Searcharxiv⌕ Search

arXiv subjects

Yue Cao

Publications and source records attributed to Yue Cao.

At least 37 records · Page 2Linked to original sources
arXiv2026

Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport

The scarcity of high-quality imaging data for coronary angiography (CAG) stenosis limits the clinical translation of automated stenosis detection. Synthetic stenosis data provides a practical avenue to augment training sets, improving data quality, diversity, and distributional coverage, and enhancing detection precision and generalization. However, diffusion-based editing commonly relies on soft guidance in a noise-initialized reverse process, offering limited pixel-level precision and structure preservation. We propose the OT-Bridge Editor, which reframes localized editing as a constrained entropic optimal transport (OT) problem and leverages geometric information to steer the generation path, enabling stronger geometric control. Extensive experiments show that our synthesized angiograms consistently improve downstream stenosis detection, yielding substantial relative gains of 27.8% on the public ARCADE benchmark and 23.0% on our multi-center dataset, supported by consistent qualitative results.

cs.CV↗
arXiv2026

Physics-Grounded Understanding of Thermal Boundary Conductance between Ga$_2$O$_3$ and SiC from a Feedforward Neural Network Potential

Ga$_2$O$_3$/SiC heterointegration is attractive for ultra-wide-bandgap power electronics, but interfacial thermal boundary conductance (TBC) remains a major heat-removal bottleneck. Direct experimental access to intrinsic atomistic interfacial transport remains limited, particularly for ideally synthesized materials with defect-free interfacial contact. First-principles simulations are too expensive at relevant length and time scales, while empirical Molecular Dynamics (MD) potentials often lack transferability across oxide and carbide bonding environments. We develop a unified feedforward neural network potential and validate it against density-functional data, bulk phonon dispersions, and anisotropic thermal-conductivity trends in both $β$-Ga$_2$O$_3$ and SiC. Nonequilibrium simulations show that TBC decreases with transport length, increases with temperature, and is consistently higher for Ga$_2$O$_3$$(\bar{2}01)$/SiC(0001) than for Ga$_2$O$_3$(100)/SiC(0001). These trends are explained by attenuation of long-mean-free-path carriers, enhanced incoherent and anharmonic interfacial exchange within broadly unchanged spectral channels, and stronger bonding and vibrational coupling at the $(\bar{2}01)$ interface. The results show how a single transferable feedforward neural network potential can enable large-scale transport prediction and physics-grounded mechanistic understanding of thermal boundary conductance. Code for NEP training and simulation workflows is available at the project repository https://github.com/knowhow07/TBC_Ga2O3_SiC.git

cond-mat.mtrl-sci↗
arXiv2026

InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning

Recent advances in Vision-Language Models (VLMs) have enabled mobile agents to perceive and interact with real-world mobile environments based on human instructions. However, the current fully autonomous paradigm poses potential safety risks when model understanding or reasoning capabilities are insufficient. To address this challenge, we first introduce \textbf{InquireBench}, a comprehensive benchmark specifically designed to evaluate mobile agents' capabilities in safe interaction and proactive inquiry with users, encompassing 5 categories and 22 sub-categories, where most existing VLM-based agents demonstrate near-zero performance. In this paper, we aim to develop an interactive system that actively seeks human confirmation at critical decision points. To achieve this, we propose \textbf{InquireMobile}, a novel model inspired by reinforcement learning, featuring a two-stage training strategy and an interactive pre-action reasoning mechanism. Finally, our model achieves an 46.8% improvement in inquiry success rate and the best overall success rate among existing baselines on InquireBench. We will open-source all datasets, models, and evaluation codes to facilitate development in both academia and industry.

cs.AI↗
arXiv2026

Adaptor: Advancing Assistive Teleoperation with Few-Shot Learning and Cross-Operator Generalization

