arXiv subjects

Hong Pan

Publications and source records attributed to Hong Pan.

15 recordsLinked to original sources

arXiv2026

Structured Transfer Learning for Survival Risk Stratification in Data-Sparse Clinical Cohorts

Background: Survival prediction models are often less reliable in clinical groups with limited sample sizes or few outcome events. Target-only models may be unstable, whereas models from larger cohorts may transfer poorly when risk-factor effects differ across populations. We evaluated whether structured transfer learning can improve survival risk stratification in data-sparse cohorts while allowing cohort-specific adaptation. Methods: We developed the COhort-shared Rank-rEduced Cox model (CORE-Cox), a two-stage framework for multi-outcome survival prediction. CORE-Cox learns shared risk-factor patterns across related outcomes in a larger source cohort via a low-rank Cox coefficient structure, then adapts these patterns to a smaller target cohort through regularized residual correction. We evaluated CORE-Cox in UK Biobank (White source, n=150,093; Asian target, n=2,534) and MIMIC-IV (White ICU source, n=15,997; Asian ICU target, n=672), comparing against target-only Cox, penalized Cox, low-rank multi-task, naive pooling, direct transfer, and single-outcome residual transfer under repeated nested cross-validation. Results: CORE-Cox achieved best or near-best discrimination across most outcomes. Mean C-index improved from 0.733 to 0.766 in UK Biobank and from 0.628 to 0.658 in MIMIC-IV, with gains in eight of nine outcomes. CORE-Cox also improved top-15% risk enrichment, with hazard-ratio estimates typically intermediate between source-only and target-only models. Discussion: CORE-Cox offers an interpretable transfer-learning framework for survival risk stratification in data-sparse cohorts, combining shared cross-outcome structure with cohort-specific adaptation. Further validation is needed before use in calibrated absolute-risk prediction or clinical decision-making.

stat.ME↗

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

Lemon Agent Technical Report

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and multimodal perception. Based on these observations, Lemon Agent is introduced, a multi-agent orchestrator-worker system built on a newly proposed AgentCortex framework, which formalizes the classic Planner-Executor-Memory paradigm through an adaptive task execution mechanism. Our system integrates a hierarchical self-adaptive scheduling mechanism that operates at both the overall orchestrator layer and workers layer. This mechanism can dynamically adjust computational intensity based on task complexity. It enables orchestrator to allocate one or more workers for parallel subtask execution, while workers can further improve operational efficiency by invoking tools concurrently. By virtue of this two-tier architecture, the system achieves synergistic balance between global task coordination and local task execution, thereby optimizing resource utilization and task processing efficiency in complex scenarios. To reduce context redundancy and increase information density during parallel steps, we adopt a three-tier progressive context management strategy. To make fuller use of historical information, we propose a self-evolving memory system, which can extract multi-dimensional valid information from all historical experiences to assist in completing similar tasks. Furthermore, we provide an enhanced MCP toolset. Empirical evaluations on authoritative benchmarks demonstrate that our Lemon Agent can achieve a state-of-the-art 91.36% overall accuracy on GAIA and secures the top position on the xbench-DeepSearch leaderboard with a score of 77+.

cs.MA↗

arXiv2025

MAGI-1: Autoregressive Video Generation at Scale

We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to denoise per-chunk noise that increases monotonically over time, MAGI-1 enables causal temporal modeling and naturally supports streaming generation. It achieves strong performance on image-to-video (I2V) tasks conditioned on text instructions, providing high temporal consistency and scalability, which are made possible by several algorithmic innovations and a dedicated infrastructure stack. MAGI-1 facilitates controllable generation via chunk-wise prompting and supports real-time, memory-efficient deployment by maintaining constant peak inference cost, regardless of video length. The largest variant of MAGI-1 comprises 24 billion parameters and supports context lengths of up to 4 million tokens, demonstrating the scalability and robustness of our approach. The code and models are available at https://github.com/SandAI-org/MAGI-1 and https://github.com/SandAI-org/MagiAttention. The product can be accessed at https://sand.ai.

cs.CV↗

arXiv2022

Bistability in dissipatively coupled cavity magnonics

Dissipative coupling of resonators arising from their cooperative dampings to a common reservoir induces intriguingly new physics such as energy level attraction. In this study, we report the nonlinear properties in a dissipatively coupled cavity magnonic system. A magnetic material YIG (yttrium iron garnet) is placed at the magnetic field node of a Fabry-Perot-like microwave cavity such that the magnons and cavity photons are dissipatively coupled. Under high power excitation, a nonlinear effect is observed in the transmission spectra, showing bistable behaviors. The observed bistabilities are manifested as clockwise, counterclockwise, and butterfly-like hysteresis loops with different frequency detuning. The experimental results are well explained as a Duffing oscillator dissipatively coupled with a harmonic one and the required trigger condition for bistability could be determined quantitatively by the coupled oscillator model. Our results demonstrate that the magnon damping has been suppressed by the dissipative interaction, which thereby reduces the threshold for conventional magnon Kerr bistability. This work sheds light upon potential applications in developing low power nonlinearity devices, enhanced anharmonicity sensors and for exploring the non-Hermitian physics of cavity magnonics in the nonlinear regime.

