arXiv subjects

Lu Huang

Publications and source records attributed to Lu Huang.

At least 19 recordsLinked to original sources

arXiv2026

JAX-FEM-ANISO: Differentiable GPU-Accelerated Finite Element Framework for Inverse Identification of Finite-Strain Anisotropic Plasticity

We present a fully differentiable, GPU-accelerated finite element framework JAX-FEM-ANISO, for forward simulation and inverse parameter identification of finite-strain anisotropic plasticity. Built on JAX-FEM, the framework exploits modern accelerator architectures by parallelizing the three major computational bottlenecks in nonlinear FEM: elemental weak-form and tangent-stiffness evaluation, global sparse matrix assembly, and sparse linear solution. For a large-scale forward problem with 3 million degrees of freedom, JAX-FEM-ANISO on a single NVIDIA H100 GPU achieves up to 9.4$\times$ speed-up over a 24-core CPU Abaqus baseline. Automatic differentiation is applied through the constitutive update and solver workflow, providing consistent Jacobians for complex constitutive models without manual derivation and accurate gradients for PDE-constrained inverse analysis. Compared with finite differences, the JAX-AD gradients avoid step-size sensitivity and provide the required sensitivities at substantially lower computational cost. For inverse characterization, we combine information-rich, topology-optimized heterogeneous specimens with full-field displacement data to identify advanced constitutive model parameters from a single test, replacing what would otherwise require many conventional experiments. We demonstrate accurate recovery of anisotropic yield and hardening parameters in progressively challenging settings, including uniform and spatially varying material properties. The resulting AD-based formulation enables efficient optimization in high-dimensional parameter spaces where finite-difference approaches are computationally infeasible. These results establish differentiable, GPU-accelerated FEM as a practical high-throughput engine for simulation, characterization, and optimization workflows in advanced manufacturing.

cs.CE↗

arXiv2026

Artificial intelligence-driven improvement of hospital logistics management resilience: a practical exploration based on H Hospital

Hospital logistics management faces growing pressure from internal operations and external emergencies, with artificial intelligence (AI) holding untapped potential to boost its resilience. This study explores AI's role in enhancing logistics resilience via a mixed-methods case study of H Hospital, combining 12 key informant interviews and a full survey of 151 logistics staff, with the PDCA cycle as the analytical framework. Thematic and quantitative analyses (hierarchical regression, structural equation modeling) were adopted for data analysis. Results showed 94.7% staff perceived AI application, with the strongest improvements in equipment maintenance (41.1%) and resource allocation (33.1%), but limited effects in emergency response (18.54%) and risk management (15.23%). AI integration positively correlated with logistics resilience (\b{eta}=0.642, p<0.001), with management system adaptability as a positive moderator (\b{eta}=0.208, p<0.01). The PDCA cycle fully mediated the AI-resilience relationship. We conclude AI effectively enhances logistics resilience, dependent on adaptive management systems and structured continuous improvement mechanisms. Targeted strategies are proposed to form an AI-driven closed-loop resilience mechanism, offering empirical guidance for AI-hospital logistics integration and resilient health system construction.

cs.AI↗

arXiv2026

Efficient endometrial carcinoma screening via cross-modal synthesis and gradient distillation

Early detection of myometrial invasion is critical for the staging and life-saving management of endometrial carcinoma (EC), a prevalent global malignancy. Transvaginal ultrasound serves as the primary, accessible screening modality in resource-constrained primary care settings; however, its diagnostic reliability is severely hindered by low tissue contrast, high operator dependence, and a pronounced scarcity of positive pathological samples. Existing artificial intelligence solutions struggle to overcome this severe class imbalance and the subtle imaging features of invasion, particularly under the strict computational limits of primary care clinics. Here we present an automated, highly efficient two-stage deep learning framework that resolves both data and computational bottlenecks in EC screening. To mitigate pathological data scarcity, we develop a structure-guided cross-modal generation network that synthesizes diverse, high-fidelity ultrasound images from unpaired magnetic resonance imaging (MRI) data, strictly preserving clinically essential anatomical junctions. Furthermore, we introduce a lightweight screening network utilizing gradient distillation, which transfers discriminative knowledge from a high-capacity teacher model to dynamically guide sparse attention towards task-critical regions. Evaluated on a large, multicenter cohort of 7,951 participants, our model achieves a sensitivity of 99.5\%, a specificity of 97.2\%, and an area under the curve of 0.987 at a minimal computational cost (0.289 GFLOPs), substantially outperforming the average diagnostic accuracy of expert sonographers. Our approach demonstrates that combining cross-modal synthetic augmentation with knowledge-driven efficient modeling can democratize expert-level, real-time cancer screening for resource-constrained primary care settings.

