BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Shuo huang

Shuo huang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputer Visioneess.IVastro-ph.EPComputation and LanguageMachine Learningastro-ph.GAastro-ph.SRcond-mat.softmath.DSmath.FAmath.PRphysics.app-phphysics.flu-dynphysics.ins-detphysics.med-phPopulations and Evolution

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
13works
0followers
17topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

13 published item(s)

preprint2026arXiv

NeuroAgent: LLM Agents for Multimodal Neuroimaging Analysis and Research

Multimodal neuroimaging analysis often involves complex, modality-specific preprocessing workflows that require careful configuration, quality control, and coordination across heterogeneous toolchains. Beyond preprocessing, downstream statistical analysis and disease classification commonly require task-specific code, evaluation protocols, and data-format conventions, creating additional barriers between raw acquisitions and reproducible scientific analysis. We present NeuroAgent, an LLM-driven agentic framework that automates key preprocessing and analysis steps for heterogeneous neuroimaging data, including sMRI, fMRI, dMRI, and PET, and supports interactive downstream analysis through natural-language queries. NeuroAgent employs a hierarchical multi-agent architecture with a feedback-driven Generate-Execute-Validate engine: agents autonomously generate executable preprocessing code, detect and recover from runtime errors, and validate output integrity. We evaluate the system on 1,470 subjects pooled across all ADNI phases (CN=1,000, AD=470), where all subjects have sMRI and tabular data, with subsets also having Tau-PET (n=469), fMRI (n=278), and DTI ($n=620$). Pipeline ablation studies across multiple LLM backends show that capable models reach up to 100% intent-parsing accuracy, with the strongest backend (Qwen3.5-27B) reaching 84.8% end-to-end preprocessing step correctness. Automated recovery limits manual intervention to edge cases where human review is required via the Human-In-The-Loop interface. For Alzheimer's Disease classification using automatically preprocessed multimodal data, our agent ensemble achieves an AUC of 0.9518 with four modalities, outperforming all single-modality baselines. These results show that NeuroAgent can reduce the manual effort required for neuroimaging preprocessing and enable end-to-end automated analysis pipelines for neuroimaging research.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

PromptDx: Differentiable Prompt Tuning for Multimodal In-Context Alzheimer's Diagnosis

Deep learning models in medical imaging typically operate as parametric memory, diagnosing patients by recalling fixed knowledge learned during training. This contrasts sharply with clinical practice, where physicians employ analogical reasoning to diagnose new cases by referencing similar records from past exemplars. While In-Context Learning (ICL) frameworks such as Tabular Prior-Fitted Networks (TabPFN) offer a promising diagnosis-by-reference paradigm, they are designed with tabular-specific inductive priors and rely on non-differentiable preprocessing pipelines, leading to manifold mismatch and gradient fracture when applied to heterogeneous multimodal data. To address these limitations, we propose PromptDx, a novel diagnosis-by-reference framework that leverages a pre-trained TabPFN as an ICL engine while enabling seamless integration with multimodal representations. Our core contribution is a Differentiable Prompt Tuning (DPT) mechanism that aligns a Masked Multimodal Modeling module with the pre-trained ICL engine. By training a lightweight adapter as a differentiable surrogate for the engine's non-differentiable preprocessors, we enable an end-to-end optimization of multimodal prompts within the ICL paradigm. We validate our method on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset using 3D MRI and tabular biomarkers. Experiments demonstrate that our approach outperforms traditional parametric baselines. Notably, our method achieves superior performance using only 1% context samples compared to 30% in standard ICL, demonstrating exceptional manifold condensation ability. We further validate the generalizability of our DPT framework across six tabular datasets with diverse scales. Overall, our method offers a more data-efficient and clinically aligned paradigm for Alzheimer's Disease diagnosis.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Granular dynamics in auger sampling

From geotechnical applications to space exploration, auger drilling is often used as a standard tool for soil sample collection, instrument installation, and others. Focusing on granular flow associated with the rotary drilling process, we investigate the performance of auger drilling in terms of sampling efficiency, defined as the mass ratio of the soil sample collected in the coring tube to its total volume at a given penetration depth, by means of experiments, numerical simulations, as well as theoretical analysis. The ratio of rotation to penetration speed is found to play a crucial role in the sampling process. A continuum model for the coupled granular flow in both coring and discharging channels is proposed to elucidate the physical mechanism behind the sampling process. Supported by a comparison to experimental results, the continuum model provides a practical way to predict the performance of auger drilling. Further analysis reveals that the drilling process approaches a steady state with constant granular flow speeds in both channels. In the steady state, sampling efficiency decreases linearly with the growth of the rotation to penetration speed ratio, which can be well captured by the analytical solution of the model. The analytical solution also suggests that the sampling efficiency is independent of gravity in the steady state, which has profound implications for extraterrestrial sample collection in future space missions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

OGLE-2019-BLG-1470LABc: Another Microlensing Giant Planet in a Binary System?

