arXiv subjects

Bo Wang

Publications and source records attributed to Bo Wang.

At least 451 records · Page 25Linked to original sources

arXiv2024

Integrate Any Omics: Towards genome-wide data integration for patient stratification

High-throughput omics profiling advancements have greatly enhanced cancer patient stratification. However, incomplete data in multi-omics integration presents a significant challenge, as traditional methods like sample exclusion or imputation often compromise biological diversity and dependencies. Furthermore, the critical task of accurately classifying new patients with partial omics data into existing subtypes is commonly overlooked. To address these issues, we introduce IntegrAO (Integrate Any Omics), an unsupervised framework for integrating incomplete multi-omics data and classifying new samples. IntegrAO first combines partially overlapping patient graphs from diverse omics sources and utilizes graph neural networks to produce unified patient embeddings. Our systematic evaluation across five cancer cohorts involving six omics modalities demonstrates IntegrAO's robustness to missing data and its accuracy in classifying new samples with partial profiles. An acute myeloid leukemia case study further validates its capability to uncover biological and clinical heterogeneity in incomplete datasets. IntegrAO's ability to handle heterogeneous and incomplete data makes it an essential tool for precision oncology, offering a holistic approach to patient characterization.

q-bio.GN↗

arXiv2024

Lightweight Full-Convolutional Siamese Tracker

Although single object trackers have achieved advanced performance, their large-scale models hinder their application on limited resources platforms. Moreover, existing lightweight trackers only achieve a balance between 2-3 points in terms of parameters, performance, Flops and FPS. To achieve the optimal balance among these points, this paper proposes a lightweight full-convolutional Siamese tracker called LightFC. LightFC employs a novel efficient cross-correlation module (ECM) and a novel efficient rep-center head (ERH) to improve the feature representation of the convolutional tracking pipeline. The ECM uses an attention-like module design, which conducts spatial and channel linear fusion of fused features and enhances the nonlinearity of the fused features. Additionally, it refers to successful factors of current lightweight trackers and introduces skip-connections and reuse of search area features. The ERH reparameterizes the feature dimensional stage in the standard center-head and introduces channel attention to optimize the bottleneck of key feature flows. Comprehensive experiments show that LightFC achieves the optimal balance between performance, parameters, Flops and FPS. The precision score of LightFC outperforms MixFormerV2-S on LaSOT and TNL2K by 3.7 % and 6.5 %, respectively, while using 5x fewer parameters and 4.6x fewer Flops. Besides, LightFC runs 2x faster than MixFormerV2-S on CPUs. In addition, a higher-performance version named LightFC-vit is proposed by replacing a more powerful backbone network. The code and raw results can be found at https://github.com/LiYunfengLYF/LightFC.

cs.CV↗

arXiv2024

ConvConcatNet: a deep convolutional neural network to reconstruct mel spectrogram from the EEG

To investigate the processing of speech in the brain, simple linear models are commonly used to establish a relationship between brain signals and speech features. However, these linear models are ill-equipped to model a highly dynamic and complex non-linear system like the brain. Although non-linear methods with neural networks have been developed recently, reconstructing unseen stimuli from unseen subjects' EEG is still a highly challenging task. This work presents a novel method, ConvConcatNet, to reconstruct mel-specgrams from EEG, in which the deep convolution neural network and extensive concatenation operation were combined. With our ConvConcatNet model, the Pearson correlation between the reconstructed and the target mel-spectrogram can achieve 0.0420, which was ranked as No.1 in the Task 2 of the Auditory EEG Challenge. The codes and models to implement our work will be available on Github: https://github.com/xuxiran/ConvConcatNet

