arXiv subjects

Yu Zhong

Publications and source records attributed to Yu Zhong.

At least 19 recordsLinked to original sources

arXiv2026

TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation

Vision-language-action (VLA) models leverage pretrained vision-language representations for robot control, yet simply adding historical frames does not reliably capture recent physical change. This is especially problematic in multi-stage manipulation, where visually similar states may require different actions depending on prior execution. To address this challenge, we present TemporalFlow-VLA, which learns compact execution history through physically grounded temporal supervision. Using recorded robot states, robot geometry, and calibrated cameras, we construct robot-surface temporal flow as a training-only target and supervise two execution-aligned temporal queries that provide structured history to the action expert. The geometric supervision path is not evaluated at deployment. TemporalFlow-VLA achieves 97.63 +/- 0.26% average success on LIBERO, including 96.60 +/- 0.87% on LIBERO Long, and 85.5%/84.2% Clean/Randomized success across 12 RoboTwin tasks. It shows its clearest advantage over prior methods on longer-horizon, multi-stage manipulation. Controlled history interventions show that action prediction depends on both historical content and temporal order. With asynchronous feature caching, temporal conditioning maintains single-frame-level server-side sampling latency without additional historical-encoding overhead. Overall, TemporalFlow-VLA provides a compact, physically grounded interface for exploiting ordered execution history without explicit motion estimation or geometric processing at deployment.

cs.RO↗

arXiv2026

V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action Models

Vision-language-action (VLA) models provide a scalable path toward generalist robotic manipulation by integrating visual perception, language understanding, and continuous action control. However, we reveal a critical limitation of VLA architectures: the action expert has limited access to the 3D geometric and 2D semantic information available in VLM features. This accessibility gap weakens perceptual grounding and limits performance on fine-grained robotic manipulation. To address this issue, we propose V-Link, which explicitly recovers visual representations during the vision-language (VL) to action (A) feature transfer. Specifically, V-Link learns complementary Spatial and Semantic Query representations within the VLM and injects them into Action DiT through asymmetric pathways. Semantic Queries complement the original VLM image tokens, whereas Spatial Queries provide dedicated geometric conditioning for spatially grounded action generation. Across LIBERO, LIBERO-Plus, and RoboTwin 2.0, our V-Link improves the average success rate over base model GR00T N1.6 by +1.9%, +31.2%, and +18.8%, respectively. On the AGIBOT A3 Ultra, V-Link further achieves gains of +20% and +24% on two real-world humanoid tasks.

cs.CV↗

arXiv2026

Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies

Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation, yet complex contact-rich tasks often benefit from multi-camera observations that jointly capture the end effector, objects, and targets under occlusion. Existing multi-camera VLAs usually concatenate view tokens, leaving action representations weak in metric depth and inconsistent across cameras. We introduce Multi-View Unified Camera Fields (MVUCF), a training-only framework that forms a shared action-facing latent field across views. A coordinate-query depth objective makes metric depth recoverable, while a preprocessing-aware correspondence objective aligns tokens observing the same physical point from different cameras. Both directly shape the hidden states consumed by the action module. After geometry injection, depth, camera calibration, and auxiliary heads are removed, so deployment uses the original RGB-only graph with no extra inference FLOPs. Held-out probes confirm stronger depth recovery and cross-view matching. Under matched GR00T-N1.6 settings, MVUCF reaches 98.9% on LIBERO, improves LIBERO-Plus by 22.4 points, and raises success by 23.3 points across six RoboTwin tasks spanning three action families: touch, move-and-place, and contact interaction. Real-world humanoid experiments further provide evidence of its practical effectiveness under RGB-only deployment.

cs.RO↗

arXiv2026

A Hybrid Framework for Blood Vessel Morphology Classification: Discrete Geometry-based Tortuosity Feature Measurement, Information Gain-based Feature Selection, and Random Forest Classification

