arXiv subjects

Ye Li

Publications and source records attributed to Ye Li.

At least 55 records · Page 3Linked to original sources

arXiv2026

Bias-constrained multimodal intelligence for equitable and reliable clinical AI

The integration of medical imaging and clinical text has enabled the emergence of generalist artificial intelligence (AI) systems for healthcare. However, pervasive biases, such as imbalanced disease prevalence, skewed anatomical region distributions, heterogeneous imaging protocols, and demographic disparities, pose significant challenges to the fairness and reliability of vision-language systems in real-world clinical settings. Here we present BiasCareVL, a bias-aware multimodal learning framework that introduces bias control directly into model design, rather than treating it as a post hoc correction. BiasCareVL incorporates adaptive uncertainty modeling with optional human-in-the-loop refinement to regulate the influence of dominant data patterns and to promote equitable reasoning under distributional imbalance. Trained on 3.44 million samples spanning over 15 imaging modalities, the framework supports diverse clinical tasks, including visual question answering, disease classification, segmentation, and report generation within a unified representation space. Across eight public benchmarks covering dermatology, oncology, radiology, and pathology, BiasCareVL consistently outperforms 20 state-of-the-art methods, with pronounced gains in clinically challenging scenarios, including over 10% accuracy improvement in multi-class skin lesion diagnosis and more than 20% Dice improvement in small tumor segmentation. Furthermore, BiasCareVL achieves diagnostic performance exceeding human accuracy with substantially reduced time requirements when evaluated with board-certified radiologists. By open-sourcing BiasCareVL, we aim to promote a transparent, reproducible, and equitable future for AI in healthcare, paving the way for general-purpose, trustworthy, and clinically reliable AI systems.

cs.CV↗

arXiv2026

FAST Polarization Catalog of FRB 20240114A

Polarization measurements of fast radio bursts (FRBs) probe the magnetized plasma surrounding their central engines. FRB~20240114A is an exceptionally active repeating source, with 17,356 bursts detected between 2024 January 28 and 2025 May 30 by FAST, enabling time-resolved polarimetric studies. In this work, we present a polarimetric catalog of 6,131 bright bursts (with a signal-to-noise ratio S/N $\geq$ 20, 35.3% of the total sample), including arrival time (MJD$_{\text{topo}}$), dispersion measure (DM), burst width (W$_{\text{eff}}$), bandwidth, Faraday rotation measure (RM), linear and circular polarization degrees (DOL, DOC), and intrinsic polarization angle (PA$_0$). We detect a clear temporal evolution of RM: after an initial stable phase, it decreases linearly by $\sim$200 $\rm rad\ m^{-2}$ over 200 days, forming a bimodal distribution, whereas DM remains stable at 528.9 $\rm pc\ cm^{-3}$. The linear polarization fraction is generally high, with the 3$σ$ lower bound around 76%, while circular polarization is low, with 1,157 of 17,356 bursts (6.67%) having DOC $\geq$10%. We perform a power-law fit between $|\textrm{V}|$/I and $|\textrm{RM}|$, which yields an index of $-2.98 \pm 0.80$. It is found that the combined 2D distribution of L/I versus V/I remains stable, implying that the emission mechanism is largely invariant. Our PA$_0$ measurements show a broad, non-uniform distribution, implying a complex emission geometry. These results suggest that FRB~20240114A resides in a dynamically evolving magneto-ionic environment. This catalog provides a foundation for studies of repeating FRB progenitors and their environments.

astro-ph.HE↗

arXiv2026

A Geometry-Aware Operator Learning Framework for Interface Problems on Varying Domains

Solving Partial Differential Equation (PDE) interface problems on varying domains is a critical task in design and optimization, yet it remains computationally prohibitive for traditional solvers. Although operator learning has shown promise on fixed geometries, its potential for geometry-dependent interface problems has been largely unexplored. To bridge this gap, we propose an extension-based neural operator framework applicable to general linear interface problems. A key innovation of our method is the integration of the Tailored Finite Point Method (TFPM) with our base network, which reduces memory consumption and effectively alleviates the curse of dimensionality. On the theoretical front, we establish the continuity of the Helmholtz operator with respect to domain perturbations and provide rigorous error estimates for the proposed encodings. Comprehensive numerical experiments demonstrate that our framework achieves state-of-the-art accuracy and robustness. Consequently, this work provides a powerful, data-efficient tool for varying-domain simulations, offering new possibilities for real-time shape optimization.

