arXiv subjects

Yang Chen

Publications and source records attributed to Yang Chen.

At least 397 records · Page 22Linked to original sources

arXiv2023

Large Language Models Illuminate a Progressive Pathway to Artificial Healthcare Assistant: A Review

With the rapid development of artificial intelligence, large language models (LLMs) have shown promising capabilities in mimicking human-level language comprehension and reasoning. This has sparked significant interest in applying LLMs to enhance various aspects of healthcare, ranging from medical education to clinical decision support. However, medicine involves multifaceted data modalities and nuanced reasoning skills, presenting challenges for integrating LLMs. This paper provides a comprehensive review on the applications and implications of LLMs in medicine. It begins by examining the fundamental applications of general-purpose and specialized LLMs, demonstrating their utilities in knowledge retrieval, research support, clinical workflow automation, and diagnostic assistance. Recognizing the inherent multimodality of medicine, the review then focuses on multimodal LLMs, investigating their ability to process diverse data types like medical imaging and EHRs to augment diagnostic accuracy. To address LLMs' limitations regarding personalization and complex clinical reasoning, the paper explores the emerging development of LLM-powered autonomous agents for healthcare. Furthermore, it summarizes the evaluation methodologies for assessing LLMs' reliability and safety in medical contexts. Overall, this review offers an extensive analysis on the transformative potential of LLMs in modern medicine. It also highlights the pivotal need for continuous optimizations and ethical oversight before these models can be effectively integrated into clinical practice. Visit https://github.com/mingze-yuan/Awesome-LLM-Healthcare for an accompanying GitHub repository containing latest papers.

cs.CL↗

arXiv2023

Reducing the impact of non-ideal PRBS on microwave photonic random demodulators by low biasing the optical modulator via PRBS amplitude compression

A novel method for reducing the impact of non-ideal pseudo-random binary sequence (PRBS) on microwave photonic random demodulators (RDs) in a photonics-assisted compressed sensing (CS) system is proposed. Different from the commonly used method that switches the bias point of the optical modulator in the RD between two quadrature transmission points to mix the signal to be sampled and the PRBS, this method employs a PRBS with lower amplitude to low bias the optical modulator so that the impact of non-ideal PRBS on microwave photonic RDs can be greatly reduced by compressing the amplitude of non-ideal parts of the PRBS. An experiment is performed to verify the concept. The optical modulator is properly low-biased via PRBS amplitude compression. The data rate and occupied bandwidth of the PRBS are 500 Mb/s and 1 GHz, while the multi-tone signals with a maximum frequency of 100 MHz are sampled at an equivalent sampling rate of only 50 MSa/s. The results show that the reconstruction error can be reduced by up to 85%. The proposed method can significantly reduce the requirements for PRBS in RD-based photonics-assisted CS systems, providing a feasible solution for reducing the complexity and cost of system implementation.

eess.SP↗

arXiv2023

Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks

Hypergraph Neural Networks (HGNNs) have been successfully applied in various hypergraph-related tasks due to their excellent higher-order representation capabilities. Recent works have shown that deep learning models are vulnerable to adversarial attacks. Most studies on graph adversarial attacks have focused on Graph Neural Networks (GNNs), and the study of adversarial attacks on HGNNs remains largely unexplored. In this paper, we try to reduce this gap. We design a new HGNNs attack model for the untargeted attack, namely MGHGA, which focuses on modifying node features. We consider the process of HGNNs training and use a surrogate model to implement the attack before hypergraph modeling. Specifically, MGHGA consists of two parts: feature selection and feature modification. We use a momentum gradient mechanism to choose the attack node features in the feature selection module. In the feature modification module, we use two feature generation approaches (direct modification and sign gradient) to enable MGHGA to be employed on discrete and continuous datasets. We conduct extensive experiments on five benchmark datasets to validate the attack performance of MGHGA in the node and the visual object classification tasks. The results show that MGHGA improves performance by an average of 2% compared to the than the baselines.

cs.LG↗

arXiv2023

On the quaternionic Serre weights

We determine the set of quaternionic Serre weights for generic two-dimensional mod $p$ representation of $\operatorname{Gal}(\overline{\mathbb Q}_p / K)$, where $K$ is a finite unramified extension of $\mathbb{Q}_p$.

math.NT↗

arXiv2023

Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?

