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

Yun Zhao

Yun Zhao contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningArtificial Intelligencephysics.opticsComputer VisionNeurons and Cognitionphysics.app-phquant-phComputation and LanguageComputational Engineering, Finance, and ScienceCryptography and SecurityEmerging Technologiesmath.DSmath.NTNeural and Evolutionary Computingphysics.med-ph

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
14works
0followers
15topics
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

14 published item(s)

preprint2026arXiv

CFSPMNet: Cross-subject Fourier-guided Spatial-Patch Mamba Network for EEG Motor Imagery Decoding in Stroke Patients

Motor imagery electroencephalography (MI-EEG) decoding offers a non-invasive route for post-stroke rehabilitation, but cross-patient use remains difficult because pathological neural reorganization changes task-related EEG dynamics, aperiodic activity, local excitability, cross-regional coordination, and trial-level brain-state context. This makes source-learned MI representations unreliable for unseen patients. To address this problem, we propose CFSPMNet, a cross-patient adaptation framework that models post-stroke MI-EEG as latent neural-state organization. CFSPMNet combines a Fourier-Reorganized State Mamba Network (FRSM) with Shared-Private Prototype Matching (SPPM). FRSM represents each trial as a latent physiological token sequence, reorganizes token states in the Fourier domain, and uses Fourier-derived trial context to guide Mamba state-space propagation. SPPM improves target pseudo-label updating by combining semantic confidence with shared-private physiological consistency, filtering confident but physiologically inconsistent target predictions. Leave-one-subject-out experiments on two stroke MI-EEG datasets show that CFSPMNet outperforms representative CNN-, Transformer-, Mamba-, and adaptation-based baselines, achieving average accuracies of 68.23% on XW-Stroke and 73.33% on 2019-Stroke, with gains of 5.63 and 8.25 percentage points over the strongest competitors. Ablation, sensitivity, feature-alignment, pseudo-label selection, and neurophysiological visualization analyses further support the roles of Fourier-domain token-state reorganization and calibrated pseudo-label updating. These results suggest that latent neural-state modeling can improve rehabilitation-oriented cross-patient BCI decoding. Code is available at https://github.com/wxk1224/CFSPMNet.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Generative Consistency Models for Estimation of Kinetic Parametric Image Posteriors in Total-Body PET

Dynamic total body positron emission tomography (TB-PET) makes it feasible to measure the kinetics of all organs in the body simultaneously which may lead to important applications in multi-organ disease and systems physiology. Since whole-body kinetics are highly heterogeneous with variable signal-to-noise ratios, parametric images should ideally comprise not only point estimates but also measures of posterior statistical uncertainty. However, standard Bayesian techniques, such as Markov chain Monte Carlo (MCMC), are computationally prohibitive at the total body scale. We introduce a generative consistency model (CM) that generates samples from the posterior distributions of the kinetic model parameters given measured time-activity curves and arterial input function. CM is able to collapse the hundreds of iterations required by standard diffusion models into just 3 denoising steps. When trained on 500,000 physiologically realistic two-tissue compartment model simulations, the CM produces similar accuracy to MCMC (median absolute percent error < 5%; median K-L divergence < 0.5) but is more than five orders of magnitude faster. CM produces more reliable Ki images than the Patlak method by avoiding the assumption of irreversibility, while also offering valuable information on statistical uncertainty of parameter estimates and the underlying model. The proposed framework removes the computational barrier to routine, fully Bayesian parametric imaging in TB-PET and is readily extensible to other tracers and compartment models.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Brain Model State Space Reconstruction Using an LSTM Neural Network