Subjective visual grading of blood vessel tortuosity relies heavily on clinical experience, while traditional distance-based indices often fail to adequately characterize three-dimensional spatial deformation. Because abnormal internal carotid artery morphology may be clinically relevant to cerebrovascular assessment and stroke-risk evaluation, objective and reproducible quantification of vascular tortuosity is of considerable importance. To address this limitation, we propose a mathematical framework for the morphological classification of the internal carotid artery (ICA-C1) segment. The framework integrates discrete geometric feature measurement, Information Gain-based feature selection, and Random Forest classification. An initial set of 13 tortuosity features is extracted from the corresponding 379 clinical vascular centerlines using discrete geometric methods and subsequently reduced to a six-feature subset consisting of $\mathcal{TI}$, $\mathcal{AC}$, $\mathcal{TC}$, $\mathcal{AC}/\mathcal{AT}$, $\mathcal{AT}$, and $\mathcal{TT}$. The framework is evaluated in two classification tasks. For binary classification of non-severe and severe tortuosity, the RF model achieves a Macro-F1 score of 0.9206. For ternary morphological grading into straight, low-tortuosity, and high-tortuosity groups, it achieves a Macro-F1 score of 0.8626. The results indicate that elongation- and curvature-related features provide strong discriminatory information for basic screening, whereas torsion-related features contribute additional information for more detailed morphological classification. Based on the RF feature-importance values, we further define a Morphological Risk Index (MRI), which provides a direct numerical reference for vascular morphology and may facilitate more objective and consistent clinical assessment.

eess.IV↗

arXiv2026

Application of Fractional Polynomial Model Based on Bayesian Criterion in Cerebrovascular Diseases: A Robust Framework for Occlusion Simulation and Topology Reconstruction

The internal carotid artery (ICA), especially its cervical segment (ICA-C1), holds significant importance in the diagnosis of cerebrovascular diseases. Traditional polynomial fitting methods often encounter problems such as order selection, overfitting, and oscillation. To address these issues, this paper proposes a fractional polynomial fitting model based on the effective order and Bayesian Information Criterion (BIC). Through statistical analysis, the high-frequency effective orders $\{1.1, 1.5, 2.0, 2.7, 3.4\}$ are determined to improve computational efficiency. The experimental results of 379 clinical cases show that the proposed method outperforms the traditional methods in terms of fitting accuracy, noise resistance and computational efficiency. It can achieve low-error fitting and accurately depict the complex spatial morphology of the ICA-C1 segment. Moreover, by optimizing the solution strategy and sequence selection mechanism, the running time of the algorithm has been reduced from 153.145 seconds to 23.054 seconds. Furthermore, the proposed model shows good application potential in predicting missing vascular segments in imaging tasks. The prediction results are overall stable, and in most cases, the error is small. The normalized mean square error (NMSE) is below 1.68\% in 90\% of the cases. This study presents a stable, efficient and clinically interpretable model approach for analyzing the morphology of cerebral vessels, opening up a new technological frontier for intelligent diagnosis of cerebral vascular diseases.

physics.med-ph↗

arXiv2026

Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis

Medical vision-language models (VLMs) have rapidly advanced as general-purpose multimodal assistants, yet their deployment in 3D Computed Tomography (CT) analysis remains constrained by a persistent mismatch between optimization objectives and clinical rigor. Current Reinforcement Learning (RL) paradigms still rely on lexical proxy signals that induce ``\textit{Evaluation Hallucinations}'', where models optimize linguistic fluency rather than factual clinical correctness, leading to diagnostically critical errors. To bridge this gap, we introduce the \textbf{Clinical Abnormality Benchmarking Substrate (CABS)}, a structured system that decomposes radiology reports into verifiable clinical semantic units. Using CABS, we identify a ``\textit{Mechanistic Divergence}'' in standard RL, where surface-similarity rewards drive policy gradients to bypass medical facts. We therefore propose \textbf{Trajectory-Integral Feedback GRPO (TIF-GRPO)}, a novel framework integrating control-theoretic principles into policy optimization. By formulating clinical reasoning as a pseudo-temporal trajectory for anomaly discovery, TIF-GRPO regulates anatomy-aware rewards via an integral feedback loop that penalizes persistent omissions as cumulative state errors and suppresses hallucinations as excessive control effort. Experiments on 3D CT benchmarks demonstrate that our approach significantly enhances abnormality detection and clinical faithfulness, establishing a new paradigm for fine-grained regulation in medical VLMs. Our project is available at \href{https://github.com/ZJU4HealthCare/TIF-GRPO}{GitHub}.

cs.CV↗

arXiv2026

Nonlinear steepening of a fast magnetoacoustic wave in the vicinity of a coronal magnetic null point