eess.SP↗

arXiv2024

Primordial black hole mass functions as a probe of cosmic origin

We discuss a novel window to probe the origin of our universe via the mass functions of primordial black holes (PBHs). The mass functions of PBHs are simply estimated using the conventional Press-Schechter formalism for two paradigms of cosmic origin, including inflationary $Λ$CDM and bounce cosmology. The standard inflationary $Λ$CDM model cannot generate an appreciable number of massive PBHs; however, non-trivial inflation models with blue-tilted power spectra at small scales and matter bounce cosmology provide formation mechanisms for heavy PBHs, which in turn, may seed the observed supermassive black holes (SMBHs). By fitting the SMBH mass functions at high redshift ($z \sim 6$) derived from Sloan Digital Sky Survey (SDSS) and Canada-France High-z Quasar Survey (CFHQS) quasars, for two paradigms of cosmic origin, we derive constraints on the PBH density fraction $f_{\mathrm{PBH}}$ at $z \sim 6$ and the characteristic mass $M_{\star}$, with the prior assumption that all SMBHs stem from PBHs. We demonstrate that this newly proposed procedure, relying on astronomical measurements that utilize deep-field surveys of SMBHs at high redshift, can be used to constrain models of cosmic origin. Additionally, although not the main focus of this paper, we evolve the mass function from $z\sim6$ to $z\sim0$ through an assumption of $3\times 10^8$-year Eddington's accretion, and give a rough estimation of $f_{\mathrm{PBH}}$ at $z \sim 0$.

astro-ph.CO↗

arXiv2024

U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation

Convolutional Neural Networks (CNNs) and Transformers have been the most popular architectures for biomedical image segmentation, but both of them have limited ability to handle long-range dependencies because of inherent locality or computational complexity. To address this challenge, we introduce U-Mamba, a general-purpose network for biomedical image segmentation. Inspired by the State Space Sequence Models (SSMs), a new family of deep sequence models known for their strong capability in handling long sequences, we design a hybrid CNN-SSM block that integrates the local feature extraction power of convolutional layers with the abilities of SSMs for capturing the long-range dependency. Moreover, U-Mamba enjoys a self-configuring mechanism, allowing it to automatically adapt to various datasets without manual intervention. We conduct extensive experiments on four diverse tasks, including the 3D abdominal organ segmentation in CT and MR images, instrument segmentation in endoscopy images, and cell segmentation in microscopy images. The results reveal that U-Mamba outperforms state-of-the-art CNN-based and Transformer-based segmentation networks across all tasks. This opens new avenues for efficient long-range dependency modeling in biomedical image analysis. The code, models, and data are publicly available at https://wanglab.ai/u-mamba.html.

eess.IV↗

arXiv2024

PTE: Axiomatic Semantics based Compiler Testing

The correctness of a compiler affects the correctness of every program written in the language, and thus must be thoroughly evaluated. Existing automatic compiler testing methods however either rely on weak oracles (e.g., a program behaves the same if only dead code is modified), or require substantial initial effort (e.g., having a complete operational language semantics). While the former prevents a comprehensive correctness evaluation, the latter makes those methods irrelevant in practice. In this work, we propose an axiomatic semantics based approach for testing compilers, called PTE. The idea is to incrementally develop a set of ``axioms'' capturing anecdotes of the language semantics in the form of \emph{(\textbf{p}recondition, \textbf{t}ransformation, \textbf{e}xpectation) triples, which allows us to test the compiler automatically.} Such axioms are written in the same language whose compiler is under test, and can be developed either based on the language specification, or by generalizing the bug reports. PTE has been applied to a newly developed compiler (i.e., Cangjie) and a mature compiler (i.e., Java), and successfully identified 42 implementation bugs and 9 potential language design issues.

cs.SE↗

arXiv2023

Spectrum of the molecular tetraquarks: Unraveling the $T_{cs0}(2900)$ and $T_{c\bar{s}0}^a(2900)$

