arXiv subjects

Yutong Li

Publications and source records attributed to Yutong Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

Rethinking Conditional Generation for Underwater Salient Object Detection

Salient Object Detection in underwater images remains challenging due to low contrast, uneven illumination, and color distortion caused by scattering and absorption effects, which limit the effectiveness of conventional SOD methods in underwater environments. To address these challenges, we propose a Degradation-aware Conditional Generation Network (DCGNet), specifically designed to construct reliable conditional features for underwater saliency generation. First, we design a Dynamic Multi-Granularity module (DMG) grounded in the human visual system to robustly detect salient objects of varying scales with blurred boundaries. Then, we develop an Underwater Physics-Prior module (UPP), which utilizes pseudo-depth guidance to estimate underwater light attenuation and backscatter, thereby restoring degradation-aware RGB features and mitigating color distortion and boundary ambiguity. Based on the physics-guided representation, we introduce an Underwater Spatial Gaussian module (USG), which constructs a spatial Gaussian saliency prior from the strongest guided response to enhance object-centered salient regions and suppress cluttered underwater backgrounds. In addition, a lightweight timestep-adaptive Diffusion Transformer (DiT) bottleneck is inserted into the denoising decoder to refine fused features at different diffusion timesteps. Comprehensive experiments on USOD10K, USOD, CSOD10K, MAS3K, and RMAS demonstrate that DCGNet significantly outperforms existing state-of-the-art methods, verifying its potential for complex underwater visual applications.

cs.CV↗

arXiv2026

Teach Multimodal Recommendation Model to See via Personalized Visual Extraction and Adaptive Learning

Multimodal sequential recommendation (MSR) incorporates textual and visual information to improve recommendation quality. However, recent studies and our empirical analysis show that visual features are often underutilized, thereby contributing far less than textual signals. We attribute this issue to two factors: insufficient visual representation learning (pretrained encoders fail to capture preference-relevant cues) and unbalanced visual-text optimization (textual features dominate the learning process). To address these issues, we propose Teach Multimodal Recommendation Model to See via Personalized Visual Extraction and Adaptive Learning (REVEAL), a plug-and-play framework that enhances visual representation learning and cross-modal optimization without modifying the original recommendation backbone. REVEAL consists of Feedback-Guided Visual Extraction (FVE), which refines prompt-guided visual extraction through task-level feedback, and Adaptive Visual Learning (AVL), which dynamically reweights visual learning to alleviate modality imbalance. Experiments on multiple real-world datasets and MSR backbones demonstrate that REVEAL consistently improves recommendation performance. Further analysis shows that these gains arise from more effective attention to preference-relevant visual regions and better visual utilization during training. The code is available at https://github.com/YutongLi2024/REVEAL.

cs.IR↗

arXiv2026

TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos

Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories. These limitations motivate us to introduce a new task: unified human-scene-camera reconstruction from multi-view videos, which aims to jointly estimate dynamic humans, static scenes, and camera poses in one global coordinate frame. We propose TROPHIES--Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos-a unified framework tailored for this task. TROPHIES features a Human Branch that models humans through temporal and spatial reasoning, and a Scene Branch that reconstructs static geometry with human-aware attention. A global alignment and optimization module couples both branches by enforcing scale consistency, contact priors, and cross-view temporal coherence. Experiments on EgoHuman and EgoExo4D demonstrate that TROPHIES achieves globally aligned, physically plausible 4D reconstructions and consistently outperforms existing paradigms in both global fidelity and human-scene consistency.

cs.CV↗

arXiv2026

Equip Pre-ranking with Target Attention by Residual Quantization

The pre-ranking stage in industrial recommendation systems faces a fundamental conflict between efficiency and effectiveness. While powerful models like Target Attention (TA) excel at capturing complex feature interactions in the ranking stage, their high computational cost makes them infeasible for pre-ranking, which often relies on simplistic vector-product models. This disparity creates a significant performance bottleneck for the entire system. To bridge this gap, we propose TARQ, a novel pre-ranking framework. Inspired by generative models, TARQ's key innovation is to equip pre-ranking with an architecture approximate to TA by Residual Quantization. This allows us to bring the modeling power of TA into the latency-critical pre-ranking stage for the first time, establishing a new state-of-the-art trade-off between accuracy and efficiency. Extensive offline experiments and large-scale online A/B tests at Taobao demonstrate TARQ's significant improvements in ranking performance. Consequently, our model has been fully deployed in production, serving tens of millions of daily active users and yielding substantial business improvements. The code and data are available at https://github.com/zyody/tarq_sigir2026.