cond-mat.mes-hall↗

arXiv2021

FDA: Feature Decomposition and Aggregation for Robust Airway Segmentation

3D Convolutional Neural Networks (CNNs) have been widely adopted for airway segmentation. The performance of 3D CNNs is greatly influenced by the dataset while the public airway datasets are mainly clean CT scans with coarse annotation, thus difficult to be generalized to noisy CT scans (e.g. COVID-19 CT scans). In this work, we proposed a new dual-stream network to address the variability between the clean domain and noisy domain, which utilizes the clean CT scans and a small amount of labeled noisy CT scans for airway segmentation. We designed two different encoders to extract the transferable clean features and the unique noisy features separately, followed by two independent decoders. Further on, the transferable features are refined by the channel-wise feature recalibration and Signed Distance Map (SDM) regression. The feature recalibration module emphasizes critical features and the SDM pays more attention to the bronchi, which is beneficial to extracting the transferable topological features robust to the coarse labels. Extensive experimental results demonstrated the obvious improvement brought by our proposed method. Compared to other state-of-the-art transfer learning methods, our method accurately segmented more bronchi in the noisy CT scans.

eess.IV↗

arXiv2021

Strongly coupled Yukawa plasma layer in a harmonic trap

Observations made in dusty plasma experiments suggest that an ensemble of electrically charged solid particles, confined in an elongated trap, develops structural inhomogeneities. With narrowing the trap the particles tend to form layers oriented parallel with the trap walls. In this work we present theoretical and numerical results on the structure of three-dimensional many-particle systems with screened Coulomb (Yukawa) inter-particle interaction in the strongly coupled liquid phase, confined in one-dimensional harmonic trap, forming quasi-2D configurations. Particle density profiles are calculated by means of the hypernetted chain approximation (HNC), showing clear signs of layer formation. The mechanism behind the formation of layer structure is discussed and a method to predict the number of layers is presented. Molecular dynamics (MD) simulations provide validation of the theoretical results and detailed microscopic insights.

physics.plasm-ph↗

arXiv2021

Condition Assessment of Stay Cables through Enhanced Time Series Classification Using a Deep Learning Approach

This study proposes a data-driven method that detects cable damage from measured cable forces by recognizing biased patterns from the intact conditions. The proposed method solves the pattern recognition problem for cable damage detection through time series classification (TSC) in deep learning, considering that the cable's behavior can be implicitly represented by the measured cable force series. A deep learning model, long short term memory fully convolutional network (LSTM-FCN), is leveraged by assigning appropriate inputs and representative class labels for the TSC problem, First, a TSC classifier is trained and validated using the data collected under intact conditions of stay cables, setting the segmented data series as input and the cable (or cable pair) ID as class labels. Subsequently, the classifier is tested using the data collected under possible damaged conditions. Finally, the cable or cable pair corresponding to the least classification accuracy is recommended as the most probable damaged cable or cable pair. The proposed method was tested on an in-service cable-stayed bridge with damaged stay cables. Two scenarios in the proposed TSC scheme were investigated: 1) raw time series of cable forces were fed into the classifiers; and 2) cable force ratios were inputted in the classifiers considering the possible variation of force distribution between cable pairs due to cable damage. Combining the results of TSC testing in these two scenarios, the cable with rupture was correctly identified. This study proposes a data-driven methodology for cable damage detection that requires the least data preprocessing and feature engineering, which enables fast and convenient early detection in real applications.

cs.LG↗

arXiv2020

Strongly coupled Yukawa trilayer liquid: Structure and dynamics

The equilibrium structure and the dispersion relations of collective excitations in trilayer Yukawa systems in the strongly coupled liquid regime are examined. The equilibrium correlations reveal a variety of structures in the liquid phase, reminiscent of the corresponding structures in the solid phase. At small layer separation substitutional disorder becomes the governing feature. Theoretical dispersion relations are obtained by applying the Quasi-Localised Charge Approximation (QLCA) formalism, while numerical data are generated by micro-canonical molecular dynamics (MD) simulations. The dispersions and polarizations of the collective excitations obtained through both of these methods are compared and discussed in detail. We find that the QLCA method is, in general, very satisfactory, but that there are phenomena not covered by the QLCA. In particular, by analyzing the dynamical longitudinal and transverse current fluctuation spectra we discover the existence of a novel structure, not related to the collective mode spectra. This also provides a new insight into the long-standing problem of the gap frequency discrepancy, observed in strongly coupled layered systems in earlier studies.

physics.plasm-ph↗

arXiv2020

PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors

Precise segmentation of organs and tumors plays a crucial role in clinical applications. It is a challenging task due to the irregular shapes and various sizes of organs and tumors as well as the significant class imbalance between the anatomy of interest (AOI) and the background region. In addition, in most situation tumors and normal organs often overlap in medical images, but current approaches fail to delineate both tumors and organs accurately. To tackle such challenges, we propose a position-guided deformable UNet, namely PGD-UNet, which exploits the spatial deformation capabilities of deformable convolution to deal with the geometric transformation of both organs and tumors. Position information is explicitly encoded into the network to enhance the capabilities of deformation. Meanwhile, we introduce a new pooling module to preserve position information lost in conventional max-pooling operation. Besides, due to unclear boundaries between different structures as well as the subjectivity of annotations, labels are not necessarily accurate for medical image segmentation tasks. It may cause the overfitting of the trained network due to label noise. To address this issue, we formulate a novel loss function to suppress the influence of potential label noise on the training process. Our method was evaluated on two challenging segmentation tasks and achieved very promising segmentation accuracy in both tasks.