The interaction of a fast magnetoacoustic wave with a magnetic null point is studied in the context of the sympathetic flare phenomenon. Attention is paid to steepening the wave caused by the finite-amplitude effects in a non-uniform plasma environment. The null point is modelled by a potential magnetic configuration without a guiding field. The equilibrium plasma density and temperature are taken to be constant. The fast wave is excited by an impulsive point source outside the distance at which the local Alfv\'en and sound speeds are equal to each other. The incoming fast wave approaches the null point along the bisector of the magnetic configuration, i.e., across the local field. The fast-speed non-uniformity around the null point causes the refraction of the incident fast wave. However, the segment of the incoming wave, which approaches the null point is locally plane. The decrease in the fast speed towards the null point amplifies the nonlinear deformation of the incoming wave. Hence, the fast wave can become subject to nonlinear dissipation at a distance from the null point and not reach it.

astro-ph.SR↗

arXiv2026

LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation

Large Multimodal Models (LMMs) have achieved remarkable progress in general-purpose vision--language understanding, yet they remain limited in tasks requiring precise object-level grounding, fine-grained spatial reasoning, and controllable visual manipulation. In particular, existing systems often struggle to identify the correct instance, preserve object identity across interactions, and localize or modify designated regions with high precision. Object-centric vision provides a principled framework for addressing these challenges by promoting explicit representations and operations over visual entities, thereby extending multimodal systems from global scene understanding to object-level understanding, segmentation, editing, and generation. This paper presents a comprehensive review of recent advances at the convergence of LMMs and object-centric vision. We organize the literature into four major themes: object-centric visual understanding, object-centric referring segmentation, object-centric visual editing, and object-centric visual generation. We further summarize the key modeling paradigms, learning strategies, and evaluation protocols that support these capabilities. Finally, we discuss open challenges and future directions, including robust instance permanence, fine-grained spatial control, consistent multi-step interaction, unified cross-task modeling, and reliable benchmarking under distribution shift. We hope this paper provides a structured perspective on the development of scalable, precise, and trustworthy object-centric multimodal systems.

cs.CV↗

arXiv2026

Betweenness relations and Fuzzy betweenness relations in fuzzy metric spaces

In this paper, we mainly discuss the constructions and the characteristics of betweenness relations and fuzzy betweenness relations in KM-fuzzy metric spaces. And the family of betweenness relations induced by a KM-fuzzy metric form a nest of betweenness relations.The main focus of this paper is to introduce two different construction methods for fuzzy betweenness relations induced by a KM-fuzzy metric.One of them is directly obtained by using the implication operator. The other is through the corresponding nest of metrics of KM-fuzzy metrics. Furthermore, we also show that the two types of fuzzy betweenness relations are the same, and they also satisfy the eight kinds of four-point transitivity properties and the six kinds of five-point transitivity properties.

math.GM↗

arXiv2026

MAU-GPT: Enhancing Multi-type Industrial Anomaly Understanding via Anomaly-aware and Generalist Experts Adaptation

As industrial manufacturing scales, automating fine-grained product image analysis has become critical for quality control. However, existing approaches are hindered by limited dataset coverage and poor model generalization across diverse and complex anomaly patterns. To address these challenges, we introduce MAU-Set, a comprehensive dataset for Multi-type industrial Anomaly Understanding. It spans multiple industrial domains and features a hierarchical task structure, ranging from binary classification to complex reasoning. Alongside this dataset, we establish a rigorous evaluation protocol to facilitate fair and comprehensive model assessment. Building upon this foundation, we further present MAU-GPT, a domain-adapted multimodal large model specifically designed for industrial anomaly understanding. It incorporates a novel AMoE-LoRA mechanism that unifies anomaly-aware and generalist experts adaptation, enhancing both understanding and reasoning across diverse defect classes. Extensive experiments show that MAU-GPT consistently outperforms prior state-of-the-art methods across all domains, demonstrating strong potential for scalable and automated industrial inspection.