Pre-trained vision and language models have demonstrated state-of-the-art capabilities over existing tasks involving images and texts, including visual question answering. However, it remains unclear whether these models possess the capability to answer questions that are not only querying visual content but knowledge-intensive and information-seeking. In this study, we introduce InfoSeek, a visual question answering dataset tailored for information-seeking questions that cannot be answered with only common sense knowledge. Using InfoSeek, we analyze various pre-trained visual question answering models and gain insights into their characteristics. Our findings reveal that state-of-the-art pre-trained multi-modal models (e.g., PaLI-X, BLIP2, etc.) face challenges in answering visual information-seeking questions, but fine-tuning on the InfoSeek dataset elicits models to use fine-grained knowledge that was learned during their pre-training. Furthermore, we show that accurate visual entity recognition can be used to improve performance on InfoSeek by retrieving relevant documents, showing a significant space for improvement.

cs.CV↗

arXiv2023

Group SLOPE Penalized Low-Rank Tensor Regression

This article aims to seek a selection and estimation procedure for a class of tensor regression problems with multivariate covariates and matrix responses, which can provide theoretical guarantees for model selection in finite samples. Considering the frontal slice sparsity and low-rankness inherited in the coefficient tensor, we formulate the regression procedure as a group SLOPE penalized low-rank tensor optimization problem based on an orthogonal decomposition, namely TgSLOPE. This procedure provably controls the newly introduced tensor group false discovery rate (TgFDR), provided that the predictor matrix is column-orthogonal. Moreover, we establish the asymptotically minimax convergence with respect to the TgSLOPE estimate risk. For efficient problem resolution, we equivalently transform the TgSLOPE problem into a difference-of-convex (DC) program with the level-coercive objective function. This allows us to solve the reformulation problem of TgSLOPE by an efficient proximal DC algorithm (DCA) with global convergence. Numerical studies conducted on synthetic data and a real human brain connection data illustrate the efficacy of the proposed TgSLOPE estimation procedure.

math.ST↗

arXiv2023

Can Language Models be Instructed to Protect Personal Information?

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data leaks should be prevented, it is also crucial to examine the trade-off between the privacy protection and model utility of proposed approaches. In this paper, we introduce PrivQA -- a multimodal benchmark to assess this privacy/utility trade-off when a model is instructed to protect specific categories of personal information in a simulated scenario. We also propose a technique to iteratively self-moderate responses, which significantly improves privacy. However, through a series of red-teaming experiments, we find that adversaries can also easily circumvent these protections with simple jailbreaking methods through textual and/or image inputs. We believe PrivQA has the potential to support the development of new models with improved privacy protections, as well as the adversarial robustness of these protections. We release the entire PrivQA dataset at https://llm-access-control.github.io/.

cs.CL↗

arXiv2023

Dissecting the Gaia HR diagram II. The vertical structure of the star formation history across the Solar Cylinder

Starting from the Gaia DR3 HR diagram, we derive the star formation history (SFH) as a function of distance from the Galactic Plane within a cylinder centred on the Sun with a 200~pc radius and spanning 1.3~kpc above and below the Galaxy's midplane. We quantify both the concentration of the more recent star formation in the Galactic Plane, and the age-related increase in the scale height of the Galactic Disc stellar component, which is well-described by power-laws with indices ranging from $1/2$ to $2/3$. The vertically-integrated star formation rate falls from $(1.147 \pm 0.039)\times10^{-8}\, \text{M}_{\odot} \text{yr}^{-1} \text{pc}^{-2}$ at earlier times down to $(6.2 \pm 3.0) \times10^{-9}\, \text{M}_{\odot} \text{yr}^{-1} \text{pc}^{-2}$ at present times, but we find a significant peak of star formation in the 2 to 3 Gyr age bin. The total mass of stars formed per unit area over time is $118.7 \pm 6.2\, \text{M}_{\odot} \text{pc}^{-2}$, which is nearly twice the present stellar mass derived from kinematics within 1~kpc from the Galactic Plane, implying a high degree of matter recycling in successive generations of stars. The method is then modified by adopting an age-dependent correlation between the SFH across the different slices, which results in less noisy and more symmetrical results without significantly changing the previously mentioned quantities. This appears to be a promising way to improve SFH recovery in external galaxies.