cs.IR↗

arXiv2026

EchoVQA: Enabling Conversational Assistance for Point-of-Care Cardiac Ultrasound

Point-of-care transthoracic echocardiography (TTE) enables cardiac assessment in virtually any clinical setting, yet its diagnostic utility remains constrained by the expertise required for image acquisition and interpretation. Visual question answering (VQA) offers a promising paradigm for bridging this expertise gap through interactive clinical assistance, but existing echocardiography VQA datasets are limited in scale, restricted to high-quality images, and only cover a few views. We introduce EchoVQA, the first large-scale VQA dataset for echocardiography, comprising 14,299 images and 74,819 question-answer pairs. The dataset integrates public sources (EchoNet-Dynamic, CAMUS) with our own point-of-care acquisitions from two handheld probes (Lumify, Clarius), spanning diverse views and including both high-quality and suboptimal images. Uniquely, EchoVQA includes acquisition guidance questions to help users optimize transducer positioning toward a diagnostic apical 4-chamber view for left ventricular ejection fraction estimation -- a challenging task for novice operators in point-of-care settings. We further develop a parameter-efficient method based on multimodal learnable prompts achieving state-of-the-art performance on most benchmarks, including EchoVQA, with significantly less trainable parameters than existing state-of-the-art approaches.

cs.CV↗

arXiv2026

GraphMind: Theorem Selection and Conclusion Generation Framework with Dynamic GNN for LLM Reasoning

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, including multi-step reasoning such as mathematical proving. However, existing approaches often lack an explicit and dynamic mechanism to structurally represent and evolve intermediate reasoning states, which limits their ability to perform context-aware theorem selection and iterative conclusion generation. To address these challenges, we propose GraphMind, a novel dynamic graph-based framework that integrates the graph neural network (GNN) with LLMs to iteratively select theorems and generate intermediate conclusions for multi-step reasoning. Our method models the reasoning process as a heterogeneous evolving graph, where nodes represent conditions, theorems, and conclusions, while edges capture logical dependencies between nodes. By encoding the current reasoning state with GNN and leveraging semantic matching for theorem selection, our framework enables context-aware, interpretable, and structured reasoning in a closed-loop manner. Experiments on various question-answering (QA) datasets demonstrate that our proposed GraphMind method achieves consistent performance improvements and significantly outperforms existing baselines in multi-step reasoning, validating the effectiveness and generalizability of our approach.

cs.CL↗

arXiv2026

Coronal Diagnostics Via Modelling Periodic-Beaded Stripes of Solar Radio Bursts

Using high-resolution data from the Chashan Broadband Solar radio spectrometer at meter wavelengths (CBSm) of the Chinese Meridian Project-Phase II (CMP-II), Li et al. (2025) identified a novel fine spectral structure of solar radio bursts, termed periodic beaded stripes, and proposed a generation mechanism. Here we report additional events and develop a quantitative method to determine the physical conditions in the emission region. Periodic stripes tend to occur in the post-phase of flares and are associated with complex magnetic configurations. They repeat on sub-second timescales and show $\sim$0.1 s bead-like modulations, often accompanied by low-frequency absorptions. Modeling the chained stripes with linear kinetic theory of the double plasma resonance (DPR) instability constrains the source-region magnetic field to 0.2-1.7 G and the plasma density to (1-7) $\times 10^8$ cm $^{-3}$. The former follows the drift of individual stripes, and the latter tracks the overall trend. This study summarizes the key properties of periodic beaded stripes and establishes a quantitative DPR-based framework for coronal diagnostics.

