, thereby promoting pronounced jet formation, whereas large particles resist this drag-induced effect. The greater drag-induced deceleration on smaller particles leads to an increased velocity difference across the particle bed, explaining the accelerated thickening. A characteristic radius model that integrates the Gurney model for the linear stage with a drag-dominated deceleration model for the nonlinear stage is established and shows good agreement with numerical results across different particle sizes.

physics.flu-dyn↗

arXiv2025

CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation

Configuring computational fluid dynamics (CFD) simulations requires significant expertise in physics modeling and numerical methods, posing a barrier to non-specialists. Although automating scientific tasks with large language models (LLMs) has attracted attention, applying them to the complete, end-to-end CFD workflow remains a challenge due to its stringent domain-specific requirements. We introduce CFD-copilot, a domain-specialized LLM framework designed to facilitate natural language-driven CFD simulation from setup to post-processing. The framework employs a fine-tuned LLM to directly translate user descriptions into executable CFD setups. A multi-agent system integrates the LLM with simulation execution, automatic error correction, and result analysis. For post-processing, the framework utilizes the model context protocol (MCP), an open standard that decouples LLM reasoning from external tool execution. This modular design allows the LLM to interact with numerous specialized post-processing functions through a unified and scalable interface, improving the automation of data extraction and analysis. The framework was evaluated on benchmarks including the NACA~0012 airfoil and the three-element 30P-30N airfoil. The results indicate that domain-specific adaptation and the incorporation of the MCP jointly enhance the reliability and efficiency of LLM-driven engineering workflows.

cs.SE↗

arXiv2025

Modelling and synthesizing turbulence with multi-scale coherent vortices

Turbulence is a complex system exhibiting both universal statistical features and prominent coherent structures. We model turbulence using coherent vortices distributed within a multi-scale statistical framework, termed `woven turbulence'. These entangled vortices are generated based on fractional Brownian bridges, with scale-dependent parameters set by dimensional analysis and geometric similarity. By integrating statistical and structural modeling, our approach naturally captures both the universal statistical features of turbulence and its coherent vortex structures. The spatial filling fraction of vortices in woven turbulence, termed `vortex density', is tunable, enabling us to investigate the statistical-structural interaction and uncover two concise physical insights of turbulence. First, the invariance of the hierarchical vortex density across scales corresponds to Kolmogorov's $-5/3$ law in the inertial range. Second, there exists a critical total vortex density at which the intermittency of woven turbulence closely matches that of real turbulence, and this critical density converges to a finite value in the inviscid limit. Deviating from this critical density reveals a negative correlation between intermittency and total vortex density. In addition, woven turbulence also serves as a fast turbulence synthesis method, requiring only the Taylor-Reynolds number as input and exhibiting an extremely low computational cost proportional to the grid size. It generates instantaneous turbulent fields at Taylor-Reynolds numbers of order $10^3$ on $4096^3$ grid points, with computational cost over five orders of magnitude lower than that of direct numerical simulation.

physics.flu-dyn↗

arXiv2025

Deep reinforcement learning based navigation of a jellyfish-like swimmer in flows with obstacles

We develop a deep reinforcement learning framework for controlling a bio-inspired jellyfish swimmer to navigate complex fluid environments with obstacles. While existing methods often rely on kinematic and geometric states, a key challenge remains in achieving efficient obstacle avoidance under strong fluid-structure interactions and near-wall effects. We augment the agent's state representation within a soft actor-critic algorithm to include the real-time forces and torque experienced by the swimmer, providing direct mechanical feedback from vortex-wall interactions. This augmented state space enables the swimmer to perceive and interpret wall proximity and orientation through distinct hydrodynamic force signatures. We analyze how these force and torque patterns, generated by walls at different positions influence the swimmer's decision-making policy. Comparative experiments with a baseline model without force feedback demonstrate that the present one with force feedback achieves higher navigation efficiency in two-dimensional obstacle-avoidance tasks. The results show that explicit force feedback facilitates earlier, smoother maneuvers and enables the exploitation of wall effects for efficient turning behaviors. With an application to autonomous cave mapping, this work underscores the critical role of direct mechanical feedback in fluid environments and presents a physics-aware machine learning framework for advancing robust underwater exploration systems.

physics.flu-dyn↗

arXiv2025

Constructing wall turbulence using hierarchical hairpin vortices

Wall-bounded turbulence is characterized by coherent, worm-like structures such as hairpin vortices. The attached-eddy model provides a successful statistical framework for the log-law region, yet the complex geometry and multiscale nature of wall-turbulence vortices remain challenging for physics-based modelling. Here, we model wall turbulence as an ensemble of complex vortices, introducing a systematic approach to constructing turbulence fields enriched with hierarchically organized hairpin vortex packets. The geometry and organization of the vortex packets are calibrated to match observations, enabling the model to reproduce both attached and detached motions through a height-dependent core-size variation. Our model successfully reproduces the key statistical and structural features of wall turbulence, matching direct numerical simulations of turbulent channel flow at friction Reynolds numbers from 1,000 to 10,000. More importantly, it also reveals new insights into the coherent structures, emphasizing the role of vortex geometry, packet organization, and hierarchy in setting the attached/detached balance, meandering streaks and inclination angles, superstructure alignment, and the overall partition of contributions. Moreover, the constructed channel turbulence rapidly transitions into fully developed turbulence in direct numerical simulation, demonstrating its physical self-consistency and practical utility for initializing high-fidelity simulations. This approach significantly reduces computational costs associated with turbulence development while providing a flexible framework for testing and advancing turbulence models based on vortex structures.