math.NA↗

arXiv2026

An Intertwined Short and Long GRB with 4-minute Separation

Gamma-ray bursts (GRBs), the most energetic transients in the Universe, are traditionally classified into long-duration ($T_{90}>2$ s) and short-duration ($T_{90}<2$ s) events, associated with the core collapse of massive stars (Type II) and the merger of compact binary systems (Type I), respectively. The two classes exhibit distinct observational properties that serve as key diagnostic criteria for classification. Here we report GRB 160425A, a peculiar event comprising two sub-bursts separated by four minutes: a short-duration burst ($G_1$) and a long-duration burst ($G_2$). Nearly all standard prompt-emission diagnostics, including pulse morphology, duration, hardness ratio, minimum variability timescale, spectral properties, and established empirical correlations, consistently categorize $G_1$ as a short-like (Type I, merger-origin) and $G_2$ as a long-like (Type II, collapsar-origin) GRB. The coexistence of merger and collapsar signatures in a single event challenges existing progenitor frameworks and calls for a re-evaluation of GRB classification schemes and progenitor scenarios.

astro-ph.HE↗

arXiv2026

Set-Valued Prediction for Large Language Models with Feasibility-Aware Coverage Guarantees

Large language models (LLMs) inherently operate over a large generation space, yet conventional usage typically reports the most likely generation (MLG) as a point prediction, which underestimates the model's capability: although the top-ranked response can be incorrect, valid answers may still exist within the broader output space and can potentially be discovered through repeated sampling. This observation motivates moving from point prediction to set-valued prediction, where the model produces a set of candidate responses rather than a single MLG. In this paper, we propose a principled framework for set-valued prediction, which provides feasibility-aware coverage guarantees. We show that, given the finite-sampling nature of LLM generation, coverage is not always achievable: even with multiple samplings, LLMs may fail to yield an acceptable response for certain questions within the sampled candidate set. To address this, we establish a minimum achievable risk level (MRL), below which statistical coverage guarantees cannot be satisfied. Building on this insight, we then develop a data-driven calibration procedure that constructs prediction sets from sampled responses by estimating a rigorous threshold, ensuring that the resulting set contains a correct answer with a desired probability whenever the target risk level is feasible. Extensive experiments on six language generation tasks with five LLMs demonstrate both the statistical validity and the predictive efficiency of our framework.

cs.CL↗

arXiv2026

SG-DeepONet: Source-generalized deep operator learning for full waveform inversion

Full waveform inversion (FWI) aims to reconstruct subsurface velocity models from observed seismic wavefields and has recently benefited from advances in deep learning (DL). The performance of DL-based FWI critically depends on the diversity of training data, yet existing datasets such as OpenFWI rely on fixed or weakly varying source conditions, limiting their ability to represent realistic seismic scenarios and hindering source generalization. To address this issue, we construct a new source-variable seismic dataset, termed SVFWI, by systematically varying the frequencies and horizontal locations of multiple surface sources. SVFWI is further divided into three subsets that respectively model frequency variations, location variations, and their combined effects, providing a challenging benchmark in data-driven FWI. We further propose SG-DeepONet, a novel DeepONet-based encoder-decoder framework tailored for FWI. The branch network extracts multi-scale time-frequency features from seismic observations, the trunk network explicitly embeds source physical parameters, and an interactive decoding network enables effective nonlinear fusion and high-fidelity velocity reconstruction. Extensive experiments on SVFWI demonstrate that SG-DeepONet achieves superior inversion accuracy and robustness under varying source conditions compared with existing DL-based FWI methods.

cs.LG↗

arXiv2026

Image Segmentation via Variational Model Based Tailored UNet: A Deep Variational Framework

Traditional image segmentation methods, such as variational models based on partial differential equations (PDEs), offer strong mathematical interpretability and precise boundary modeling, but often suffer from sensitivity to parameter settings and high computational costs. In contrast, deep learning models such as UNet, which are relatively lightweight in parameters, excel in automatic feature extraction but lack theoretical interpretability and require extensive labeled data. To harness the complementary strengths of both paradigms, we propose Variational Model Based Tailored UNet (VM_TUNet), a novel hybrid framework that integrates the fourth-order modified Cahn-Hilliard equation with the deep learning backbone of UNet, which combines the interpretability and edge-preserving properties of variational methods with the adaptive feature learning of neural networks. Specifically, a data-driven operator is introduced to replace manual parameter tuning, and we incorporate the tailored finite point method (TFPM) to enforce high-precision boundary preservation. Experimental results on benchmark datasets demonstrate that VM_TUNet achieves superior segmentation performance compared to existing approaches, especially for fine boundary delineation.