Assistive teleoperation enhances efficiency via shared control, yet inter-operator variability, stemming from diverse habits and expertise, induces highly heterogeneous trajectory distributions that undermine intent recognition stability. We present Adaptor, a few-shot framework for robust cross-operator intent recognition. The Adaptor bridges the domain gap through two stages: (i) preprocessing, which models intent uncertainty by synthesizing trajectory perturbations via noise injection and performs geometry-aware keyframe extraction; and (ii) policy learning, which encodes the processed trajectories with an Intention Expert and fuses them with the pre-trained vision-language model context to condition an Action Expert for action generation. Experiments on real-world and simulated benchmarks demonstrate that Adaptor achieves state-of-the-art performance, improving success rates and efficiency over baselines. Moreover, the method exhibits low variance across operators with varying expertise, demonstrating robust cross-operator generalization.

cs.RO↗
arXiv2026

Unified Thinker: A General Reasoning Modular Core for Image Generation

Despite impressive progress in high-fidelity image synthesis, generative models still struggle with logic-intensive instruction following, exposing a persistent reasoning--execution gap. Meanwhile, closed-source systems (e.g., Nano Banana) have demonstrated strong reasoning-driven image generation, highlighting a substantial gap to current open-source models. We argue that closing this gap requires not merely better visual generators, but executable reasoning: decomposing high-level intents into grounded, verifiable plans that directly steer the generative process. To this end, we propose Unified Thinker, a task-agnostic reasoning architecture for general image generation, designed as a unified planning core that can plug into diverse generators and workflows. Unified Thinker decouples a dedicated Thinker from the image Generator, enabling modular upgrades of reasoning without retraining the entire generative model. We further introduce a two-stage training paradigm: we first build a structured planning interface for the Thinker, then apply reinforcement learning to ground its policy in pixel-level feedback, encouraging plans that optimize visual correctness over textual plausibility. Extensive experiments on text-to-image generation and image editing show that Unified Thinker substantially improves image reasoning and generation quality.

cs.CV↗
arXiv2026

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

We present daVinci-MagiHuman, an open-source audio-video generative foundation model for human-centric generation. daVinci-MagiHuman jointly generates synchronized video and audio using a single-stream Transformer that processes text, video, and audio within a unified token sequence via self-attention only. This single-stream design avoids the complexity of multi-stream or cross-attention architectures while remaining easy to optimize with standard training and inference infrastructure. The model is particularly strong in human-centric scenarios, producing expressive facial performance, natural speech-expression coordination, realistic body motion, and precise audio-video synchronization. It supports multilingual spoken generation across Chinese (Mandarin and Cantonese), English, Japanese, Korean, German, and French. For efficient inference, we combine the single-stream backbone with model distillation, latent-space super-resolution, and a Turbo VAE decoder, enabling generation of a 5-second 256p video in 2 seconds on a single H100 GPU. In automatic evaluation, daVinci-MagiHuman achieves the highest visual quality and text alignment among leading open models, along with the lowest word error rate (14.60%) for speech intelligibility. In pairwise human evaluation, it achieves win rates of 80.0% against Ovi 1.1 and 60.9% against LTX 2.3 over 2000 comparisons. We open-source the complete model stack, including the base model, the distilled model, the super-resolution model, and the inference codebase.

cs.CV↗
arXiv2026

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial relationships, often producing images that appear plausible overall yet contain inaccuracies in object positioning. In this work, we present \textbf{SpatialReward}, a verifiable reward model explicitly designed to evaluate spatial layouts in generated images. SpatialReward adopts a multi-stage pipeline: a \emph{Prompt Decomposer} extracts entities, attributes, and spatial metadata from free-form prompts; expert detectors provide accurate visual grounding of object positions and attributes; and a vision-language model applies chain-of-thought reasoning over grounded observations to assess complex spatial relations that are challenging for rule-based methods. To more comprehensively evaluate spatial relationships in generated images, we introduce \textbf{SpatRelBench}, a benchmark covering object attributes, orientation, inter-object relations, and rendered text placement. Experiments on Stable Diffusion and FLUX show that incorporating SpatialReward into RL training consistently improves spatial consistency and overall generation quality, with results aligned more closely to human judgments. These findings indicate that verifiable reward models hold considerable potential for enabling more accurate and controllable optimization in text-to-image generation models.