We report the discovery and analysis of a candidate triple-lens single-source (3L1S) microlensing event, OGLE-2019-BLG-1470. This event was first classified as a normal binary-lens single-source (2L1S) event, but a careful 2L1S modelling showed that it needs an additional lens or source to fit the observed data. It is found that the 3L1S model provides the best fit, but the binary-lens binary-source (2L2S) model is only disfavoured by $Δχ^2 \simeq 18$. All of the feasible models include a planet with planet-to-host mass-ratios $10^{-3} \lesssim q \lesssim 10^{-2}$. A Bayesian analysis based on a Galactic model indicates that the planet is super-Jovian, and the projected host-planet separation is about 3 $\mathrm{au}$. Specifically, for the best-fit 3L1S model, the two stars have masses of $M_1=0.57^{+0.43}_{-0.32}M_{\odot}$, and $M_2=0.18^{+0.15}_{-0.10}M_{\odot}$, with projected separation of $1.3^{+0.5}_{-0.5}$ $\mathrm{au}$, and the planetary mass is $M_3=2.2^{+1.8}_{-1.3}M_{\rm{Jupiter}}$. For the 2L2S model, the masses of the host star and the planet are $0.55^{+0.44}_{-0.31}M_{\odot}$ and $4.6^{+3.7}_{-2.6}M_{\rm{Jupiter}}$, respectively. By investigating the properties of all known microlensing planets in binary systems, we find that all planets in binary systems published by the KMTNet survey are located inside the resonant caustics range with $q \gtrsim 2 \times 10^{-3}$, indicating the incompleteness of the KMTNet sample for planets in binary systems. Thus, planets in binary systems cannot be included in the current study of the KMTNet mass-ratio function, and a systematic search for planetary anomalies in KMTNet microlensing light curves of binary systems is needed.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

The dynamics of the TRAPPIST-1 system in the context of its formation

TRAPPIST-1 is an 0.09 $M_{\odot}$ star, which harbours a system of seven Earth-sized planets. Two main features stand out: (i) all planets have similar radii, masses, and compositions; and (ii) all planets are in resonance. Previous works have outlined a pebble-driven formation scenario where planets of similar composition form sequentially at the H$_2$O snowline (${\sim}0.1$ au for this low-mass star). It was hypothesized that the subsequent formation and migration led to the current resonant configuration. Here, we investigate whether the sequential planet formation model is indeed capable to produce the present-day resonant configuration, characterized by its two-body and three-body mean motion resonances structure. We carry out N-body simulations, accounting for type-I migration, stellar tidal damping, disc eccentricity-damping, and featuring a migration barrier located at the disc's inner edge. Due to the sequential migration, planets naturally form a chain of first-order resonances. But to explain the period ratios of the b/c/d-system, which are presently in higher-order resonances, we find that planets b and c must have marched across the migration barrier, into the gas-free cavity, before the disc has dispersed. We investigate both an early and late cavity infall scenario and find that the early infall model best matches the constraints, as well as being more probable. After the dispersal of the gaseous disc, stellar tidal torque also contributes towards a modest separation of the inner system. We outline how the insights obtained in this work can be applied to aid the understanding of other compact resonant planet systems.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Few-Shot Semantic Parsing for New Predicates

In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with utterance-logical form pairs per new predicate. The state-of-the-art neural semantic parsers achieve less than 25% accuracy on benchmark datasets when k= 1. To tackle this problem, we proposed to i) apply a designated meta-learning method to train the model; ii) regularize attention scores with alignment statistics; iii) apply a smoothing technique in pre-training. As a result, our method consistently outperforms all the baselines in both one and two-shot settings.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On Robustness of Neural Semantic Parsers

Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities against adversarial examples. In this paper, we provide the empirical study on the robustness of semantic parsers in the presence of adversarial attacks. Formally, adversaries of semantic parsing are considered to be the perturbed utterance-LF pairs, whose utterances have exactly the same meanings as the original ones. A scalable methodology is proposed to construct robustness test sets based on existing benchmark corpora. Our results answered five research questions in measuring the sate-of-the-art parsers' performance on robustness test sets, and evaluating the effect of data augmentation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Total Variation Denoising Method Based on Median Filter and Phase Consistency

The total variation method is widely used in image noise suppression. However, this method is easy to cause the loss of image details, and it is also sensitive to parameters such as iteration time. In this work, the total variation method has been modified using a diffusion rate adjuster based on the phase congruency and a fusion filter of median filter and phase consistency boundary, which is called the MPC-TV method. Experimental results indicate that MPC-TV method is effective in noise suppression, especially for the removing of speckle noise, and it can also improve the robustness of iteration time of TV method on noise with different variance.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Extinction and quasi-stationarity for discrete-time, endemic SIS and SIR models