astro-ph.GA↗

arXiv2023

Dronevision: An Experimental 3D Testbed for Flying Light Specks

Today's robotic laboratories for drones are housed in a large room. At times, they are the size of a warehouse. These spaces are typically equipped with permanent devices to localize the drones, e.g., Vicon Infrared cameras. Significant time is invested to fine-tune the localization apparatus to compute and control the position of the drones. One may use these laboratories to develop a 3D multimedia system with miniature sized drones configured with light sources. As an alternative, this brave new idea paper envisions shrinking these room-sized laboratories to the size of a cube or cuboid that sits on a desk and costs less than 10K dollars. The resulting Dronevision (DV) will be the size of a 1990s Television. In addition to light sources, its Flying Light Specks (FLSs) will be network-enabled drones with storage and processing capability to implement decentralized algorithms. The DV will include a localization technique to expedite development of 3D displays. It will act as a haptic interface for a user to interact with and manipulate the 3D virtual illuminations. It will empower an experimenter to design, implement, test, debug, and maintain software and hardware that realize novel algorithms in the comfort of their office without having to reserve a laboratory. In addition to enhancing productivity, it will improve safety of the experimenter by minimizing the likelihood of accidents. This paper introduces the concept of a DV, the research agenda one may pursue using this device, and our plans to realize one.

cs.MM↗

arXiv2023

Comparison of saturation rules used for gyrokinetic quasilinear transport modeling

Theory-based transport modeling has been widely successful and is built on the foundations of quasilinear theory. Specifically, the quasilinear expression of the flux can be used in combination with a saturation rule for the toroidal mode amplitude. Most transport models follow this approach. Saturation rules are heuristic and difficult to rigorously derive. We compare three common saturation rules using a fairly accurate quasilinear expression for the fluxes computed using local linear gyrokinetic simulation. We take plasma parameters from experimental H-mode profiles and magnetic equilibrium and include electrons, Deuterium, and Carbon species. We find that the various saturation rules give qualitatively similar behavior. This may help explain why the different theory-based transport models can all predict core tokamak profiles reasonably well. Comparisons with nonlinear local and global gyrokinetic simulations are also discussed.

physics.plasm-ph↗

arXiv2023

Tensor Gaussian Process with Contraction for Multi-Channel Imaging Analysis

Multi-channel imaging data is a prevalent data format in scientific fields such as astronomy and biology. The structured information and the high dimensionality of these 3-D tensor data makes the analysis an intriguing but challenging topic for statisticians and practitioners. The low-rank scalar-on-tensor regression model, in particular, has received widespread attention and has been re-formulated as a tensor Gaussian Process (Tensor-GP) model with multi-linear kernel in Yu et al.(2018). In this paper, we extend the Tensor-GP model by introducing an integrative dimensionality reduction technique, called tensor contraction, with a Tensor-GP for a scalar-on-tensor regression task with multi-channel imaging data. This is motivated by the solar flare forecasting problem with high dimensional multi-channel imaging data. We first estimate a latent, reduced-size tensor for each data tensor and then apply a multi-linear Tensor-GP on the latent tensor data for prediction. We introduce an anisotropic total-variation regularization when conducting the tensor contraction to obtain a sparse and smooth latent tensor. We then propose an alternating proximal gradient descent algorithm for estimation. We validate our approach via extensive simulation studies and applying it to the solar flare forecasting problem.