astro-ph.SR↗

arXiv2026

ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection

Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shapes, and large variations in object scale. Existing discriminative methods directly regress saliency maps, while recent diffusion-based generative approaches suffer from stochastic sampling and high computational cost. In this paper, we propose ORSIFlow, a saliency-guided rectified flow framework that reformulates ORSI-SOD as a deterministic latent flow generation problem. ORSIFlow performs saliency mask generation in a compact latent space constructed by a frozen variational autoencoder, enabling efficient inference with only a few steps. To enhance saliency awareness, we design a Salient Feature Discriminator for global semantic discrimination and a Salient Feature Calibrator for precise boundary refinement. Extensive experiments on multiple public benchmarks show that ORSIFlow achieves state-of-the-art performance with significantly improved efficiency.

cs.CV↗

arXiv2026

Scientific tools and Innovation: Big Science Facilities Yield More Novel and Interdisciplinary Knowledge

Scientific tools dictate the boundaries of human knowledge, serving as the foundation for perceptions and explorations. In the era of Big Science, science are increasingly dependent on advanced analytical technologies and experimental platforms. Over the past decades, national and supranational entities have invested massive financial resources, collaborative networks, and collective intelligence to construct Big Science Facilities (BSFs) aimed at generating cutting edge knowledge. However, empirical evaluations of these machines actual performance in driving scientific innovation remain scarce. To address this gap, we collected 310,086 publications from 88 global BSFs and constructed a matched control dataset of approximately 3 million publications sharing the same last authors. Our analysis reveals that the utilization of BSFs has expanded significantly since 1950s. Crucially, publications supported by these facilities exhibit higher recombinant novelty and interdisciplinary integration. Furthermore, this improvement is most pronounced in non physical sciences domains traditionally peripheral to BSFs core focus indicating the emergence of a powerful intra facility knowledge spillover effect. By enriching the Facilitymetrics framework, our findings provide empirical evidence that BSFs act as vital engines for scientific discovery, offering policymakers essential metrics to justify infrastructural investments, while prompting the science of science community to reassess the profound impact of scientific tools on knowledge production

cs.DL↗

arXiv2026

Experimental Determination of Gamma-Ray Polarization in Strong-Field Nonlinear Compton Scattering

The polarization of gamma rays produced in strong-field quantum electrodynamics (SFQED) is a fundamental and long-standing prediction, the verification of which has remained elusive, limiting both foundational tests and applications. Here, we report the first experimental measurement of gamma-ray polarization generated via all-optical nonlinear Compton scattering. Colliding a laser-wakefield-accelerated electron beam with an intense counter-propagating laser pulse reflected from a plasma mirror, we produce bright gamma rays in the strong-field regime ($a_0 > 1$). For gamma rays with $a_0 \approx 3$, a linear polarization degree of $\sim 50\%$ is measured via the azimuthal asymmetry of photoneutrons from a deuterium target, and independently verified by a Compton polarimeter.The results show excellent agreement with SFQED calculations employing the locally monochromatic approximation, while diverging from predictions based on the locally constant field approximation, highlighting the importance of quantum interference effects in this regime. Our work provides experimental evidence for polarization dynamics in SFQED, supports a key prediction of nonperturbative QED, and paves the way for compact, laser-driven sources of polarized gamma rays.}

physics.plasm-ph↗

arXiv2026

Stereo-Inertial Poser: Towards Metric-Accurate Shape-Aware Motion Capture Using Sparse IMUs and a Single Stereo Camera

Recent advancements in visual-inertial motion capture systems have demonstrated the potential of combining monocular cameras with sparse inertial measurement units (IMUs) as cost-effective solutions, which effectively mitigate occlusion and drift issues inherent in single-modality systems. However, they are still limited by metric inaccuracies in global translations stemming from monocular depth ambiguity, and shape-agnostic local motion estimations that ignore anthropometric variations. We present Stereo-Inertial Poser, a real-time motion capture system that leverages a single stereo camera and six IMUs to estimate metric-accurate and shape-aware 3D human motion. By replacing the monocular RGB with stereo vision, our system resolves depth ambiguity through calibrated baseline geometry, enabling direct 3D keypoint extraction and body shape parameter estimation. IMU data and visual cues are fused for predicting drift-compensated joint positions and root movements, while a novel shape-aware fusion module dynamically harmonizes anthropometry variations with global translations. Our end-to-end pipeline achieves over 200 FPS without optimization-based post-processing, enabling real-time deployment. Quantitative evaluations across various datasets demonstrate state-of-the-art performance. Qualitative results show our method produces drift-free global translation under a long recording time and reduces foot-skating effects.