Stochastic discrete-time SIS and SIR models of endemic diseases are introduced and analyzed. For the deterministic, mean-field model, the basic reproductive number $R_0$ determines their global dynamics. If $R_0\le 1$, then the frequency of infected individuals asymptotically converges to zero. If $R_0>1$, then the infectious class uniformly persists for all time; conditions for a globally stable, endemic equilibrium are given. In contrast, the infection goes extinct in finite time with probability one in the stochastic models for all $R_0$ values. To understand the length of the transient prior to extinction as well as the behavior of the transients, the quasi-stationary distributions and the associated mean time to extinction are analyzed using large deviation methods. When $R_0>1$, these mean times to extinction are shown to increase exponentially with the population size $N$. Moreover, as $N$ approaches $\infty$, the quasi-stationary distributions are supported by a compact set bounded away from extinction; sufficient conditions for convergence to a Dirac measure at the endemic equilibrium of the deterministic model are also given. In contrast, when $R_0<1$, the mean times to extinction are bounded above $1/(1-α)$ where $α<1$ is the geometric rate of decrease of the infection when rare; as $N$ approaches $\infty$, the quasi-stationary distributions converge to a Dirac measure at the disease-free equilibrium for the deterministic model. For several special cases, explicit formulas for approximating the quasi-stationary distribution and the associated mean extinction are given. These formulas illustrate how for arbitrarily small $R_0$ values, the mean time to extinction can be arbitrarily large, and how for arbitrarily large $R_0$ values, the mean time to extinction can be arbitrarily large.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Measurement of Liquid Flow Rate among the Annular Flow in Vertical Tee Junction

Since the liquid flow rate of the annular flow is closely related to the heat exchange efficiency, it has great significance to measure the liquid flow rate of the annular flow in vertical tee junction. In order to acquire the liquid flow rate of the annular flow in vertical tee junction, a measurement method has been designed, which implements the digital subtraction method to measure the thickness of the liquid film under the visible light and to apply the image feature matching algorithm to obtain the liquid velocity field. Moreover, the accuracy of the liquid film velocity field as well as the spatial and temporal stability of the mass flow rate is tested by proposed algorithms in this study. Experimental results show that the measurement error of our method is approximately 5% in the lower section of the main pipe and the branch pipe, and lower than 15% in the upper section of the main pipe. Therefore, this method has a high accuracy in comparison with other measurement approaches. Our method can be applied to measure and analyse the shape and property of the annular flow in the vertical tee junction.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Simulation of Skin Stretching around the Forehead Wrinkles in Rhytidectomy

Objective: Skin stretching around the forehead wrinkles is an important method in rhytidectomy. Proper parameters are required to evaluate the surgical effect. In this paper, a simulation method was proposed to obtain the parameters. Methods: Three-dimensional point cloud data with a resolution of 50 μm were employed. First, a smooth supporting contour under the wrinkled forehead was generated via b-spline interpolation and extrapolation to constrain the deformation of the wrinkled zone. Then, based on the vector formed intrinsic finite element (VFIFE) algorithm, the simulation was implemented in Matlab for the deformation of wrinkled forehead skin in the stretching process. Finally, the stress distribution and the residual wrinkles of forehead skin were employed to evaluate the surgical effect. Results: Although the residual wrinkles are similar when forehead wrinkles are finitely stretched, their stress distribution changes greatly. This indicates that the stress distribution in the skin is effective to evaluate the surgical effect, and the forehead wrinkles are easily to be overstretched, which may lead to potential skin injuries. Conclusion: The simulation method can predict stress distribution and residual wrinkles after forehead wrinkle stretching surgery, which can be potentially used to control the surgical process and further reduce risks of skin injury.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Theory of Deep Convolutional Neural Networks II: Spherical Analysis

Deep learning based on deep neural networks of various structures and architectures has been powerful in many practical applications, but it lacks enough theoretical verifications. In this paper, we consider a family of deep convolutional neural networks applied to approximate functions on the unit sphere $\mathbb{S}^{d-1}$ of $\mathbb{R}^d$. Our analysis presents rates of uniform approximation when the approximated function lies in the Sobolev space $W^r_\infty (\mathbb{S}^{d-1})$ with $r>0$ or takes an additive ridge form. Our work verifies theoretically the modelling and approximation ability of deep convolutional neural networks followed by downsampling and one fully connected layer or two. The key idea of our spherical analysis is to use the inner product form of the reproducing kernels of the spaces of spherical harmonics and then to apply convolutional factorizations of filters to realize the generated linear features.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Non-rigid Registration Method between 3D CT Liver Data and 2D Ultrasonic Images based on Demons Model

The non-rigid registration between CT data and ultrasonic images of liver can facilitate the diagnosis and treatment, which has been widely studied in recent years. To improve the registration accuracy of the Demons model on the non-rigid registration between 3D CT liver data and 2D ultrasonic images, a novel boundary extraction and enhancement method based on radial directional local intuitionistic fuzzy entropy in the polar coordinates has been put forward, and a new registration workflow has been provided. Experiments show that our method can acquire high-accuracy registration results. Experiments also show that the accuracy of the results of our method is higher than that of the original Demons method and the Demons method using simulated ultrasonic image by Field II. The operation time of our registration workflow is about 30 seconds, and it can be used in the surgery.

0 citations0 reviewsNo code linkedOpen access