arXiv subjects

Jingpeng Wu

Publications and source records attributed to Jingpeng Wu.

11 recordsLinked to original sources

arXiv2026

EasyBCI Agent: Towards Universal Neural Data Preprocessing for Brain-Computer Interfaces

Brain-computer interfaces translate neural activity into device commands, yet their performance hinges on preprocessing that remains manual, expert-dependent and poorly reproducible. Large language model agents can automate scientific coding, but existing systems lack the modality coverage, raw-data isolation, experience accumulation and domain oversight that neural preprocessing requires. We introduce EasyBCI, a two-phase LLM agent that plans and executes preprocessing pipelines for six signal types. A Plan Agent profiles each recording into a text-only Data Fingerprint that never exposes raw data to the model and selects a literature-grounded operator sequence. An Execution Agent generates, runs and self-corrects code until quality criteria are met, while a quality-gated experience system retains validated strategies as reusable skills. A domain expert intervenes at two decision gates, retaining human judgement where undetected error can invalidate downstream analyses. Evaluation on EEG with a fixed linear classifier shows that all five EasyBCI backbones preserve more task-relevant separability than the manual pipeline. Under same-backbone comparison, EasyBCI outperforms general-purpose coding agents on both label schemes for four of five configurations. EasyBCI extends to five additional modalities spanning nearly three orders of magnitude in sampling rate, producing complete reproducible pipelines with recorded decision provenance. These results indicate that domain-specific orchestration can bring auditable preprocessing within reach of laboratories lacking dedicated expertise, illustrating design principles applicable to AI agents in other scientific domains.

q-bio.QM↗

arXiv2026

The Plasma-Charge Model: Boundary Effects and Global Well-posedness

This article focuses on the Vlasov-Poisson system with point charges in bounded convex domains, accounting the interactions of point charges with the self-consistent electric field and the boundary, which were not addressed in the previous work \cite{Wu24}. We provide a rigorous characterization of the charge-boundary effect and establish the global well-posedness of the associated initial-boundary value problems under various boundary conditions. The analysis rests upon delicate estimates of the Green and Robin functions in convex domains, the Pfaffelmoser and Lions-Perthame methods for global well-posedness, and a desingularization argument that justifies the point-charge dynamics.

math.AP↗

arXiv2024

The gyrokinetic limit for the two dimensional Vlasov-Poisson system with multi-point charges

In this article, we investigate the gyrokinetic limit for the two dimensional Vlasov-Poisson system with multi-point charges. We show that the solution converges to a measure-valued solution of the Euler equation with a defect measure, which extends the results of Miot (Nonlinearity 32(2):654-677, 2019) to the case of multi-point charges and removes the smallness condition $\sup_{0<\varepsilon<1}\|f_{\varepsilon}^0\|_{L^1}<1$. The main difficulty arises from the fact that the orbits of point charges will intersect frequently and rapidly as the magnetic field intensity becomes large. To overcome the problem, we adopt the techniques recently developed by Wu and Zhang (Journal of Statistical Physics 190:183, 2023) combined with a new technique introduced here.

math.AP↗

arXiv2024

TriSAM: Tri-Plane SAM for zero-shot cortical blood vessel segmentation in VEM images

While imaging techniques at macro and mesoscales have garnered substantial attention and resources, microscale Volume Electron Microscopy (vEM) imaging, capable of revealing intricate vascular details, has lacked the necessary benchmarking infrastructure. In this paper, we address a significant gap in this field of neuroimaging by introducing the first-in-class public benchmark, BvEM, designed specifically for cortical blood vessel segmentation in vEM images. Our BvEM benchmark is based on vEM image volumes from three mammals: adult mouse, macaque, and human. We standardized the resolution, addressed imaging variations, and meticulously annotated blood vessels through semi-automatic, manual, and quality control processes, ensuring high-quality 3D segmentation. Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation. To extend SAM from 2D to 3D volume segmentation, TriSAM employs a multi-seed tracking framework, leveraging the reliability of certain image planes for tracking while using others to identify potential turning points. This approach effectively achieves long-term 3D blood vessel segmentation without model training or fine-tuning. Experimental results show that TriSAM achieved superior performances on the BvEM benchmark across three species. Our dataset, code, and model are available online at \url{https://jia-wan.github.io/bvem}.

cs.CV↗

arXiv2023

On the non-uniqueness of transport equation: the quantitative relationship between temporal and spatial regularity

In this paper, we consider the non-uniqueness of transport equation on the torus $\mathbb{T}^d$, with density $ρ\in L^{s}_tL_x^{p}$ and divergence-free vector field $\boldsymbol{u}\in L^{s'}_tL_x^{p'}\cap L^{\tilde{s}}_tW_x^{1,\tilde{p}}$. We prove that the non-uniqueness holds for $\frac{1}{p}+\frac{\tilde{s}'}{s\tilde{p}}>1+\frac{1}{d-1}$, with $d\ge 2$ and $s,p,\tilde{p}\in[1,\infty)$, $1\le\tilde{s}<s'$. The result can be extended to the transport-diffusion equation with diffusion operator of order $k$ in the class $ρ\in L^{s}_tL_x^{p}\cap L_t^{\bar{s}}C_x^{\bar{m}}$, $\boldsymbol{u}\in L^{s'}_tL_x^{p'}\cap L^{\tilde{s}}_tW_x^{1,\tilde{p}}$, under some conditions on $\bar{s},\bar{m},k$. In particular, when $\tilde{s}=1$, the additional condition is $\bar{m}<\frac{s}{\bar{s}}-1$, $k<\frac{s}{s'}+1$. These results can be considered as quantitative versions of Cheskidov and Luo's [Ann. PDE, 2021]. The main tool is the convex integration developed by Modena-Sattig-Székelyhidi [Ann. PDE, 2018; Calc. Var. Partial Differ. Equ., 2019; Annales de l'Institut Henri Poincaré C, Analyse non linèaire, 2020] and Cheskidov-Luo [Ann. PDE, 2021; arXiv, 2022 (forthcoming in Anal. PDE, 2023)].