cs.CV↗

arXiv2026

Revisiting the Origin of the Star-Forming Main Sequence Based on a Volume-Limited Sample of ~25,000 Galaxies

We revisit the extensively debated star-forming main sequence (SFMS)-a tight correlation between the star formation rate and stellar mass in both kiloparsec-resolved and integrated galaxies. We statistically explore the fundamental drivers of star formation at global scales, using a large volume-limited sample of 24,954 local star-forming galaxies to overcome the limitations of previous works. Based on the mid-infrared 12 micron luminosity, stellar mass, and g-r color, we estimate the molecular gas mass for the considered sample. At galaxy-wide scales, we establish global relations between the surface densities of the star formation rate, stellar mass, and molecular gas mass . These global density relations are connected with and follow similar trends as the resolved SFMS, the Kennicutt-Schmidt (KS) relation, and the molecular gas main sequence (MGMS). Taking advantage of this large catalog, we show that the scatters in the global KS and MGMS relations are smaller than that of the global relation between the star formation rate surface density and stellar mass surface density, and their Pearson correlation coefficients are higher. More importantly, multivariate regression and partial correlation analyses demonstrate that the apparent correlation between the star formation rate surface density and stellar mass surface density is entirely mediated by the molecular gas surface density, with its best-fit parameters directly derivable from those of the KS and MGMS relations. Overall, our findings suggest that the correlation between stellar mass and molecular gas, as well as that between molecular gas and star formation, are more direct and fundamental. The star-forming main sequence thus appears to be a natural by-product of these two tighter relations.

astro-ph.GA↗

arXiv2026

EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports

Endometriosis ultrasound reports are often unstructured free-text documents that require manual abstraction for downstream tasks such as analytics, machine learning model training, and clinical auditing. We present \textbf{EndoExtract}, an on-premise LLM-powered system that extracts structured data from these reports and surfaces interpretive fields for human review. Through contextual inquiry with research assistants, we identified key workflow pain points: asymmetric trust between numerical and interpretive fields, repetitive manual highlighting, fatigue from sustained comparison, and terminology inconsistency across radiologists. These findings informed an interface that surfaces only interpretive fields for mandatory review, automatically highlights source evidence within PDFs, and separates batch extraction from human-paced verification. A formative workshop revealed that \textbf{EndoExtract} supports a shift from field-by-field data entry to supervisory validation, though participants noted risks of over-skimming and challenges in managing missing data.

cs.HC↗

arXiv2026

Beyond Global Scanning: Adaptive Visual State Space Modeling for Salient Object Detection in Optical Remote Sensing Images

Salient object detection (SOD) in optical remote sensing images (ORSIs) faces numerous challenges, including significant variations in target scales and low contrast between targets and the background. Existing methods based on vision transformers (ViTs) and convolutional neural networks (CNNs) architectures aim to leverage both global and local features, but the difficulty in effectively integrating these heterogeneous features limits their overall performance. To overcome these limitations, we propose an adaptive state space context network (ASCNet), which builds upon the state space model mechanism to simultaneously capture long-range dependencies and enhance regional feature representation. Specifically, we employ the visual state space encoder to extract multi-scale features. To further achieve deep guidance and enhancement of these features, we design a Multi-Level Context Module (MLCM), which module strengthens cross-layer interaction capabilities between features of different scales while enhancing the model's structural perception, allowing it to distinguish between foreground and background more effectively. Then, we design the Adaptive Patchwise Visual State Space (APVSS) block as the decoder of ASCNet, which integrates our proposed Dynamic Adaptive Granularity Scan (DAGS) and Granularity-aware Propagation Module (GPM). It performs adaptive patch scanning on feature maps enhanced by local perception, thereby capturing rich local region information and enhancing state space model's local modeling capability. Extensive experimental results demonstrate that the proposed model achieves state-of-the-art performance, validating its effectiveness and superiority.