We relate the interactions of the $\bar{D}^{(\ast)} K^\ast$ and $D^{(\ast)} K^\ast$ systems to those of $D^{(\ast)}D^{(\ast)}$ and $D^{(\ast)}\bar{D}^{(\ast)}$ respectively, considering the residual strong interactions at the near-threshold energy is too weak to excite the strange quarks inside the hadrons. We propose an effective model to describe the low-energy S-wave interactions that are undertaken by the light $u$, $d$ quarks between two separated heavy hadrons. We find that the existence of molecules in the heavy-(anti)heavy sectors will naturally lead to the emergence of molecular states in $\bar{D}^{(\ast)} K^\ast$ and $D^{(\ast)} K^\ast$ systems. The recently observed $T_{cs0}(2900)$ and $T_{c\bar{s}0}^a(2900)$ can be well identified as the $0(0^+)$ and $1(0^+)$ partners of $T_{cc}(3875)$ and $Z_c(3900)$ in the charmed strange sector, respectively. We also predict their members under the {\it heavy} ($c$ and $s$) quark symmetry and SU(2) flavor symmetry. Most of them are very good molecule candidates, for example, (i) the $0(1^+)$ states in $D^\ast D^\ast$, $\bar{D}K^\ast$, $\bar{D}^\ast K^\ast$; (ii) the $0^{(+)}(2^{+(+)})$ states in $D^\ast \bar{D}^\ast$, $\bar{D}^\ast K^\ast$, $D^\ast K^\ast$; (iii) the $1^-(0^{++})$ state in $D^\ast\bar{D}^\ast$ and $1(1^+)$ state in $D^\ast K^\ast$. The $0^+(0^{++})$ state in $D\bar{D}$ and the $0(1^+)$ state in $DK^\ast$ might also exist as virtual states, and the $0(1^+)$ $DK^\ast$ can serve as a key to infer the existence of $0^+(0^{++})$ $D\bar{D}$. The $D_sπ$ invariant mass spectrum of $T_{c\bar{s}0}^a(2900)$ is also studied within the coupled-channel approach, and the molecular interpretation of $T_{c\bar{s}0}^a(2900)$ is consistent with the experimental data. Searching for the predicted states in experiments is crucial to discriminate the different pictures for interpreting these near-threshold exotica.

hep-ph↗

arXiv2023

A Longitudinal Multi-modal Dataset for Dementia Monitoring and Diagnosis

Dementia affects cognitive functions of adults, including memory, language, and behaviour. Standard diagnostic biomarkers such as MRI are costly, whilst neuropsychological tests suffer from sensitivity issues in detecting dementia onset. The analysis of speech and language has emerged as a promising and non-intrusive technology to diagnose and monitor dementia. Currently, most work in this direction ignores the multi-modal nature of human communication and interactive aspects of everyday conversational interaction. Moreover, most studies ignore changes in cognitive status over time due to the lack of consistent longitudinal data. Here we introduce a novel fine-grained longitudinal multi-modal corpus collected in a natural setting from healthy controls and people with dementia over two phases, each spanning 28 sessions. The corpus consists of spoken conversations, a subset of which are transcribed, as well as typed and written thoughts and associated extra-linguistic information such as pen strokes and keystrokes. We present the data collection process and describe the corpus in detail. Furthermore, we establish baselines for capturing longitudinal changes in language across different modalities for two cohorts, healthy controls and people with dementia, outlining future research directions enabled by the corpus.

cs.CL↗

arXiv2023

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets

One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes and their products that control gene expression and cellular function. We can treat this as a causal discovery problem but with two non-standard challenges: (1) regulatory networks are inherently cyclic so we should not model a GRN as a directed acyclic graph (DAG), and (2) observations have significant measurement noise, so for typical sample sizes there will always be a large equivalence class of graphs that are likely given the data, and we want methods that capture this uncertainty. Existing methods either focus on challenge (1), identifying cyclic structure from dynamics, or on challenge (2) learning complex Bayesian posteriors over DAGs, but not both. In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges. Because we have access to velocity information, we can treat the Bayesian structure learning problem as a problem of sparse identification of a dynamical system, capturing cyclic feedback loops through time. Since our objective is to model uncertainty over discrete structures, we leverage Generative Flow Networks (GFlowNets) to estimate the posterior distribution over the combinatorial space of possible sparse dependencies. Our results indicate that our method learns posteriors that better encapsulate the distributions of cyclic structures compared to counterpart state-of-the-art Bayesian structure learning approaches.

cs.LG↗

arXiv2023

Generative Pretraining at Scale: Transformer-Based Encoding of Transactional Behavior for Fraud Detection

In this work, we introduce an innovative autoregressive model leveraging Generative Pretrained Transformer (GPT) architectures, tailored for fraud detection in payment systems. Our approach innovatively confronts token explosion and reconstructs behavioral sequences, providing a nuanced understanding of transactional behavior through temporal and contextual analysis. Utilizing unsupervised pretraining, our model excels in feature representation without the need for labeled data. Additionally, we integrate a differential convolutional approach to enhance anomaly detection, bolstering the security and efficacy of one of the largest online payment merchants in China. The scalability and adaptability of our model promise broad applicability in various transactional contexts.