eess.IV↗

arXiv2020

A Novel DNN Training Framework via Data Sampling and Multi-Task Optimization

Conventional DNN training paradigms typically rely on one training set and one validation set, obtained by partitioning an annotated dataset used for training, namely gross training set, in a certain way. The training set is used for training the model while the validation set is used to estimate the generalization performance of the trained model as the training proceeds to avoid over-fitting. There exist two major issues in this paradigm. Firstly, the validation set may hardly guarantee an unbiased estimate of generalization performance due to potential mismatching with test data. Secondly, training a DNN corresponds to solve a complex optimization problem, which is prone to getting trapped into inferior local optima and thus leads to undesired training results. To address these issues, we propose a novel DNN training framework. It generates multiple pairs of training and validation sets from the gross training set via random splitting, trains a DNN model of a pre-specified structure on each pair while making the useful knowledge (e.g., promising network parameters) obtained from one model training process to be transferred to other model training processes via multi-task optimization, and outputs the best, among all trained models, which has the overall best performance across the validation sets from all pairs. The knowledge transfer mechanism featured in this new framework can not only enhance training effectiveness by helping the model training process to escape from local optima but also improve on generalization performance via implicit regularization imposed on one model training process from other model training processes. We implement the proposed framework, parallelize the implementation on a GPU cluster, and apply it to train several widely used DNN models. Experimental results demonstrate the superiority of the proposed framework over the conventional training paradigm.

cs.NE↗

arXiv2019

Trilayer dusty plasma lattice: structure and dynamics

In this paper, we studied the structure and dynamics for a trilayer Yukawa crystal. We firstly studied the optimal lattice structure by comparing lattice interaction energy from different lattice distribution, after that, we did the collective mode calculation and analyzed its eigenvectors, if the lattice structure is stable, all the eigenvalues of the dynamical matrix should be positive.

physics.plasm-ph↗

arXiv2016

A comprehensive study of sparse codes on abnormality detection

Sparse representation has been applied successfully in abnormal event detection, in which the baseline is to learn a dictionary accompanied by sparse codes. While much emphasis is put on discriminative dictionary construction, there are no comparative studies of sparse codes regarding abnormality detection. We comprehensively study two types of sparse codes solutions - greedy algorithms and convex L1-norm solutions - and their impact on abnormality detection performance. We also propose our framework of combining sparse codes with different detection methods. Our comparative experiments are carried out from various angles to better understand the applicability of sparse codes, including computation time, reconstruction error, sparsity, detection accuracy, and their performance combining various detection methods. Experiments show that combining OMP codes with maximum coordinate detection could achieve state-of-the-art performance on the UCSD dataset [14].

cs.CV↗

arXiv2015

Ultrafast electron dynamics at the Dirac node of the topological insulator Sb$_2$Te$_3$

Topological insulators (TIs) are a new quantum state of matter. Their surfaces and interfaces act as a topological boundary to generate massless Dirac fermions with spin-helical textures. Investigation of fermion dynamics near the Dirac point is crucial for the future development of spintronic devices incorporating topological insulators. However, research so far has been unsatisfactory because of a substantial overlap with the bulk valence band and a lack of a completely unoccupied Dirac point (DP). Here, we explore the surface Dirac fermion dynamics in the TI Sb$_2$Te$_3$ by time- and angle-resolved photoemission spectroscopy (TrARPES). Sb$_2$Te$_3$ has a DP located completely above the Fermi energy ($E_F$) with an in-gap DP. The excited electrons in the upper Dirac cone stay longer than those below the Dirac point to form an inverted population. This was attributed to a reduced density of states (DOS) near the DP .

cond-mat.mtrl-sci↗

arXiv2012

Carrier dependent ferromagnetism in chromium doped topological insulator $Cr_{0.2}Bi_xSb_{1.8-x}Te_3$

Carrier-independent ferromagnetism of chromium doped topological insulator $Bi_xSb_{2-x}Te_3$ thin films,which cannot be explained by current theory of dilute magnetic semiconductor, has been reported recently. To study if it is related to the distinctive surface state of topological insulator, we studied the structural, magnetic and transport characters of $Cr_{0.2}Bi_xSb_{1.8-x}Te_3$ single crystals. The Curie temperature $T_c$, which is determined from magnetization and anomalous Hall effect measurements by Arrott plots, is found to be proportional to $p^{1/3}$, where p is the hole density. This fact supports a scenario of RKKY interaction with mean-field approximation. This carrier density dependent nature enables tuning and controlling of the magnetic properties by applying a gate voltage in the future science researches and spintronics applications.

cond-mat.mtrl-sci↗