arXiv subjects

Yuting Shen

Publications and source records attributed to Yuting Shen.

16 recordsLinked to original sources

arXiv2026

Parallelism and Generation Order in Masked Diffusion Language Models: Limits Today, Potential Tomorrow

Masked Diffusion Language Models (MDLMs) promise parallel token generation and arbitrary-order decoding, yet it remains unclear to what extent current models truly realize these capabilities. We characterize MDLM behavior along two dimensions -- parallelism strength and generation order -- using Average Finalization Parallelism (AFP) and Kendall's tau. We evaluate eight mainstream MDLMs (up to 100B parameters) on 58 benchmarks spanning knowledge, reasoning, and programming. The results show that MDLMs still lag behind comparably sized autoregressive models, mainly because parallel probabilistic modeling weakens inter-token dependencies. Meanwhile, MDLMs exhibit adaptive decoding behavior: their parallelism and generation order vary significantly with the task domain, the stage of reasoning, and whether the output is correct. On tasks that require "backward information" (e.g., Sudoku), MDLMs adopt a solution order that tends to fill easier Sudoku blanks first, highlighting their advantages. Finally, we provide theoretical motivation and design insights supporting a Generate-then-Edit paradigm, which mitigates dependency loss while retaining the efficiency of parallel decoding.

cs.CL↗

arXiv2025

Egent: An Autonomous Agent for Equivalent Width Measurement

We present Egent, an autonomous agent that combines classical multi-Voigt profile fitting with large language model (LLM) visual inspection and iterative refinement. The fitting engine is built from scratch with minimal dependencies, creating an ecosystem where the LLM can reason about fits through function calls--adjusting wavelength windows, adding blend components, modifying continuum treatment, and flagging problematic cases. Egent operates directly on raw flux spectra without requiring pre-normalized continua. We validate against manual measurements from human experts using 18,615 lines from the C3PO program across 84 Magellan/MIKE spectra at SNR~50-250. The raw agreement between Egent and expert measurements is MAD=5-7mA, without any post-hoc per-spectrum correction. Per-spectrum slopes of ~0.85-1.19 around unity reflect differences in global continuum methodology rather than fitting failures. The LLM's primary role is quality control: it confirms good fits (~60-65% of lines are LLM-refined and accepted), flags problematic cases (~10-20%), and occasionally rescues edge cases where tool use improves fits. Agreement between GPT-5 and GPT-5-mini confirms reproducibility, with GPT-5-mini enabling low-cost analysis at ~200 lines per US dollar. Every fit stores complete Voigt parameters, continuum coefficients, and LLM reasoning chains, enabling exact reconstruction without re-running. Egent compresses what traditionally requires months of expert effort into days of automated analysis, enabling survey-scale EW measurement. We provide open-source code at https://github.com/tingyuansen/Egent, including a web interface for drag-and-drop analysis and a local LLM backend for fully offline operation on consumer hardware.

astro-ph.IM↗

arXiv2025

A Composed Alternating Relaxed Projection Algorithm for Feasibility Problem

Feasibility problem aims to find a common point of two or more closed (convex) sets whose intersection is nonempty. In the literature, projection based algorithms are widely adopted to solve the problem, such as the method of alternating projection (MAP), and Douglas--Rachford splitting method (DR). The performance of the methods are governed by the geometric properties of the underlying sets. For example, the fixed-point sequence of the Douglas--Rachford splitting method exhibits a spiraling behavior when solving the feasibility problem of two subspaces, leading to a slow convergence speed and slower than MAP. However, when the problem at hand is non-polyhedral, DR can demonstrate significant faster performance. Motivated by the behaviors of the DR method, in this paper we propose a new algorithm for solving convex feasibility problems. The method is designed based on DR method by further incorporating a composition of projection and reflection. A non-stationary version of the method is also designed, aiming to achieve faster practical performance. Theoretical guarantees of the proposed schemes are provided and supported by numerical experiments.

math.OC↗

arXiv2024

HDN: Hybrid Deep-Learning and Non-Line-of-Sight Reconstruction Framework for Transcranial Photoacoustic Imaging of Human Brain

Photoacoustic imaging combines the high contrast of optical imaging with the deep penetration depth of ultrasonic imaging, showing great potential in cerebrovascular disease detection. However, the ultrasonic wave suffers strong attenuation and multi-scattering when it passes through the skull tissue, resulting in the distortion of the collected photoacoustic signal. In this paper, inspired by the principles of deep learning and non-line-of-sight imaging, we propose an image reconstruction framework named HDN (Hybrid Deep-learning and Non-line-of-sight), which consists of the signal extraction part and difference utilization part. The signal extraction part is used to correct the distorted signal and reconstruct an initial image. The difference utilization part is used to make further use of the signal difference between the distorted signal and corrected signal, reconstructing the residual image between the initial image and the target image. The test results on a photoacoustic digital brain simulation dataset show that compared with the traditional method (delay-and-sum) and deep-learning-based method (UNet), the HDN achieved superior performance in both signal correction and image reconstruction. Specifically for the structural similarity index, the HDN reached 0.661 in imaging results, compared to 0.157 for the delay-and-sum method and 0.305 for the deep-learning-based method.