math.AP↗

arXiv2023

Non-uniqueness of the transport equation at high spacial integrability

In this paper, we show the non-uniqueness of the weak solution in the class $ρ\in L^{s}_tL^p_x$ for the transport equation driven by a divergence-free vector field $\boldsymbol{u}\in L^{\tilde{s}}_tW^{1,q}_x\cap L_t^{s'}L_x^{p'}$ happens in the range $1/p+1/q>1-\frac{p-1}{4(p+1)p}$ with some $\tilde{s}>1$, as long as $1\le s<\infty$, $p>1$. As a corollary, $L^{\infty}$ in time of the density $ρ$ is critical in some sense for the uniqueness of weak solution. Our proof is based on the convex integration method developed in [Modena and Sattig, 2020, Ann. Inst. H. Poincaré C Anal. Non Linéaire], [Cheskidov and Luo, 2021, Ann. PDE].

math.AP↗

arXiv2023

An Out-of-Domain Synapse Detection Challenge for Microwasp Brain Connectomes

The size of image stacks in connectomics studies now reaches the terabyte and often petabyte scales with a great diversity of appearance across brain regions and samples. However, manual annotation of neural structures, e.g., synapses, is time-consuming, which leads to limited training data often smaller than 0.001\% of the test data in size. Domain adaptation and generalization approaches were proposed to address similar issues for natural images, which were less evaluated on connectomics data due to a lack of out-of-domain benchmarks.

cs.CV↗

arXiv2021

Bridging the Gap: Point Clouds for Merging Neurons in Connectomics

In the field of Connectomics, a primary problem is that of 3D neuron segmentation. Although deep learning-based methods have achieved remarkable accuracy, errors still exist, especially in regions with image defects. One common type of defect is that of consecutive missing image sections. Here, data is lost along some axis, and the resulting neuron segmentations are split across the gap. To address this problem, we propose a novel method based on point cloud representations of neurons. We formulate the problem as a classification problem and train CurveNet, a state-of-the-art point cloud classification model, to identify which neurons should be merged. We show that our method not only performs strongly but also scales reasonably to gaps well beyond what other methods have attempted to address. Additionally, our point cloud representations are highly efficient in terms of data, maintaining high performance with an amount of data that would be unfeasible for other methods. We believe that this is an indicator of the viability of using point cloud representations for other proofreading tasks.

cs.CV↗

arXiv2019

Synaptic Partner Assignment Using Attentional Voxel Association Networks

Connectomics aims to recover a complete set of synaptic connections within a dataset imaged by volume electron microscopy. Many systems have been proposed for locating synapses, and recent research has included a way to identify the synaptic partners that communicate at a synaptic cleft. We re-frame the problem of identifying synaptic partners as directly generating the mask of the synaptic partners from a given cleft. We train a convolutional network to perform this task. The network takes the local image context and a binary mask representing a single cleft as input. It is trained to produce two binary output masks: one which labels the voxels of the presynaptic partner within the input image, and another similar labeling for the postsynaptic partner. The cleft mask acts as an attentional gating signal for the network. We find that an implementation of this approach performs well on a dataset of mouse somatosensory cortex, and evaluate it as part of a combined system to predict both clefts and connections.

cs.CV↗

arXiv2019

Chunkflow: Distributed Hybrid Cloud Processing of Large 3D Images by Convolutional Nets

It is now common to process volumetric biomedical images using 3D Convolutional Networks (ConvNets). This can be challenging for the teravoxel and even petavoxel images that are being acquired today by light or electron microscopy. Here we introduce chunkflow, a software framework for distributing ConvNet processing over local and cloud GPUs and CPUs. The image volume is divided into overlapping chunks, each chunk is processed by a ConvNet, and the results are blended together to yield the output image. The frontend submits ConvNet tasks to a cloud queue. The tasks are executed by local and cloud GPUs and CPUs. Thanks to the fault-tolerant architecture of Chunkflow, cost can be greatly reduced by utilizing cheap unstable cloud instances. Chunkflow currently supports PyTorch for GPUs and PZnet for CPUs. To illustrate its usage, a large 3D brain image from serial section electron microscopy was processed by a 3D ConvNet with a U-Net style architecture. Chunkflow provides some chunk operations for general use, and the operations can be composed flexibly in a command line interface.

cs.DC↗

arXiv2019

Convolutional nets for reconstructing neural circuits from brain images acquired by serial section electron microscopy

Neural circuits can be reconstructed from brain images acquired by serial section electron microscopy. Image analysis has been performed by manual labor for half a century, and efforts at automation date back almost as far. Convolutional nets were first applied to neuronal boundary detection a dozen years ago, and have now achieved impressive accuracy on clean images. Robust handling of image defects is a major outstanding challenge. Convolutional nets are also being employed for other tasks in neural circuit reconstruction: finding synapses and identifying synaptic partners, extending or pruning neuronal reconstructions, and aligning serial section images to create a 3D image stack. Computational systems are being engineered to handle petavoxel images of cubic millimeter brain volumes.

cs.CV↗