Objective Kalman filtering has previously been applied to track neural model states and parameters, particularly at the scale relevant to EEG. However, this approach lacks a reliable method to determine the initial filter conditions and assumes that the distribution of states remains Gaussian. This study presents an alternative, data-driven method to track the states and parameters of neural mass models (NMMs) from EEG recordings using deep learning techniques, specifically an LSTM neural network. Approach An LSTM filter was trained on simulated EEG data generated by a neural mass model using a wide range of parameters. With an appropriately customised loss function, the LSTM filter can learn the behaviour of NMMs. As a result, it can output the state vector and parameters of NMMs given observation data as the input. Main Results Test results using simulated data yielded correlations with R squared of around 0.99 and verified that the method is robust to noise and can be more accurate than a nonlinear Kalman filter when the initial conditions of the Kalman filter are not accurate. As an example of real-world application, the LSTM filter was also applied to real EEG data that included epileptic seizures, and revealed changes in connectivity strength parameters at the beginnings of seizures. Significance Tracking the state vector and parameters of mathematical brain models is of great importance in the area of brain modelling, monitoring, imaging and control. This approach has no need to specify the initial state vector and parameters, which is very difficult to do in practice because many of the variables being estimated cannot be measured directly in physiological experiments. This method may be applied using any neural mass model and, therefore, provides a general, novel, efficient approach to estimate brain model variables that are often difficult to measure.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Dimension approximation in smooth dynamical systems

For a non-conformal repeller $Λ$ of a $C^{1+α}$ map $f$ preserving an ergodic measure $μ$ of positive entropy, this paper shows that the Lyapunov dimension of $μ$ can be approximated gradually by the Carathéodory singular dimension of a sequence of horseshoes. For a $C^{1+α}$ diffeomorphism $f$ preserving a hyperbolic ergodic measure $μ$ of positive entropy, if $(f, μ)$ has only two Lyapunov exponents $λ_u(μ)>0>λ_s(μ)$, then the Hausdorff or lower box or upper box dimension of $μ$ can be approximated by the corresponding dimension of the horseshoes $\{Λ_n\}$. The same statement holds true if $f$ is a $C^1$ diffeomorphism with a dominated Oseledet&#39;s splitting with respect to $μ$.

0 citations0 reviewsNo code linkedOpen access
preprint2023arXiv

Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models

The burgeoning interest in Multimodal Large Language Models (MLLMs), such as OpenAI&#39;s GPT-4V(ision), has significantly impacted both academic and industrial realms. These models enhance Large Language Models (LLMs) with advanced visual understanding capabilities, facilitating their application in a variety of multimodal tasks. Recently, Google introduced Gemini, a cutting-edge MLLM designed specifically for multimodal integration. Despite its advancements, preliminary benchmarks indicate that Gemini lags behind GPT models in commonsense reasoning tasks. However, this assessment, based on a limited dataset (i.e., HellaSWAG), does not fully capture Gemini&#39;s authentic commonsense reasoning potential. To address this gap, our study undertakes a thorough evaluation of Gemini&#39;s performance in complex reasoning tasks that necessitate the integration of commonsense knowledge across modalities. We carry out a comprehensive analysis of 12 commonsense reasoning datasets, ranging from general to domain-specific tasks. This includes 11 datasets focused solely on language, as well as one that incorporates multimodal elements. Our experiments across four LLMs and two MLLMs demonstrate Gemini&#39;s competitive commonsense reasoning capabilities. Additionally, we identify common challenges faced by current LLMs and MLLMs in addressing commonsense problems, underscoring the need for further advancements in enhancing the commonsense reasoning abilities of these models.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Enhancing Transformer Efficiency for Multivariate Time Series Classification

Most current multivariate time series (MTS) classification algorithms focus on improving the predictive accuracy. However, for large-scale (either high-dimensional or long-sequential) time series (TS) datasets, there is an additional consideration: to design an efficient network architecture to reduce computational costs such as training time and memory footprint. In this work we propose a methodology based on module-wise pruning and Pareto analysis to investigate the relationship between model efficiency and accuracy, as well as its complexity. Comprehensive experiments on benchmark MTS datasets illustrate the effectiveness of our method.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Integrating Physiological Time Series and Clinical Notes with Transformer for Early Prediction of Sepsis