cs.CV↗

arXiv2025

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

General-purpose robots need a deep understanding of the physical world, advanced reasoning, and general and dexterous control. This report introduces the latest generation of the Gemini Robotics model family: Gemini Robotics 1.5, a multi-embodiment Vision-Language-Action (VLA) model, and Gemini Robotics-ER 1.5, a state-of-the-art Embodied Reasoning (ER) model. We are bringing together three major innovations. First, Gemini Robotics 1.5 features a novel architecture and a Motion Transfer (MT) mechanism, which enables it to learn from heterogeneous, multi-embodiment robot data and makes the VLA more general. Second, Gemini Robotics 1.5 interleaves actions with a multi-level internal reasoning process in natural language. This enables the robot to "think before acting" and notably improves its ability to decompose and execute complex, multi-step tasks, and also makes the robot's behavior more interpretable to the user. Third, Gemini Robotics-ER 1.5 establishes a new state-of-the-art for embodied reasoning, i.e., for reasoning capabilities that are critical for robots, such as visual and spatial understanding, task planning, and progress estimation. Together, this family of models takes us a step towards an era of physical agents-enabling robots to perceive, think and then act so they can solve complex multi-step tasks.

cs.RO↗

arXiv2025

Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System

Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability estimation for robust speech-to-text system, which is lightweight, flexible, and accurate. Attention2Probability converts cross-attention weights between speech and terminology into presence probabilities, and it further employs curriculum learning to enhance retrieval accuracy. Furthermore, to tackle the lack of data for speech-to-text tasks with terminology intervention, we create and release a new speech dataset with terminology to support future research in this area. Experimental results show that Attention2Probability significantly outperforms the VectorDB method on our test set. Specifically, its maximum recall rates reach 92.57% for Chinese and 86.83% for English. This high recall is achieved with a latency of only 8.71ms per query. Intervening in SLMs' recognition and translation tasks using Attention2Probability-retrieved terms improves terminology accuracy by 6-17%, while revealing that the current utilization of terminology by SLMs has limitations.

cs.CL↗

arXiv2025

Selective Densification for Rapid Motion Planning in High Dimensions with Narrow Passages

Sampling-based algorithms are widely used for motion planning in high-dimensional configuration spaces. However, due to low sampling efficiency, their performance often diminishes in complex configuration spaces with narrow corridors. Existing approaches address this issue using handcrafted or learned heuristics to guide sampling toward useful regions. Unfortunately, these strategies often lack generalizability to various problems or require extensive prior training. In this paper, we propose a simple yet efficient sampling-based planning framework along with its bidirectional version that overcomes these issues by integrating different levels of planning granularity. Our approach probes configuration spaces with uniform random samples at varying resolutions and explores these multi-resolution samples online with a bias towards sparse samples when traveling large free configuration spaces. By seamlessly transitioning between sparse and dense samples, our approach can navigate complex configuration spaces while maintaining planning speed and completeness. The simulation results demonstrate that our approach outperforms several state-of-the-art sampling-based planners in $\mathbb{SE}(2)$, $\mathbb{SE}(3)$, and $\mathbb{R}^{14}$ with challenging terrains. Furthermore, experiments conducted with the Franka Emika Panda robot operating in a constrained workspace provide additional evidence of the superiority of the proposed method.

cs.RO↗

arXiv2025

A GAN-Enhanced Deep Learning Framework for Rooftop Detection from Historical Aerial Imagery