cs.CV↗

arXiv2026

Unified Personalized Understanding, Generating and Editing

Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-fits-all'' paradigm and struggle to model user-specific concepts (e.g., generate a photo of \texttt{ }) in a consistent and controllable manner. Existing personalization methods typically rely on external retrieval, which is inefficient and poorly integrated into unified multimodal pipelines. Recent personalized unified models introduce learnable soft prompts to encode concept information, yet they either couple understanding and generation or depend on complex multi-stage training, leading to cross-task interference and ultimately to fuzzy or misaligned personalized knowledge. We present \textbf{OmniPersona}, an end-to-end personalization framework for unified LMMs that, for the first time, integrates personalized understanding, generation, and image editing within a single architecture. OmniPersona introduces structurally decoupled concept tokens, allocating dedicated subspaces for different tasks to minimize interference, and incorporates an explicit knowledge replay mechanism that propagates personalized attribute knowledge across tasks, enabling consistent personalized behavior. To systematically evaluate unified personalization, we propose \textbf{\texttt{OmniPBench}}, extending the public UnifyBench concept set with personalized editing tasks and cross-task evaluation protocols integrating understanding, generation, and editing. Experimental results demonstrate that OmniPersona delivers competitive and robust performance across diverse personalization tasks. We hope OmniPersona will serve as a strong baseline and spur further research on controllable, unified personalization.

cs.CV↗

arXiv2026

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.

cs.RO↗

arXiv2025

Masgent: An AI-assisted Materials Simulation Agent

Density functional theory (DFT) and machine learning potentials (MLPs) are essential for predicting and understanding materials properties, yet preparing, executing, and analyzing these simulations typically requires extensive scripting, multi-step procedures, and significant high-performance computing (HPC) expertise. These challenges hinder reproducibility and slow down discovery. Here, we introduce Masgent, an AI-assisted materials simulation agent that unifies structure manipulation, automated VASP input generation, DFT workflow construction and analysis, fast MLP-based simulations, and lightweight machine learning (ML) utilities within a single platform. Powered by large language models (LLMs), Masgent enables researchers to perform complex simulation tasks through natural-language interaction, eliminating most manual scripting and reducing setup time from hours to seconds. By standardizing protocols and integrating advanced simulation and data-driven tools, Masgent lowers the barrier to performing state-of-the-art computational methodologies, enabling faster hypothesis testing, pre-screening, and exploratory research for both new and experienced practitioners.

physics.comp-ph↗

arXiv2025

SelfAI: A self-directed framework for long-horizon scientific discovery

Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time, particularly balancing efficiency-diversity trade-offs and supporting reproducible, human-in-the-loop discovery workflows. We introduce SelfAI, a self-directed, multi-agent-enabled discovery system that automates scientific exploration as a strategic, trajectory-driven decision-making process. SelfAI translates high-level research intent into executable experiments, reasons over accumulated experimental trajectories to guide subsequent exploration, and applies adaptive stopping decisions to terminate unproductive search paths within a closed-loop workflow governed by explicit efficiency-diversity trade-offs. Evaluated using real-world experiments spanning domains from machine learning to drug discovery, SelfAI consistently discovers high-quality solutions with substantially fewer redundant trials than classical optimization and recent LLM-based baselines. The proposed methods establish a general framework for organizing long-horizon scientific discovery and adaptive decision-making in complex scientific and engineering systems.

cs.LG↗

arXiv2025

Run, Ruminate, and Regulate: A Dual-process Thinking System for Vision-and-Language Navigation

Vision-and-Language Navigation (VLN) requires an agent to dynamically explore complex 3D environments following human instructions. Recent research underscores the potential of harnessing large language models (LLMs) for VLN, given their commonsense knowledge and general reasoning capabilities. Despite their strengths, a substantial gap in task completion performance persists between LLM-based approaches and domain experts, as LLMs inherently struggle to comprehend real-world spatial correlations precisely. Additionally, introducing LLMs is accompanied with substantial computational cost and inference latency. To address these issues, we propose a novel dual-process thinking framework dubbed R3, integrating LLMs' generalization capabilities with VLN-specific expertise in a zero-shot manner. The framework comprises three core modules: Runner, Ruminator, and Regulator. The Runner is a lightweight transformer-based expert model that ensures efficient and accurate navigation under regular circumstances. The Ruminator employs a powerful multimodal LLM as the backbone and adopts chain-of-thought (CoT) prompting to elicit structured reasoning. The Regulator monitors the navigation progress and controls the appropriate thinking mode according to three criteria, integrating Runner and Ruminator harmoniously. Experimental results illustrate that R3 significantly outperforms other state-of-the-art methods, exceeding 3.28% and 3.30% in SPL and RGSPL respectively on the REVERIE benchmark. This pronounced enhancement highlights the effectiveness of our method in handling challenging VLN tasks.