physics.flu-dyn↗

arXiv2025

A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

cs.CL↗

arXiv2025

Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis

Synthesizing high-quality images from low-field MRI holds significant potential. Low-field MRI is cheaper, more accessible, and safer, but suffers from low resolution and poor signal-to-noise ratio. This synthesis process can reduce reliance on costly acquisitions and expand data availability. However, synthesizing high-field MRI still suffers from a clinical fidelity gap. There is a need to preserve anatomical fidelity, enhance fine-grained structural details, and bridge domain gaps in image contrast. To address these issues, we propose a \emph{cyclic self-supervised diffusion (CSS-Diff)} framework for high-field MRI synthesis from real low-field MRI data. Our core idea is to reformulate diffusion-based synthesis under a cycle-consistent constraint. It enforces anatomical preservation throughout the generative process rather than just relying on paired pixel-level supervision. The CSS-Diff framework further incorporates two novel processes. The slice-wise gap perception network aligns inter-slice inconsistencies via contrastive learning. The local structure correction network enhances local feature restoration through self-reconstruction of masked and perturbed patches. Extensive experiments on cross-field synthesis tasks demonstrate the effectiveness of our method, achieving state-of-the-art performance (e.g., 31.80 $\pm$ 2.70 dB in PSNR, 0.943 $\pm$ 0.102 in SSIM, and 0.0864 $\pm$ 0.0689 in LPIPS). Beyond pixel-wise fidelity, our method also preserves fine-grained anatomical structures compared with the original low-field MRI (e.g., left cerebral white matter error drops from 12.1$\%$ to 2.1$\%$, cortex from 4.2$\%$ to 3.7$\%$). To conclude, our CSS-Diff can synthesize images that are both quantitatively reliable and anatomically consistent.

cs.CV↗

arXiv2025

COSMO-RL: Towards Trustworthy LMRMs via Joint Safety and Stability

Large Multimodal Reasoning Models (LMRMs) are moving into real applications, where they must be both useful and safe. Safety is especially challenging in multimodal settings: images and text can be combined to bypass guardrails, and single objective training can cause policy drift that yields over-refusal on benign inputs or unsafe compliance on risky ones. We present COSMO-RL, a mixed reinforcement learning framework that trains reasoning oriented LMRMs under multimodal, multitask, and multiobjective signals, and we release the resulting model, COSMO-R1. Our approach aims to let safety and capability grow together in one stable pipeline rather than competing during alignment. In experiments, COSMO-R1 improves safety while maintaining-and often improving multimodal reasoning and instruction following, shows stronger robustness to multimodal jailbreaks, and reduces unnecessary refusals. The framework also transfers across backbones with consistent gains. Ablations support the design choices, indicating a simple path to advancing safety and general capability together in LMRMs.

cs.AI↗

arXiv2025

Truly Assessing Fluid Intelligence of Large Language Models through Dynamic Reasoning Evaluation

Recent advances in large language models (LLMs) have demonstrated impressive reasoning capacities that mirror human-like thinking. However, whether LLMs possess genuine fluid intelligence (i.e., the ability to reason abstractly and generalize rules in novel situations) remains an open question. Existing reasoning benchmarks either focus on domain-specific knowledge (crystallized intelligence) or lack interpretability. To address these limitations, we propose DRE-Bench, a dynamic reasoning evaluation benchmark grounded in a hierarchical cognitive framework. DRE-Bench consists of 36 abstract reasoning tasks organized across four cognitive levels, with each task featuring multiple dynamic variants that test the same underlying latent rule. This design enables fine-grained, interpretable, and reliable assessments of fluid intelligence. We evaluate a range of state-of-the-art LLMs, including both general LLMs (GPT-4o, Claude 3.7) and reasoning LLMs (o1, DeepSeek-R1, QwQ, Skywork-OR1). Experimental results reveal that although most LLMs achieve competent and robust performance in low-level cognition, they struggle with high-level cognition and exhibit limited generalization as task complexity grows. Our findings highlight the gap between current LLMs and true human-like fluid intelligence and offer a new path for systematically tracking reasoning progress in LLMs.

cs.AI↗

arXiv2025

Efficient quantum state tomography with Chebyshev polynomials

Quantum computing shows promise for addressing computationally intensive problems but is constrained by the exponential resource requirements of general quantum state tomography (QST), which fully characterizes quantum states through parameter estimation. We introduce the QST with Chebyshev polynomials, an approximate tomography method for pure quantum states encoding complex-valued functions. This method reformulates tomography as the estimation of Chebyshev expansion coefficients, expressed as inner products between the target quantum state and Chebyshev basis functions, measured using the Hadamard test circuit. By treating the truncation order of the Chebyshev polynomials as a controllable parameter, the method provides a practical balance between efficiency and accuracy. For quantum states encoding functions dominated by large-scale features, such as those representing fluid flow fields, appropriate truncation enables faithful reconstruction of the dominant components via quantum circuits with linear depth, while keeping both measurement repetitions and post-processing independent of qubit count, in contrast to the exponential scaling of full measurement-based QST methods. Validation on analytic functions and numerically generated flow-field data demonstrates accurate reconstruction and effective extraction of large-scale features, indicating the method's suitability for systems governed by macroscopic dynamics.

quant-ph↗