cs.CV↗
arXiv2026

AVION: Aerial Vision-Language Instruction from Offline Teacher to Prompt-Tuned Network

Adapting vision-language models to remote sensing imagery remains challenging due to two key factors: limited semantic coverage in textual representations and insufficient adaptability of visual features. These issues are particularly significant in aerial scenes, which involve various visual appearances and fine-grained object distinctions. We propose AVION, a knowledge distillation framework tailored for remote sensing adaptation of vision-language models. The teacher module constructs semantically rich textual prototypes by collecting descriptions from a large language model and verifying validity using remote sensing image features. The student module integrates lightweight and learnable prompts into both vision and language encoders, guided by the teacher to align embeddings and their cross-modal relationships. Once trained, the student operates independently during inference. Experiments on six optical remote sensing benchmarks show that AVION improves few-shot classification and base-class accuracy without degrading generalization to novel categories. It also enhances mean recall for cross-modal retrieval, with minimal additional trainable parameters.

cs.CV↗
arXiv2026

Intrinsic Even-Odd Thickness-Driven Anomalous Hall in Epitaxial MnBi2Te4 Thin Films

We demonstrate precise control of magnetism in MnBi2Te4 thin films through careful synthesis by molecular beam epitaxy, achieving minimal defects and accurate layer thickness control. By optimizing Mn-Bi-Te ratios and growth temperatures, we minimize detrimental self-doping effects and accurately target integer-layer films. X-ray diffraction and reflectivity provide quantitative measures of film quality and thickness. When these macroscale probes of structure and thickness are integrated with magnetotransport measurements, a striking even-odd layer dependence of the anomalous Hall effect is revealed. Odd-layer films exhibit a large hysteresis up to the Néel temperature (~25K), consistent with non-compensated antiferromagnetism, while even-layer films show minimal response, as expected for an antiferromagnet. The sign of the anomalous Hall effect exhibits a sign reversal for intrinsic magnetism versus magnetism associated with defects. This work identifies critical factors for inducing pure, non-compensated ferromagnetism and reveals the character of the intrinsic anomalous Hall effect in MnBi2Te4, which together is a step towards realizing the zero-field quantum anomalous Hall effect in topological materials.

cond-mat.mtrl-sci↗
arXiv2026

Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections

U-like networks have become fundamental frameworks in medical image segmentation through skip connections that bridge high-level semantics and low-level spatial details. Despite their success, conventional skip connections exhibit two key limitations: inter-feature constraints and intra-feature constraints. The inter-feature constraint refers to the static nature of feature fusion in traditional skip connections, where information is transmitted along fixed pathways regardless of feature content. The intra-feature constraint arises from the insufficient modeling of multi-scale feature interactions, thereby hindering the effective aggregation of global contextual information. To overcome these limitations, we propose a novel Dynamic Skip Connection (DSC) block that fundamentally enhances cross-layer connectivity through adaptive mechanisms. The DSC block integrates two complementary components. (1) Test-Time Training (TTT) module. This module addresses the inter-feature constraint by enabling dynamic adaptation of hidden representations during inference, facilitating content-aware feature refinement. (2) Dynamic Multi-Scale Kernel (DMSK) module. To mitigate the intra-feature constraint, this module adaptively selects kernel sizes based on global contextual cues, enhancing the network capacity for multi-scale feature integration. The DSC block is architecture-agnostic and can be seamlessly incorporated into existing U-like network structures. Extensive experiments demonstrate the plug-and-play effectiveness of the proposed DSC block across CNN-based, Transformer-based, hybrid CNN-Transformer, and Mamba-based U-like networks.