cs.LG↗

arXiv2023

Few-Shot Learning from Augmented Label-Uncertain Queries in Bongard-HOI

Detecting human-object interactions (HOI) in a few-shot setting remains a challenge. Existing meta-learning methods struggle to extract representative features for classification due to the limited data, while existing few-shot HOI models rely on HOI text labels for classification. Moreover, some query images may display visual similarity to those outside their class, such as similar backgrounds between different HOI classes. This makes learning more challenging, especially with limited samples. Bongard-HOI (Jiang et al. 2022) epitomizes this HOI few-shot problem, making it the benchmark we focus on in this paper. In our proposed method, we introduce novel label-uncertain query augmentation techniques to enhance the diversity of the query inputs, aiming to distinguish the positive HOI class from the negative ones. As these augmented inputs may or may not have the same class label as the original inputs, their class label is unknown. Those belonging to a different class become hard samples due to their visual similarity to the original ones. Additionally, we introduce a novel pseudo-label generation technique that enables a mean teacher model to learn from the augmented label-uncertain inputs. We propose to augment the negative support set for the student model to enrich the semantic information, fostering diversity that challenges and enhances the student's learning. Experimental results demonstrate that our method sets a new state-of-the-art (SOTA) performance by achieving 68.74% accuracy on the Bongard-HOI benchmark, a significant improvement over the existing SOTA of 66.59%. In our evaluation on HICO-FS, a more general few-shot recognition dataset, our method achieves 73.27% accuracy, outperforming the previous SOTA of 71.20% in the 5-way 5-shot task.

cs.CV↗

arXiv2023

Random resistive memory-based deep extreme point learning machine for unified visual processing

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent machines is crucial for numerous emerging edge applications, such as augmented and virtual reality and unmanned aerial vehicles, which necessitates unified data representation, unprecedented hardware energy efficiency and rapid model training. However, multi-sensory data are intrinsically heterogeneous, causing significant complexity in the system development for edge-side intelligent machines. In addition, the performance of conventional digital hardware is limited by the physically separated processing and memory units, known as the von Neumann bottleneck, and the physical limit of transistor scaling, which contributes to the slowdown of Moore's law. These limitations are further intensified by the tedious training of models with ever-increasing sizes. We propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM), that offers efficient unified point set analysis. We show the system's versatility across various data modalities and two different learning tasks. Compared to a conventional digital hardware-based system, our co-design system achieves huge energy efficiency improvements and training cost reduction when compared to conventional systems. Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.

cs.LG↗

arXiv2023

Metric results for the eventually always hitting points and level sets in subshift with specification

We study the set of eventually always hitting points for symbolic dynamics with specification. The measure and Hausdorff dimension of such sets are obtained. Moreover, we establish the stronger metric results by introducing a new quantity L_{N}(ω) which describes the maximal length of string of zreos of the prefix among the first N iterations of ω in symbolic space. The Hausdorff dimensions of the level sets for this quantity are also completely determined.

math.DS↗

arXiv2023

Fully Dynamic Algorithms for Euclidean Steiner Tree

The Euclidean Steiner tree problem asks to find a min-cost metric graph that connects a given set of \emph{terminal} points $X$ in $\mathbb{R}^d$, possibly using points not in $X$ which are called Steiner points. Even though near-linear time $(1 + ε)$-approximation was obtained in the offline setting in seminal works of Arora and Mitchell, efficient dynamic algorithms for Steiner tree is still open. We give the first algorithm that (implicitly) maintains a $(1 + ε)$-approximate solution which is accessed via a set of tree traversal queries, subject to point insertion and deletions, with amortized update and query time $O(\poly\log n)$ with high probability. Our approach is based on an Arora-style geometric dynamic programming, and our main technical contribution is to maintain the DP subproblems in the dynamic setting efficiently. We also need to augment the DP subproblems to support the tree traversal queries.

cs.CG↗

arXiv2023

Black Hole Ultracompact X-Ray Binaries as Galactic Low-frequency Gravitational Wave Sources: the He Star Channel