cs.CV↗

arXiv2026

Safe Control and Learning Using Generalized Action Governor

This paper introduces the Generalized Action Governor (AG), a supervisory scheme that augments a nominal closed-loop system with the capability to enforce state and input constraints through online action adjustment. We develop a generalized AG theory for discrete-time systems under bounded uncertainties, and relax the usual requirement of positive invariance to returnability of a safe set. Based on the theory, we present tailored AG design procedures for linear systems and for discrete systems with finite state and action spaces. We further study safe online learning enabled by the AG and present two safe learning strategies, namely safe Q-learning and safe data-driven Koopman operator-based control, both integrated with the AG to guarantee constraint satisfaction during learning. Numerical results illustrate the proposed methods.

eess.SY↗

arXiv2026

WaterFlow: Explicit Physics-Prior Rectified Flow for Underwater Saliency Mask Generation

Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to ignore the physical principles of underwater imaging or simply treat degradation phenomena in underwater images as interference factors that must be eliminated, failing to fully exploit the valuable information they contain. We propose WaterFlow, a rectified flow-based framework for underwater salient object detection that innovatively incorporates underwater physical imaging information as explicit priors directly into the network training process and introduces temporal dimension modeling, significantly enhancing the model's capability for salient object identification. On the USOD10K dataset, WaterFlow achieves a 0.072 gain in S_m, demonstrating the effectiveness and superiority of our method. https://github.com/Theo-polis/WaterFlow.

cs.CV↗

arXiv2026

Who Fails Where? LLM and Human Error Patterns in Endometriosis Ultrasound Report Extraction

In this study, we evaluate a locally-deployed large-language model (LLM) to convert unstructured endometriosis transvaginal ultrasound (eTVUS) scan reports into structured data for imaging informatics workflows. Across 49 eTVUS reports, we compared three LLMs (7B/8B and a 20B-parameter model) against expert human extraction. The 20B model achieved a mean accuracy of 86.02%, substantially outperforming smaller models and confirming the importance of scale in handling complex clinical text. Crucially, we identified a highly complementary error profile: the LLM excelled at syntactic consistency (e.g., date/numeric formatting) where humans faltered, while human experts provided superior semantic and contextual interpretation. We also found that the LLM's semantic errors were fundamental limitations that could not be mitigated by simple prompt engineering. These findings strongly support a human-in-the-loop (HITL) workflow in which the on-premise LLM serves as a collaborative tool, not a full replacement. It automates routine structuring and flags potential human errors, enabling imaging specialists to focus on high-level semantic validation. We discuss implications for structured reporting and interactive AI systems in clinical practice.

cs.HC↗

arXiv2026

VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology

Accurate semantic segmentation for histopathology image is crucial for quantitative tissue analysis and downstream clinical modeling. Recent segmentation foundation models have improved generalization through large-scale pretraining, yet remain poorly aligned with pathology because they treat segmentation as a static visual prediction task. Here we present VISTA-PATH, an interactive, class-aware pathology segmentation foundation model designed to resolve heterogeneous structures, incorporate expert feedback, and produce pixel-level segmentation that are directly meaningful for clinical interpretation. VISTA-PATH jointly conditions segmentation on visual context, semantic tissue descriptions, and optional expert-provided spatial prompts, enabling precise multi-class segmentation across heterogeneous pathology images. To support this paradigm, we curate VISTA-PATH Data, a large-scale pathology segmentation corpus comprising over 1.6 million image-mask-text triplets spanning 9 organs and 93 tissue classes. Across extensive held-out and external benchmarks, VISTA-PATH consistently outperforms existing segmentation foundation models. Importantly, VISTA-PATH supports dynamic human-in-the-loop refinement by propagating sparse, patch-level bounding-box annotation feedback into whole-slide segmentation. Finally, we show that the high-fidelity, class-aware segmentation produced by VISTA-PATH is a preferred model for computational pathology. It improve tissue microenvironment analysis through proposed Tumor Interaction Score (TIS), which exhibits strong and significant associations with patient survival. Together, these results establish VISTA-PATH as a foundation model that elevates pathology image segmentation from a static prediction to an interactive and clinically grounded representation for digital pathology. Source code and demo can be found at https://github.com/zhihuanglab/VISTA-PATH.

cs.CV↗