stat.ME↗

arXiv2023

Molecular environment of the thermal composite supernova remnant G352.7$-$0.1

Galactic supernova remnants (SNRs) play an important role in our understanding of supernovae and their feedback on the interstellar environment. SNR G352.7$-$0.1 is special for its thermal composite morphology and double-ring structure. We have performed spectroscopic mapping in $^{12}$CO and $^{13}$CO $J=2$-1 lines toward G352.7$-$0.1 with the Atacama Pathfinder Experiment telescope. Broad $^{12}$CO lines are found in the northeastern ring at a local-standard-of-rest velocity range of $\sim-50$-$-30$ km s$^{-1}$, suggesting that the remnant is interacting with molecular clouds (MCs) at $\sim-51$ km s$^{-1}$. Thus, we adopt a distance of $\sim10.5$ kpc for this SNR. The momentum and kinetic energy of the shocked gas along the line of sight are estimated to be $\sim10^2{\rm M_{sun}}$ km s$^{-1}$ and $\sim10^{46}$ erg, respectively. We also find an expanding structure around the remnant, which is possibly related to the wind-blown bubble of the progenitor star. From the Fermi-LAT data in an energy range of 0.1-500 GeV, we find no gamma-ray counterparts of G352.7$-$0.1.

astro-ph.HE↗

arXiv2023

The first comprehensive Milky Way stellar mock catalogue for the Chinese Space Station Telescope Survey Camera

The Chinese Space Station Telescope (CSST) is a cutting-edge two-meter astronomical space telescope currently under construction. Its primary Survey Camera (SC) is designed to conduct large-area imaging sky surveys using a sophisticated seven-band photometric system. The resulting data will provide unprecedented data for studying the structure and stellar populations of the Milky Way. To support the CSST development and scientific projects related to its survey data, we generate the first comprehensive Milky Way stellar mock catalogue for the CSST SC photometric system using the TRILEGAL stellar population synthesis tool. The catalogue includes approximately 12.6 billion stars, covering a wide range of stellar parameters, photometry, astrometry, and kinematics, with magnitude reaching down to $g\,=\,27.5$ mag in the AB magnitude system. The catalogue represents our benchmark understanding of the stellar populations in the Milky Way, enabling a direct comparison with the future CSST survey data. Particularly, it sheds light on faint stars that are hidden from current sky surveys. Our crowding limit analysis based on this catalogue provides compelling evidence for the extension of the CSST Optical Survey (OS) to cover low Galactic latitude regions. The strategic extension of the CSST-OS coverage, combined with this comprehensive mock catalogue, will enable transformative science with the CSST.

astro-ph.GA↗

arXiv2023

Scientific Objectives of the Hot Universe Baryon Surveyor (HUBS) Mission

The Hot Universe Baryon Surveyor (HUBS) is a proposed space-based X-ray telescope for detecting X-ray emissions from the hot gas content in our universe. With its unprecedented spatially-resolved high-resolution spectroscopy and large field of view, the HUBS mission will be uniquely qualified to measure the physical and chemical properties of the hot gas in the interstellar medium, the circumgalactic medium, the intergalactic medium, and the intracluster medium. These measurements will be valuable for two key scientific goals of HUBS, namely to unravel the AGN and stellar feedback physics that governs the formation and evolution of galaxies, and to probe the baryon budget and multi-phase states from galactic to cosmological scales. In addition to these two goals, the HUBS mission will also help us solve some problems in the fields of galaxy clusters, AGNs, diffuse X-ray backgrounds, supernova remnants, and compact objects. This paper discusses the perspective of advancing these fields using the HUBS telescope.

astro-ph.GA↗

arXiv2023

Lithium tantalate electro-optical photonic integrated circuits for high volume manufacturing