Precise detection of rooftops from historical aerial imagery is essential for analyzing long-term urban development and human settlement patterns. Nonetheless, black-and-white analog photographs present considerable challenges for modern object detection frameworks due to their limited spatial resolution, absence of color information, and archival degradation. To address these challenges, this research introduces a two-stage image enhancement pipeline based on Generative Adversarial Networks (GANs): image colorization utilizing DeOldify, followed by super-resolution enhancement with Real-ESRGAN. The enhanced images were subsequently employed to train and evaluate rooftop detection models, including Faster R-CNN, DETReg, and YOLOv11n. The results demonstrate that the combination of colorization with super-resolution significantly enhances detection performance, with YOLOv11n achieving a mean Average Precision (mAP) exceeding 85\%. This signifies an enhancement of approximately 40\% over the original black-and-white images and 20\% over images enhanced solely through colorization. The proposed method effectively bridges the gap between archival imagery and contemporary deep learning techniques, facilitating more reliable extraction of building footprints from historical aerial photographs. Code and resources for reproducing our results are publicly available at \href{https://github.com/Pengyu-gis/Historical-Aerial-Photos}{github.com/Pengyu-gis/Historical-Aerial-Photos}.

cs.CV↗

arXiv2025

The DESI DR1/DR2 evidence for dynamical dark energy is biased by low-redshift supernovae

Recently, a $3\sim4\sigma$ preference for dynamical dark energy has been reported by the Dark Energy Spectroscopic Instrument (DESI) collaboration, which has inspired hot debates on new physics or systematics. In this paper, we reveal that this preference is significantly biased by an external low-redshift supernova (low-$z$ SN) sample, which was combined with the Dark Energy Survey SN program (DES-SN) in their Year-Five data release (DESY5). Using the intercept in the SN magnitude-distance relation as a diagnostic for systematics, we find not only large dispersions but also a large discrepancy in the low-$z$ SN sample when compared to the high-$z$ DES-SN sample within the single DESY5 compilation, in contrast to the uniform behavior found in the PantheonPlus data. Correcting for this low-$z$ systematics with or without including the cosmic microwave background data can largely reduce the preference for dynamical DE to be less than $2\sigma$. Therefore, the DESI preference for dynamical DE is biased by some unknown systematics in the low-$z$ SN sample.

astro-ph.CO↗

arXiv2024

Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift

Data heterogeneity is one of the key challenges in federated learning, and many efforts have been devoted to tackling this problem. However, distributed concept drift with data heterogeneity, where clients may additionally experience different concept drifts, is a largely unexplored area. In this work, we focus on real drift, where the conditional distribution $P(Y|X)$ changes. We first study how distributed concept drift affects the model training and find that local classifier plays a critical role in drift adaptation. Moreover, to address data heterogeneity, we study the feature alignment under distributed concept drift, and find two factors that are crucial for feature alignment: the conditional distribution $P(Y|X)$ and the degree of data heterogeneity. Motivated by the above findings, we propose FedCCFA, a federated learning framework with classifier clustering and feature alignment. To enhance collaboration under distributed concept drift, FedCCFA clusters local classifiers at class-level and generates clustered feature anchors according to the clustering results. Assisted by these anchors, FedCCFA adaptively aligns clients' feature spaces based on the entropy of label distribution $P(Y)$, alleviating the inconsistency in feature space. Our results demonstrate that FedCCFA significantly outperforms existing methods under various concept drift settings. Code is available at https://github.com/Chen-Junbao/FedCCFA.