cs.CV↗

arXiv2026

A Secure Splitting and Acceleration Strategy for TCP/QUIC in Interplanetary Networks

Interplanetary networks (IPNs) present unique challenges such as extreme delay, high loss, and frequent disruptions that severely degrade the performance of conventional transport protocols like Transmission Control Protocol (TCP) and Quick UDP Internet Connection (QUIC). To address these issues, we propose a secure transport acceleration strategy tailored for IPNs. This strategy is founded on our Non-Transparent Secure Proxy (NTSP) architecture, which enables connection splitting for end-to-end encrypted flows while preserving application layer security. Based on the NTSP, we design an IPN-aware transport policy that combines (i) a rate-based congestion control algorithm exploiting the pre-scheduled nature of deep-space links to achieve stable and efficient bandwidth utilization, and (ii) an adaptive packet-level forward error correction scheme to provide low-latency loss recovery without retransmissions. Furthermore, we introduce a theoretically grounded backpressure flow control mechanism, deriving an analytical model for optimal buffer sizing to mitigate rate mismatch and prevent bufferbloat. The strategy is implemented in a prototype system, PEPspace, and evaluated in representative Earth-Moon scenarios. Results show near-capacity and stable goodput and substantially improved delivery performance compared with TCP/QUIC variants and existing Performance Enhancing Proxies, while maintaining low latency and robust data delivery across intermittent links. The NTSP architecture is further discussed as a foundational framework for future unified IP/DTN architectures, bridging a key architectural gap in heterogeneous space networks.

cs.NI↗

arXiv2026

Seamless Handover in Direct-to-Device Satellite Networks: From an Interference-Aware Perspective

The direct-to-device (D2D) satellite network is an important 6G evolution direction to enable seamless ubiquitous connectivity. However, the network faces critical handover challenges due to high satellite mobility and wide beam footprints. Conventional handover strategies, mostly designed for terrestrial networks, may encounter excessive co-channel interference (CCI) and service degradation in the satellite environments. To address the issue, this paper introduces a novel handover optimization method to perform dynamic adjustment of an important parameter called elevation angle threshold (EAT) from an interference-aware perspective. Explicitly, we first analyze the trade-off between satellite visibility and CCI. Then, we propose a numerical algorithm to determine the optimal EAT that can achieve seamless coverage with CCI. We validate our method using a customized D2D LEO satellite network simulator in the Network Simulator (NS-3). The results demonstrate that the EAT optimization significantly reduces packet loss and hence enhances handover reliability. The work highlights the importance of interference-aware handover design for improving service continuity in future D2D satellite networks.

cs.NI↗

arXiv2026

AT 2024wpp: the most luminous fast-evolving optical transient linked to the merger explosion of a black-hole binary

Fast blue optical transients (FBOTs) represent one of the most exotic astrophysical transients, exhibiting unusually strong emission across X-ray, optical, and radio wavelengths. Their physical origins remain highly debated, with proposed explanations ranging from stellar explosion to tidal disruption event (TDE). Here we report observations of the most luminous FBOT, AT 2024wpp whose post-peak luminosity rebrightens in X ray and becomes flattening in optical in a manner follows the decay rate characteristic of TDEs ($L_{\rm bol} \propto t^{-5/3}$). This invokes energy contribution of accretion by a central compact object, getting further corroborations from hardening of X-ray spectral index and detection of outflow inferred from the emission lines at similar phase. Detailed modeling of luminsoity evolution favors a coalesce explosion of a 34 M$_{\odot}$ Wolf-Rayet star with a 15 M$_{\odot}$ black hole (BH), demonstrating that some FBOTs may be associated with TDE of a stellar blackhole.

astro-ph.HE↗

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↗

arXiv2026

Mass Concept Erasure in Diffusion Models with Concept Hierarchy

The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress specific concepts while preserving general generative capabilities. However, as the number of erased concepts grows, these methods often become inefficient and ineffective, since each concept requires a separate set of fine-tuned parameters and may degrade the overall generation quality. In this work, we propose a supertype-subtype concept hierarchy that organizes erased concepts into a parent-child structure. Each erased concept is treated as a child node, and semantically related concepts (e.g., macaw, and bald eagle) are grouped under a shared parent node, referred to as a supertype concept (e.g., bird). Rather than erasing concepts individually, we introduce an effective and efficient group-wise suppression method, where semantically similar concepts are grouped and erased jointly by sharing a single set of learnable parameters. During the erasure phase, standard diffusion regularization is applied to preserve denoising process in unmasked regions. To mitigate the degradation of supertype generation caused by excessive erasure of semantically related subtypes, we propose a novel method called Supertype-Preserving Low-Rank Adaptation (SuPLoRA), which encodes the supertype concept information in the frozen down-projection matrix and updates only the up-projection matrix during erasure. Theoretical analysis demonstrates the effectiveness of SuPLoRA in mitigating generation performance degradation. We construct a more challenging benchmark that requires simultaneous erasure of concepts across diverse domains, including celebrities, objects, and pornographic content.