Photonic integrated circuits based on Lithium Niobate have demonstrated the vast capabilities afforded by material with a high Pockels coefficient, allowing linear and high-speed modulators operating at CMOS voltage levels for applications ranging from data-center communications and photonic accelerators for AI. However despite major progress, the industrial adoption of this technology is compounded by the high cost per wafer. Here we overcome this challenge and demonstrate a photonic platform that satisfies the dichotomy of allowing scalable manufacturing at low cost, while at the same time exhibiting equal, and superior properties to those of Lithium Niobate. We demonstrate that it is possible to manufacture low loss photonic integrated circuits using Lithium Tantalate, a material that is already commercially adopted for acoustic filters in 5G and 6G. We show that LiTaO3 posses equally attractive optical properties and can be etched with high precision and negligible residues using DUV lithography, diamond like carbon (DLC) as a hard mask and alkaline wet etching. Using this approach we demonstrate microresonators with an intrinsic cavity linewidth of 26.8 MHz, corresponding to a linear loss of 5.6 dB/m and demonstrate a Mach Zehnder modulator with Vpi L = 4.2 V cm half-wave voltage length product. In comparison to Lithium Niobate, the photonic integrated circuits based on LiTaO3 exhibit a much lower birefringence, allowing high-density circuits and broadband operation over all telecommunication bands (O to L band), exhibit higher photorefractive damage threshold, and lower microwave loss tangent. Moreover, we show that the platform supports generation of soliton microcombs in X-Cut LiTaO3 racetrack microresonator with electronically detectable repetition rate, i.e. 30.1 GHz.

physics.optics↗

arXiv2023

Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments

We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them. Our approach extracts check-worthy claims, which are aggregated and ranked for review. Stance classifiers are then used to identify tweets supporting novel misinformation claims, which are further reviewed to determine whether they violate relevant policies. To demonstrate the feasibility of our approach, we develop a baseline system based on modern NLP methods for human-in-the-loop fact-checking in the domain of COVID-19 treatments. We make our data and detailed annotation guidelines available to support the evaluation of human-in-the-loop systems that identify novel misinformation directly from raw user-generated content.

cs.CL↗

arXiv2023

HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image

Survival prediction based on whole slide images (WSIs) is a challenging task for patient-level multiple instance learning (MIL). Due to the vast amount of data for a patient (one or multiple gigapixels WSIs) and the irregularly shaped property of WSI, it is difficult to fully explore spatial, contextual, and hierarchical interaction in the patient-level bag. Many studies adopt random sampling pre-processing strategy and WSI-level aggregation models, which inevitably lose critical prognostic information in the patient-level bag. In this work, we propose a hierarchical vision Transformer framework named HVTSurv, which can encode the local-level relative spatial information, strengthen WSI-level context-aware communication, and establish patient-level hierarchical interaction. Firstly, we design a feature pre-processing strategy, including feature rearrangement and random window masking. Then, we devise three layers to progressively obtain patient-level representation, including a local-level interaction layer adopting Manhattan distance, a WSI-level interaction layer employing spatial shuffle, and a patient-level interaction layer using attention pooling. Moreover, the design of hierarchical network helps the model become more computationally efficient. Finally, we validate HVTSurv with 3,104 patients and 3,752 WSIs across 6 cancer types from The Cancer Genome Atlas (TCGA). The average C-Index is 2.50-11.30% higher than all the prior weakly supervised methods over 6 TCGA datasets. Ablation study and attention visualization further verify the superiority of the proposed HVTSurv. Implementation is available at: https://github.com/szc19990412/HVTSurv.

cs.CV↗

arXiv2023

Emergence of Symbols in Neural Networks for Semantic Understanding and Communication

The capacity to generate meaningful symbols and effectively employ them for advanced cognitive processes, such as communication, reasoning, and planning, constitutes a fundamental and distinctive aspect of human intelligence. Existing deep neural networks still notably lag human capabilities in terms of generating symbols for higher cognitive functions. Here, we propose a solution (symbol emergence artificial network (SEA-net)) to endow neural networks with the ability to create symbols, understand semantics, and achieve communication. SEA-net generates symbols that dynamically configure the network to perform specific tasks. These symbols capture compositional semantic information that allows the system to acquire new functions purely by symbolic manipulation or communication. In addition, these self-generated symbols exhibit an intrinsic structure resembling that of natural language, suggesting a common framework underlying the generation and understanding of symbols in both human brains and artificial neural networks. We believe that the proposed framework will be instrumental in producing more capable systems that can synergize the strengths of connectionist and symbolic approaches for artificial intelligence (AI).

cs.AI↗