cs.LG↗

arXiv2024

Narrowing down the Hubble tension to the first two rungs of distance ladders

The decade-persistent Hubble tension has become a $5\sigma$ crisis of modern cosmology between the early-Universe extrapolation from globally fitting the standard $\Lambda$CDM to Planck-CMB measurements and the late-Universe measurement from the three-rung distance ladder with SH0ES calibration. Regarding the current dilemma of theoretical resolutions, recent focus has shifted to systematics inspection. Here we find an associated $5\sigma$ tension in the intercept of the supernova magnitude-redshift relation between the second-rung and third-rung supernovae from the PantheonPlus compilation independent of calibrations in use. As required by the consistency of the distance-ladder method, we propose a method to eliminate the intercept tension, directly constraining $H_0=73.4\pm1.0\;\mathrm{km/s/Mpc}$ from the first two-rung distance ladder alone without referring to the third-rung supernovae but still consistent with both SH0ES typical three-rung and first two-rung constraints, which not only supports our method to rebuild the intercept consistency but also rules out third-rung supernova systematics including the late-time transition in supernova absolute magnitude. Further crosschecking with the Carnegie Supernova Project revealed that different calibrators alone still consistently prefer our results. Therefore, the original Hubble tension between the Planck-CMB measurements and SH0ES three-rung distance ladder can be narrowed down to a tension between the Planck-CMB and the first two-rung measurements.

astro-ph.CO↗

arXiv2024

Asymptotically Optimal Lazy Lifelong Sampling-based Algorithm for Efficient Motion Planning in Dynamic Environments

The paper introduces an asymptotically optimal lifelong sampling-based path planning algorithm that combines the merits of lifelong planning algorithms and lazy search algorithms for rapid replanning in dynamic environments where edge evaluation is expensive. By evaluating only sub-path candidates for the optimal solution, the algorithm saves considerable evaluation time and thereby reduces the overall planning cost. It employs a novel informed rewiring cascade to efficiently repair the search tree when the underlying search graph changes. Theoretical analysis indicates that the proposed algorithm converges to the optimal solution as long as sufficient planning time is given. Planning results on robotic systems with $\mathbb{SE}(3)$ and $\mathbb{R}^7$ state spaces in challenging environments highlight the superior performance of the proposed algorithm over various state-of-the-art sampling-based planners in both static and dynamic motion planning tasks. The experiment of planning for a Turtlebot 4 operating in a dynamic environment with several moving pedestrians further verifies the feasibility and advantages of the proposed algorithm.

cs.RO↗

arXiv2024

Curvature perturbations from kinetic preheating after $\alpha$-attractor inflation

Preheating at the end of inflation is a violent nonlinear process that efficiently transfers the energy of the inflaton to a second field, the preheat field. When the preheat field is light during inflation and its background value modulates the preheating process, the superhorizon isocurvature perturbations of the preheat field may be converted to curvature perturbations that leave an imprint on the cosmic microwave background and the large-scale structure of the universe. We use high-precision lattice simulations to study kinetic preheating after $\alpha$-attractor inflation, a case where the effective mass of the preheat field is naturally suppressed during inflation. By comparing the expansion e-folds between different Hubble patches, we find that the conversion from isocurvature perturbations to curvature perturbations is very inefficient and can hardly be detected by cosmological observations.

astro-ph.CO↗

arXiv2024

Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

eess.AS↗

arXiv2024

Deep-learning-based groupwise registration for motion correction of cardiac $T_1$ mapping

Quantitative $T_1$ mapping by MRI is an increasingly important tool for clinical assessment of cardiovascular diseases. The cardiac $T_1$ map is derived by fitting a known signal model to a series of baseline images, while the quality of this map can be deteriorated by involuntary respiratory and cardiac motion. To correct motion, a template image is often needed to register all baseline images, but the choice of template is nontrivial, leading to inconsistent performance sensitive to image contrast. In this work, we propose a novel deep-learning-based groupwise registration framework, which omits the need for a template, and registers all baseline images simultaneously. We design two groupwise losses for this registration framework: the first is a linear principal component analysis (PCA) loss that enforces alignment of baseline images irrespective of the intensity variation, and the second is an auxiliary relaxometry loss that enforces adherence of intensity profile to the signal model. We extensively evaluated our method, termed ``PCA-Relax'', and other baseline methods on an in-house cardiac MRI dataset including both pre- and post-contrast $T_1$ sequences. All methods were evaluated under three distinct training-and-evaluation strategies, namely, standard, one-shot, and test-time-adaptation. The proposed PCA-Relax showed further improved performance of registration and mapping over well-established baselines. The proposed groupwise framework is generic and can be adapted to applications involving multiple images.