cs.CV↗

arXiv2025

Investigating FRB 20240114A with FAST: Morphological Classification and Drifting Rate Measurements in a Burst-Cluster Framework

This study investigates the morphological classification and drifting rate measurement of the repeating fast radio burst (FRB) source FRB 20240114A using the Five-hundred-meter Aperture Spherical Telescope (FAST). Detected on January 14, 2024, FRB 20240114A exhibited an exceptionally high burst rate, revealing unique properties. Through observational campaigns over several months, we selected a dataset comprising 3,203 bursts (2,109 burst-clusters) during a continuous monitoring session (15,780 seconds) on March 12, 2024. Improving upon previous work, we clarify the definitions of sub-bursts, bursts and burst-clusters. Using an average dispersion measures (DM) of 529.2 pc cm$^{-3}$, we classified the burst-clusters into Downward Drifting, Upward Drifting, No Drifting, No Evidence for Drifting, Not-Clear, and Complex burst-clusters. Among the 978 burst-clusters that exhibit drifting behavior, 233 (23.82%) show upward drifting. Additionally, if 142 upward drifting single-component burst-clusters are excluded, upward drifting double- and multi-component burst-clusters still account for 10.89% of the 836 burst-clusters exhibiting drifting behavior, equating to 91 burst-clusters. Furthermore, if only upward drifting burst-clusters with consecutive time intervals (or upward drifting bursts) are considered, only 9 bursts remain. Drifting rate comparisons with other physical quantities reveal that the drifting rate increases with peak frequency for single-component burst-clusters with drifting behavior. Moreover, in single-component burst-clusters, those with upward drifting exhibit smaller effective widths, bandwidths, and fluxes than their downward drifting counterparts. A Kolmogorov-Smirnov test further indicates that upward drifting burst-clusters possess longer consecutive time intervals than downward drifting ones, suggesting distinct underlying physical mechanisms.

astro-ph.HE↗

arXiv2025

DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction

Lung cancer continues to be the leading cause of cancer-related deaths globally. Early detection and diagnosis of pulmonary nodules are essential for improving patient survival rates. Although previous research has integrated multimodal and multi-temporal information, outperforming single modality and single time point, the fusion methods are limited to inefficient vector concatenation and simple mutual attention, highlighting the need for more effective multimodal information fusion. To address these challenges, we introduce a Dual-Graph Spatiotemporal Attention Network, which leverages temporal variations and multimodal data to enhance the accuracy of predictions. Our methodology involves developing a Global-Local Feature Encoder to better capture the local, global, and fused characteristics of pulmonary nodules. Additionally, a Dual-Graph Construction method organizes multimodal features into inter-modal and intra-modal graphs. Furthermore, a Hierarchical Cross-Modal Graph Fusion Module is introduced to refine feature integration. We also compiled a novel multimodal dataset named the NLST-cmst dataset as a comprehensive source of support for related research. Our extensive experiments, conducted on both the NLST-cmst and curated CSTL-derived datasets, demonstrate that our DGSAN significantly outperforms state-of-the-art methods in classifying pulmonary nodules with exceptional computational efficiency.