Sepsis is a leading cause of death in the Intensive Care Units (ICU). Early detection of sepsis is critical for patient survival. In this paper, we propose a multimodal Transformer model for early sepsis prediction, using the physiological time series data and clinical notes for each patient within $36$ hours of ICU admission. Specifically, we aim to predict sepsis using only the first 12, 18, 24, 30 and 36 hours of laboratory measurements, vital signs, patient demographics, and clinical notes. We evaluate our model on two large critical care datasets: MIMIC-III and eICU-CRD. The proposed method is compared with six baselines. In addition, ablation analysis and case studies are conducted to study the influence of each individual component of the model and the contribution of each data modality for early sepsis prediction. Experimental results demonstrate the effectiveness of our method, which outperforms competitive baselines on all metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning

Secure multi-party computation enables multiple mutually distrusting parties to perform computations on data without revealing the data itself, and has become one of the core technologies behind privacy-preserving machine learning. In this work, we present several improved privacy-preserving protocols for both linear and non-linear layers in machine learning. For linear layers, we present an extended beaver triple protocol for bilinear maps that significantly reduces communication of convolution layer. For non-linear layers, we introduce novel protocols for computing the sigmoid and softmax function. Both functions are essential building blocks for machine learning training of classification tasks. Our protocols are both more scalable and robust than prior constructions, and improves runtime performance by 3-17x. Finally, we introduce Morse-STF, an end-to-end privacy-preserving system for machine learning training that leverages all these improved protocols. Our system achieves a 1.8x speedup on logistic regression and 3.9-4.9x speedup on convolutional neural networks compared to prior state-of-the-art systems.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Predicting the Need for Blood Transfusion in Intensive Care Units with Reinforcement Learning

As critically ill patients frequently develop anemia or coagulopathy, transfusion of blood products is a frequent intervention in the Intensive Care Units (ICU). However, inappropriate transfusion decisions made by physicians are often associated with increased risk of complications and higher hospital costs. In this work, we aim to develop a decision support tool that uses available patient information for transfusion decision-making on three common blood products (red blood cells, platelets, and fresh frozen plasma). To this end, we adopt an off-policy batch reinforcement learning (RL) algorithm, namely, discretized Batch Constrained Q-learning, to determine the best action (transfusion or not) given observed patient trajectories. Simultaneously, we consider different state representation approaches and reward design mechanisms to evaluate their impacts on policy learning. Experiments are conducted on two real-world critical care datasets: the MIMIC-III and the UCSF. Results demonstrate that policy recommendations on transfusion achieved comparable matching against true hospital policies via accuracy and weighted importance sampling evaluations on the MIMIC-III dataset. Furthermore, a combination of transfer learning (TL) and RL on the data-scarce UCSF dataset can provide up to $17.02% improvement in terms of accuracy, and up to 18.94% and 21.63% improvement in jump-start and asymptotic performance in terms of weighted importance sampling averaged over three transfusion tasks. Finally, simulations on transfusion decisions suggest that the transferred RL policy could reduce patients&#39; estimated 28-day mortality rate by 2.74% and decreased acuity rate by 1.18% on the UCSF dataset.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Frequency-Domain Quantum Interference with Correlated Photons from an Integrated Microresonator

Frequency encoding of quantum information together with fiber and integrated photonic technologies can significantly reduce the complexity and resource requirements for realizing all-photonic quantum networks. The key challenge for such frequency domain processing of single photons is to realize coherent and selective interactions between quantum optical fields of different frequencies over a range of bandwidths. Here, we report frequency-domain Hong-Ou-Mandel interference with spectrally distinct photons generated from a chip-based microresonator. We use four-wave mixing to implement an active frequency beam-splitter and achieve interference visibilities of $0.95 \pm 0.02$. Our work establishes four-wave mixing as a tool for selective high-fidelity two-photon operations in the frequency domain which, combined with integrated single-photon sources, provides a building block for frequency-multiplexed photonic quantum networks.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Nanophotonic spin-glass for realization of a coherent Ising machine