cs.AI↗

arXiv2025

Detection of kink oscillations in solar coronal loops by a CNN-LSTM neural network

A hybrid machine learning model which combines a shallow convolutional neural network and a long short-term memory network (CNN--LSTM), has been developed to automate the detection of kink oscillations in coronal plasma loops within large volumes of high-cadence sequences of imaging data. The network was trained on a set of 10,000 synthetic data cubes designed to mimic sequences of coronal images, achieving an accuracy greater than 98\% on this synthetic dataset. The model was then applied to detect kink oscillations in real data cubes of coronal active regions observed with SDO/AIA in the 171~\AA\ channel. This dataset consisted of 50 samples with visually detected kink oscillations and 128 samples without. Each sample covered an area of 260$\times$260~pixels in the spatial domain and a duration of 30~min with a 12~s cadence in the time domain. Both off-limb and on-disk regions of interest were used. The data were pre-processed by median filtering in the time domain, and Gaussian smoothing and Contrast Limited Adaptive Histogram Equalization in the spatial domain. In the real dataset, the performance of the model was 83.7\%.The model is fully available in open access. We regard the CNN--LSTM model developed as a first step toward creating robust tools for routine solar coronal data mining in the context of coronal oscillation study.

astro-ph.SR↗

arXiv2025

HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding

Although electrocardiograms (ECG) play a dominant role in cardiovascular diagnosis and treatment, their intrinsic data forms and representational patterns pose significant challenges for medical multimodal large language models (Med-MLLMs) in achieving cross-modal semantic alignment. To address this gap, we propose Heartcare Suite, a unified ECG suite designed for dual signal-image modeling and understanding: (i) Heartcare-400K. A fine-grained ECG instruction dataset on top of our data pipeline engine--HeartAgent--by integrating high quality clinical ECG reports from top hospitals with open-source data. (ii) Heartcare-Bench. A systematic benchmark assessing performance of models in multi-perspective ECG understanding and cross-modal generalization, providing guidance for optimizing ECG comprehension models. (iii) HeartcareGPT. Built upon a structure-aware discrete tokenizer Beat, we propose Dual Stream Projection Alignment (DSPA) paradigm--a dual encoder projection alignment mechanism enabling joint optimizing and modeling native ECG signal-image within a shared feature space. HeartcareGPT achieves consistent improvements across diverse ECG understanding tasks, validating both the effectiveness of the unified modeling paradigm and the necessity of a high-quality data pipeline, and establishing a methodological foundation for extending Med-MLLMs towards physiological signal domains. Our project is available at https://github.com/ZJU4HealthCare/HeartcareGPT .

cs.LG↗

arXiv2025

MMAIF: Multi-task and Multi-degradation All-in-One for Image Fusion with Language Guidance

Image fusion, a fundamental low-level vision task, aims to integrate multiple image sequences into a single output while preserving as much information as possible from the input. However, existing methods face several significant limitations: 1) requiring task- or dataset-specific models; 2) neglecting real-world image degradations (\textit{e.g.}, noise), which causes failure when processing degraded inputs; 3) operating in pixel space, where attention mechanisms are computationally expensive; and 4) lacking user interaction capabilities. To address these challenges, we propose a unified framework for multi-task, multi-degradation, and language-guided image fusion. Our framework includes two key components: 1) a practical degradation pipeline that simulates real-world image degradations and generates interactive prompts to guide the model; 2) an all-in-one Diffusion Transformer (DiT) operating in latent space, which fuses a clean image conditioned on both the degraded inputs and the generated prompts. Furthermore, we introduce principled modifications to the original DiT architecture to better suit the fusion task. Based on this framework, we develop two versions of the model: Regression-based and Flow Matching-based variants. Extensive qualitative and quantitative experiments demonstrate that our approach effectively addresses the aforementioned limitations and outperforms previous restoration+fusion and all-in-one pipelines. Codes are available at https://github.com/294coder/MMAIF.

cs.CV↗