cs.CV↗

arXiv2025

Redshift Classification of Optical Gamma-Ray Bursts using Supervised Learning

Gamma-ray bursts (GRBs) are among the most luminous explosions in the Universe and serve as powerful probes of the early cosmos. However, the rapid fading of their afterglows and the scarcity of spectroscopic measurements make photometric classification crucial for timely high-redshift identification. We present an ensemble machine learning framework for redshift classification of GRBs based solely on their optical plateau and prompt emission properties. Our dataset comprises 171 long GRBs observed by the Swift UVOT and more than 450 ground-based telescopes. The analysis pipeline integrates robust statistical techniques, including M-estimator outlier rejection, multivariate imputation using Multiple Imputation by Chained Equations, and Least Absolute Shrinkage and Selection Operator feature selection, followed by a SuperLearner ensemble combining parametric, semi-parametric, and non-parametric algorithms. The optimal model, trained on raw optical data with outlier removal at a redshift threshold of z equals 2.0, achieves a true positive rate of 74 percent and an area under the curve of 0.84, maintaining balanced generalization between training and test sets. At higher thresholds, such as z equals 3.0, the classifier sustains strong discriminative power with an area under the curve of 0.88. Validation on an independent GRB sample yields 97 percent overall accuracy, perfect specificity, and an ensemble area under the curve of 0.93. Compared to previous prompt- and X-ray-based classifiers, our optical framework offers enhanced sensitivity to high-redshift events, improved robustness against data incompleteness, and greater applicability to ground-based follow-up. We also publicly release a web application that enables real-time redshift classification, facilitating rapid identification of candidate high-redshift GRBs for cosmological studies.

astro-ph.HE↗

arXiv2025

Huayu: Advanced Real-Time Precipitation Estimation from Geostationary Satellite

As climate change drives increased frequency and intensity of extreme precipitation and flooding worldwide, posing escalating threats to public safety and economic assets, accurate and real-time satellite-based precipitation estimation is essential for operational large-scale hydrometeorological analysis and disaster monitoring. NASA's Integrated Multi-satellitE Retrievals for GPM (IMERG Final Run) combines information from "all" satellite microwave observations with gauge correction and climatological adjustment to produce precipitation estimates at 0.1° spatial and 30-min temporal resolution. However, its latency of approximately 3.5 months restricts its utility for real-time applications, despite outperforming mainstream satellite precipitation datasets in representing rainfall patterns and variability. We present Huayu, a novel machine learning-based real-time satellite precipitation retrieval system that relies solely on infrared observations from the FengYun-4B geostationary satellite to provide a more accurate precipitation estimate at a finer spatiotemporal resolution (15 min, 0.05°) over a 120° by 120° domain. Performance evaluations demonstrate that Huayu achieves strong consistency with rain gauge observations, yielding a critical success index (CSI) of 0.693 - representing a 3.43% improvement over IMERG Final Run (CSI: 0.670). Experimental results confirm that infrared satellite observations can deliver more accurate precipitation estimates than conventional multi-source algorithms.

physics.ao-ph↗

arXiv2025

Modeling and Analysis of Land-to-Ship Maritime Wireless Channels at 5.8 GHz

Maritime channel modeling is crucial for designing robust nearshore communication systems, yet reliable models that account for the dynamic marine environment with varying sea waves, wind conditions, and vessel motions remain scarce. This article investigates land-to-ship maritime wireless channel characteristics at 5.8 GHz based upon an extensive measurement campaign, with concurrent hydrological and meteorological information collection. First, a novel large-scale path loss model with physical foundation and high accuracy is proposed for dynamic marine environments. Then, we introduce the concept of sea-wave-induced fixed-point (SWIFT) fading, a peculiar phenomenon in maritime scenarios that captures the impact of sea surface fluctuations on received power. An enhanced two-ray model incorporating vessel rotational motion is propounded to simulate the SWIFT fading, showing good alignment with measured data, particularly for modest antenna movements. Next, the small-scale fading is studied by leveraging a variety of models including the two-wave with diffuse power (TWDP) and asymmetric Laplace distributions, with the latter performing well in most cases, while TWDP better captures bimodal fading in rough seas. Furthermore, maritime channel sparsity is examined via the Gini index and Rician $K$ factor, and temporal dispersion is characterized. The resulting channel models and parameter characteristics offer valuable insights for maritime wireless system design and deployment.

eess.SP↗

arXiv2025

Noise-robust Contrastive Learning for Critical Transition Detection in Dynamical Systems

Detecting critical transitions in complex, noisy time-series data is a fundamental challenge across science and engineering. Such transitions may be anticipated by the emergence of a low-dimensional order parameter, whose signature is often masked by high-amplitude stochastic variability. Standard contrastive learning approaches based on deep neural networks, while promising for detecting critical transitions, are often overparameterized and sensitive to irrelevant noise, leading to inaccurate identification of critical points. To address these limitations, we propose a neural network architecture, constructed using singular value decomposition technique, together with a strictly semi-orthogonality-constrained training algorithm, to enhance the performance of traditional contrastive learning. Extensive experiments demonstrate that the proposed method matches the performance of traditional contrastive learning techniques in identifying critical transitions, yet is considerably more lightweight and markedly more resistant to noise.

cs.LG↗