eess.IV↗

arXiv2024

A PAge-like Unified Dark Fluid Model

The unified dark fluid model unifies dark matter and dark energy into a single component, providing an alternative and more concise framework for interpreting cosmological observations. We introduce a PAge-like Unified Dark Fluid (PUDF) model based on the PAge approximation (Huang 2020), which is parameterized by the age of the universe and an $\eta$ parameter indicating the deviation from Einstein-De Sitter Universe. The PUDF model shares many similar features of the standard Lambda cold dark matter ($\Lambda$CDM) model and can effectively describe the large-scale structure formation and late-time cosmic acceleration. We constrain the PUDF model with the Planck 2018 cosmic microwave background anisotropies, baryon acoustic oscillation measurements including those from the most recent DESI 2024, the Pantheon+ sample of Type Ia supernovae, and the Cosmic Chronometers compilation. Although the PUDF performs well in fitting all the cosmological datasets, the joint analysis of the data still favors the $\Lambda$CDM model over the PUDF model, according to the Bayesian evidence of model comparison.

astro-ph.CO↗

arXiv2024

No-go guide for the Hubble tension: late-time or local-scale new physics

The standard model of modern cosmology might be cracked by the recent persistent hot debate on the Hubble-constant ($H_0$) tension, which manifests itself as the sound-horizon ($r_s$) tension or absolute-magnitude ($M_B$) tension if deeming the origin of the Hubble tension from modifying the early or late Universe, respectively. In this paper, we achieve a fully model-independent constraint (fitting a model-independent global parameterization to a model-independent inverse distant ladder with a model-independent high-redshift calibration) on late-time models with strong evidence against homogeneous new physics over the $\Lambda$-cold-dark-matter ($\Lambda$CDM) model. Further using this model-independent constraint to calibrate sufficiently local supernovae with corresponding late-time models extrapolated below the homogeneity scale, we find surprisingly that, although both $H_0$ tension and $M_B$ tension are absent in our local Universe, a combination of $H_0$ and $M_B$ as the intercept $a_B$ of the magnitude-redshift relation exhibits $3\sim 7\sigma$ tension even for the $\Lambda$CDM model. This $a_B$ tension seems to call for local-scale inhomogeneous new physics disguised as local observational systematics.

astro-ph.CO↗

arXiv2023

Improving Large-scale Deep Biasing with Phoneme Features and Text-only Data in Streaming Transducer

Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing with large-scale rare words remains challenging, as the performance drops significantly when more distractors exist and there are words with similar grapheme sequences in the bias list. In this paper, we combine the phoneme and textual information of rare words in Transducers to distinguish words with similar pronunciation or spelling. Moreover, the introduction of training with text-only data containing more rare words benefits large-scale deep biasing. The experiments on the LibriSpeech corpus demonstrate that the proposed method achieves state-of-the-art performance on rare word error rate for different scales and levels of bias lists.

cs.CL↗

arXiv2023

Quantifying the tension between cosmological models and JWST red candidate massive galaxies

We develop a Python tool to estimate the tail distribution of the number of dark matter halos beyond a mass threshold and in a given volume in a light-cone. The code is based on the extended Press-Schechter model and is computationally efficient, typically taking a few seconds on a personal laptop for a given set of cosmological parameters. The high efficiency of the code allows a quick estimation of the tension between cosmological models and the red candidate massive galaxies released by the James Webb Space Telescope, as well as scanning the theory space with the Markov Chain Monte Carlo method. As an example application, we use the tool to study the cosmological implication of the candidate galaxies presented in Labb\'e et al. (2023). The standard $\Lambda$ cold dark matter ($\Lambda$CDM) model is well consistent with the data if the star formation efficiency can reach $\sim 0.3$ at high redshift. For a low star formation efficiency $\epsilon \sim 0.1$, $\Lambda$CDM model is disfavored at $\sim 2\sigma$-$3\sigma$ confidence level.

astro-ph.CO↗