cs.CV↗
arXiv2026

Nucleation and Antiphase Twin Control in Bi$_2$Se$_3$ via Step-Terminated Al$_2$O$_3$ Substrates

The epitaxial synthesis of high-quality 2D layered materials is an essential driver of both fundamental physics studies and technological applications. Bi$_2$Se$_3$, a prototypical 2D layered topological insulator, is sensitive to defects imparted during the growth, either thermodynamically or due to the film-substrate interaction. In this study, it is shown that step-terminated Al$_2$O$_3$ substrates with a high miscut angle (3°) can effectively suppress a particular hard-to-mitigate defect, the antiphase twin. Systematic investigations across a range of growth temperatures and substrate miscut angles confirm that atomic step edges act as preferential nucleation sites, stabilizing a single twin domain. First-principles calculations suggest that there is a significant energy barrier for twin boundary formation at step edges, supporting the experimental observations. Detailed structural characterization indicates that this twin-selectivity is lost through the mechanism of the 2D layers overgrowing the step edges, leading to higher twin density as the thickness increases. These findings highlight the complex energy landscape unique to 2D materials that is driven by the interplay between substrate properties, nucleation dynamics, and defect formation, and overcoming and controlling these are critical to improve material quality for quantum and electronic applications.

cond-mat.mtrl-sci↗
arXiv2026

HalluRNN: Mitigating Hallucinations via Recurrent Cross-Layer Reasoning in Large Vision-Language Models

Though Large Vision-Language Models (LVLMs) have achieved remarkable performance across various tasks, they are still prone to hallucinations-generating outputs that are textually plausible but visually ungrounded. While prior approaches generally address this issue through data-centric fine-tuning or innovative decoding strategies, these methods often require substantial resources or task-specific configurations. In this work, we introduce an architecture-level solution, HalluRNN, which enhances model stability through recurrent cross-layer reasoning. Specifically, we propose a novel Dual-Gated Depth Propagation Unit (DG-DPU) module, which is shared across layers and recurrently refines hidden states. This allows for the adaptive propagation of information throughout the model, enforces consistency across layers, and mitigates hallucinations caused by representational drift. By fine-tuning only the DG-DPU module, HalluRNN achieves strong and robust performance across multiple benchmarks.

cs.CV↗
arXiv2026

Model-free Analysis of Scattering and Imaging Data with Escort-Weighted Shannon Entropy and Divergence Matrices

We demonstrate a model-free data analysis framework that leverages escort-weighted Shannon Entropy and several divergence matrices to detect phase transitions in scattering and imaging datasets. By establishing a connection between physical entropy and informational entropy, this approach provides a sensitive method for identifying phase transitions without an explicit physical model or order parameter. We further show that pairwise divergence matrices, including Kullback-Leibler divergence, Jeffrey Divergence, Jensen-Shannon Divergence and antisymmetric Kullback-Leibler divergence, provide more comprehensive measures of statistical changes than scalar entropy alone. Our approach successfully detects the onset of both long- and short-range order in neutron and X-ray scattering data, as well as a non-trivial phase transition in magnetic skyrmion lattices observed through Lorentz-transition electron microscopy. These results establish a framework for automated, model-free analysis of experimental data with broad applications in materials science and condensed matter physics.

cond-mat.mtrl-sci↗
arXiv2025

AndroidLens: Long-latency Evaluation with Nested Sub-targets for Android GUI Agents