The need for solving optimization problems is prevalent in a wide range of physical applications, including neuroscience, network design, biological systems, socio-economics, and chemical reactions. Many of these are classified as non-deterministic polynomial-time (NP) hard and thus become intractable to solve as the system scales to a large number of elements. Recent research advances in photonics have sparked interest in using a network of coupled degenerate optical parametric oscillators (DOPO&#39;s) to effectively find the ground state of the Ising Hamiltonian, which can be used to solve other combinatorial optimization problems through polynomial-time mapping. Here, using the nanophotonic silicon-nitride platform, we propose a network of on-chip spatial-multiplexed DOPO&#39;s for the realization of a photonic coherent Ising machine. We demonstrate the generation and coupling of two microresonator-based DOPO&#39;s on a single chip. Through a reconfigurable phase link, we achieve both in-phase and out-of-phase operation, which can be deterministically achieved at a fast regeneration speed of 400 kHz with a large phase tolerance. Our work provides the critical building blocks towards the realization of a chip-scale photonic Ising machine.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Near-degenerate quadrature-squeezed vacuum generation on a silicon-nitride chip

Squeezed states are a primary resource for continuous-variable (CV) quantum information processing. To implement CV protocols in a scalable and robust way, it is desirable to generate and manipulate squeezed states using an integrated photonics platform. In this Letter, we demonstrate the generation of quadrature-phase squeezed states in the radio-frequency carrier sideband using a small-footprint silicon-nitride microresonator with a dual-pumped four-wave-mixing process. We record a squeezed noise level of 1.34 dB ($\pm$0.16 dB) below the photocurrent shot noise, which corresponds to 3.09 dB ($\pm$0.49 dB) of quadrature squeezing on chip. We also show that it is critical to account for the nonlinear behavior of the pump fields to properly predict the squeezing that can be generated in this system. This technology represents a significant step toward creating and manipulating large-scale CV cluster states that can be used for quantum information applications including universal quantum computing.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Scalable Bayesian Functional Connectivity Inference for Multi-Electrode Array Recordings

Multi-electrode arrays (MEAs) can record extracellular action potentials (also known as &#39;spikes&#39;) from hundreds or thousands of neurons simultaneously. Inference of a functional network from a spike train is a fundamental and formidable computational task in neuroscience. With the advancement of MEA technology, it has become increasingly crucial to develop statistical tools for analyzing multiple neuronal activity as a network. In this paper, we propose a scalable Bayesian framework for inference of functional networks from MEA data. Our framework makes use of the hierarchical structure of networks of neurons. We split the large scale recordings into smaller local networks for network inference, which not only eases the computational burden from Bayesian sampling but also provides useful insights on regional connections in organoids and brains. We speed up the expensive Bayesian sampling process by using parallel computing. Experiments on both synthetic datasets and large-scale real-world MEA recordings show the effectiveness and efficiency of the scalable Bayesian framework. Inference of networks from controlled experiments exposing neural cultures to cadmium presents distinguishable results and further confirms the utility of our framework.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Visible nonlinear photonics via high-order-mode dispersion engineering

Over the past decade, remarkable advances have been realized in chip-based nonlinear photonic devices for classical and quantum applications in the near- and mid-infrared regimes. However, few demonstrations have been realized in the visible and near-visible regimes, primarily due to the large normal material group-velocity dispersion (GVD) that makes it challenging to phase match third-order parametric processes. In this paper, we show that exploiting dispersion engineering of higher-order waveguide modes provides waveguide dispersion that allows for small or anomalous GVD in the visible and near-visible regimes and phase matching of four-wave mixing processes. We illustrate the power of this concept by demonstrating in silicon nitride microresonators a near-visible modelocked Kerr frequency comb and a narrow-band photon-pair source compatible with Rb transitions. These realizations extend applications of nonlinear photonics towards the visible and near-visible regimes for applications in time and frequency metrology, spectral calibration, quantum information, and biomedical applications.

0 citations0 reviewsNo code linkedOpen access