Black hole (BH) ultracompact X-ray binaries (UCXBs) are potential Galactic low-frequency gravitational wave (GW) sources. As an alternative channel, BH UCXBs can evolve from BH+He star binaries. In this work, we perform a detailed stellar evolution model for the formation and evolution of BH UCXBs evolving from the He star channel to diagnose their detectability as low-frequency GW sources. Our calculations found that some nascent BH+He star binaries after the common-envelope (CE) phase could evolve into UCXB-LISA sources with a maximum GW frequency of $\sim5~\rm mHz$, which can be detected in a distance of 10 kpc (or 100 kpc). Once BH+He star systems become UCXBs through mass transfer, they would emit X-ray luminosities of $\sim10^{38}~\rm erg\, s^{-1}$, making them ideal multimessenger objects. If the initial He-star masses are $\geq 0.7 M_{\odot}$, those systems are likely to experience two Roche lobe overflows, and the X-ray luminosity can reach a maximum of $3.5\times 10^{39}~\rm erg\, s^{-1}$ in the second mass-transfer stage. The initial He-star masses and initial orbital periods of progenitors of Galactic BH UCXB-LISA sources are in the range of 0.32-2.9 $M_{\odot}$ and 0.02-0.19 days, respectively. Nearly all BH+He star binaries in the above parameter space can evolve into GW sources whose chirp masses can be accurately measured. Employing a population synthesis simulation, we predict the birthrate and detection number of Galactic BH UCXB-LISA source evolving from the He star channel are $R=2.2\times10^{-6}~\rm yr^{-1}$ and 33 for an optimistic CE parameter, respectively.

astro-ph.HE↗

arXiv2023

The He star donor channel towards the black widow PSR J1953+1844

Black widows (BWs) are a type of eclipsing millisecond pulsars (MSPs) with low companion masses ($\lesssim0.05\,\rm M_\odot$) and tight orbits ($<1\,$d). PSR J1953+1844 is a BW with the shortest orbital period ($\sim53$ minutes) ever discovered, which was recently detected by Five-hundred-meter Aperture Spherical radio Telescope. Its companion mass is $\sim0.01\,\rm M_\odot$ according to its mass function, indicating that the companion may be a hydrogen-deficient star. However, the origin of PSR J1953+1844 is highly unclear. In this paper, we explored the origin of PSR J1953+1844 through the neutron star+He star channel, in which the system can experience ultracompact X-ray binary phase. We found that the He star donor channel can reproduce the characteristics of PSR J1953+1844, indicating that this work provides an alternative formation channel for this source. Meanwhile, the minimum orbital period of BWs formed by this channel is $\sim28$ minutes, corresponding to the companion mass of $0.058\,\rm M_\odot$. In addition, we note that even though PSR J1953+1844 has a short orbital period, it cannot be detected by the gravitational wave (GW) observatories like Laser Interferometer Space Antenna, TaiJi and TianQin. However, we still expect that the BWs with extremely tight orbit produced by this channel are the potential sources of future space-based GW observatories. Moreover, our simulations show that PSR J1953+1844 may eventually evolve into an isolated MSP.

astro-ph.HE↗

arXiv2023

Preliminary Design of CSNS-II Linac SRF LLRF

China Spallation Neutron Source(CSNS) target power will upgrade to 500 kW(CSNS-II) from 300kW, energy gain of H-Linac will up to 300 MeV from 80 MeV using about 50 superconductor cavities. LLRF is an important device for controlling the amplitude and phase of the SRF cavity field to be less than 0.6% and 0.6 deg. The parameters and requirements for CSNS-II Linac LLRF are presented here. The preliminary design work and algorithm verification progress and results at C-ADS Injector-I are introduced.

physics.acc-ph↗

arXiv2023

GPT-4V(ision) Unsuitable for Clinical Care and Education: A Clinician-Evaluated Assessment

OpenAI's large multimodal model, GPT-4V(ision), was recently developed for general image interpretation. However, less is known about its capabilities with medical image interpretation and diagnosis. Board-certified physicians and senior residents assessed GPT-4V's proficiency across a range of medical conditions using imaging modalities such as CT scans, MRIs, ECGs, and clinical photographs. Although GPT-4V is able to identify and explain medical images, its diagnostic accuracy and clinical decision-making abilities are poor, posing risks to patient safety. Despite the potential that large language models may have in enhancing medical education and delivery, the current limitations of GPT-4V in interpreting medical images reinforces the importance of appropriate caution when using it for clinical decision-making.

cs.CV↗