Graphical user interface (GUI) agents can substantially improve productivity by automating frequently executed long-latency tasks on mobile devices. However, existing evaluation benchmarks are still constrained to limited applications, simple tasks, and coarse-grained metrics. To address this, we introduce AndroidLens, a challenging evaluation framework for mobile GUI agents, comprising 571 long-latency tasks in both Chinese and English environments, each requiring an average of more than 26 steps to complete. The framework features: (1) tasks derived from real-world user scenarios across 38 domains, covering complex types such as multi-constraint, multi-goal, and domain-specific tasks; (2) static evaluation that preserves real-world anomalies and allows multiple valid paths to reduce bias; and (3) dynamic evaluation that employs a milestone-based scheme for fine-grained progress measurement via Average Task Progress (ATP). Our evaluation indicates that even the best models reach only a 12.7% task success rate and 50.47% ATP. We also underscore key challenges in real-world environments, including environmental anomalies, adaptive exploration, and long-term memory retention.

cs.CV↗
arXiv2025

Generation of Polarization-Tunable Hybrid Cylindrical Vector gamma Rays

Cylindrical vector (CV) gamma rays can introduce spatially structured polarization as a new degree of freedom for fundamental research and practical applications. However, their generation and control remain largely unexplored. Here, we put forward a novel method to generate CV gamma rays with tunable hybrid polarization via a rotating electron beam interacting with a solid foil. In this process, the beam generates a coherent transition radiation field and subsequently emits gamma rays through nonlinear Compton scattering. By manipulating the initial azimuthal momentum of the beam, the polarization angle of gamma rays relative to the transverse momentum can be controlled, yielding tunable hybrid CV polarization states. Three-dimensional spin-resolved particle-in-cell simulations demonstrate continuous tuning of the polarization angle across (-90°, 90°) with a high polarization degree exceeding 60%. Our work contributes to the development of structured gamma rays, potentially opening new avenues in high-energy physics, nuclear science, and laboratory astrophysics.

physics.plasm-ph↗
arXiv2025

Equilibrium Portfolio Selection under Utility-Variance Analysis of Log Returns in Incomplete Markets

This paper investigates a time-inconsistent portfolio selection problem in the incomplete mar ket model, integrating expected utility maximization with risk control. The objective functional balances the expected utility and variance on log returns, giving rise to time inconsistency and motivating the search of a time-consistent equilibrium strategy. We characterize the equilibrium via a coupled quadratic backward stochastic differential equation (BSDE) system and establish the existence theory in two special cases: (i)the two Brownian motions driven the price dynamics and the factor process are independent with $ρ= 0$; (ii) the trading strategy is constrained to be bounded. For the general case with correlation coefficient $ρ\neq 0$, we introduce the notion of an approximate time-consistent equilibrium. Employing the solution structure from the equilibrium in the case $ρ= 0$, we can construct an approximate time-consistent equilibrium in the general case with an error of order $O(ρ^2)$. Numerical examples and financial insights are also presented based on deep learning algorithms.

q-fin.PM↗
arXiv2025

Beyond Pixels: Semantic-aware Typographic Attack for Geo-Privacy Protection

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image perturbations provide a potential direction for geo-privacy protection, they require relatively strong distortions to be effective against LVLMs, which noticeably degrade visual quality and diminish an image's value for sharing. To overcome this limitation, we identify typographical attacks as a promising direction for protecting geo-privacy by adding text extension outside the visual content. We further investigate which textual semantics are effective in disrupting geolocation inference and design a two-stage, semantics-aware typographical attack that generates deceptive text to protect user privacy. Extensive experiments across three datasets demonstrate that our approach significantly reduces geolocation prediction accuracy of five state-of-the-art commercial LVLMs, establishing a practical and visually-preserving protection strategy against emerging geo-privacy threats.

cs.CV↗
arXiv2025

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help reveal vulnerabilities before deployment. Previous works have shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated textures perform poorly in physical implementations, i.e., when deployed as patches, limiting their practical utility for stress-testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals among the repeated textures, creating a grid structure, significantly enhances the patch's attack performance. Through extensive experimentation, we analyze how variations of this novel structure influence the adversarial effectiveness. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the interval structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack advanced stereo depth estimation methods of different paradigms, i.e., RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems. The code is officially released at: https://github.com/WiWiN42/DepthVanish

cs.CV↗