physics.med-ph↗

arXiv2024

Hardware Architecture Design of Model-Based Image Reconstruction Towards Palm-size Photoacoustic Tomography

Photoacoustic (PA) imaging technology combines the advantages of optical imaging and ultrasound imaging, showing great potential in biomedical applications. Many preclinical studies and clinical applications urgently require fast, high-quality, low-cost and portable imaging system. Translating advanced image reconstruction algorithms into hardware implementations is highly desired. However, existing iterative PA image reconstructions, although exhibit higher accuracy than delay-and-sum algorithm, suffer from high computational cost. In this paper, we introduce a model-based hardware acceleration architecture based on superposed Wave (s-Wave) for palm-size PA tomography (palm-PAT), aiming at enhancing both the speed and performance of image reconstruction at a much lower system cost. To achieve this, we propose an innovative data reuse method that significantly reduces hardware storage resource consumption. We conducted experiments by FPGA implementation of the algorithm, using both phantoms and in vivo human finger data to verify the feasibility of the proposed method. The results demonstrate that our proposed architecture can substantially reduce system cost while maintaining high imaging performance. The hardware-accelerated implementation of the model-based algorithm achieves a speedup of up to approximately 270 times compared to the CPU, while the corresponding energy efficiency ratio is improved by more than 2700 times.

eess.IV↗

arXiv2024

Limited-View Photoacoustic Imaging Reconstruction Via High-quality Self-supervised Neural Representation

In practical applications within the human body, it is often challenging to fully encompass the target tissue or organ, necessitating the use of limited-view arrays, which can lead to the loss of crucial information. Addressing the reconstruction of photoacoustic sensor signals in limited-view detection spaces has become a focal point of current research. In this study, we introduce a self-supervised network termed HIgh-quality Self-supervised neural representation (HIS), which tackles the inverse problem of photoacoustic imaging to reconstruct high-quality photoacoustic images from sensor data acquired under limited viewpoints. We regard the desired reconstructed photoacoustic image as an implicit continuous function in 2D image space, viewing the pixels of the image as sparse discrete samples. The HIS's objective is to learn the continuous function from limited observations by utilizing a fully connected neural network combined with Fourier feature position encoding. By simply minimizing the error between the network's predicted sensor data and the actual sensor data, HIS is trained to represent the observed continuous model. The results indicate that the proposed HIS model offers superior image reconstruction quality compared to three commonly used methods for photoacoustic image reconstruction.

cs.CV↗

arXiv2023

Review of photoacoustic imaging plus X

Photoacoustic imaging (PAI) is a novel modality in biomedical imaging technology that combines the rich optical contrast with the deep penetration of ultrasound. To date, PAI technology has found applications in various biomedical fields. In this review, we present an overview of the emerging research frontiers on PAI plus other advanced technologies, named as PAI plus X, which includes but not limited to PAI plus treatment, PAI plus new circuits design, PAI plus accurate positioning system, PAI plus fast scanning systems, PAI plus novel ultrasound sensors, PAI plus advanced laser sources, PAI plus deep learning, and PAI plus other imaging modalities. We will discuss each technology's current state, technical advantages, and prospects for application, reported mostly in recent three years. Lastly, we discuss and summarize the challenges and potential future work in PAI plus X area.

physics.med-ph↗

arXiv2023

Gradient-based adaptive wavelet de-noising method for photoacoustic imaging in vivo

Photoacoustic imaging (PAI) has been applied to many biomedical applications over the past decades. However, the received PA signal usually suffers from poor signal-to-noise ratio (SNR). Conventional solution of employing higher-power laser, or doing long-time signal averaging, may raise the system cost, time consumption, and tissue damage. Another strategy is de-noising algorithm design. In this paper, we propose a new de-noising method, termed gradient-based adaptive wavelet de-noising, which sets the energy gradient mutation point of low-frequency wavelet components as the threshold. We conducted simulation, ex vivo and in vivo experiments to validate the performance of the algorithm. The quality of de-noised PA image/signal by our proposed algorithm has improved by 20%-40%, in comparison to the traditional signal denoising algorithms, which produces better contrast and clearer details. The proposed de-noising method provides potential to improve the SNR of PA signal under single-shot low-power laser illumination for biomedical applications in vivo.

eess.SP↗

arXiv2023

Photoacoustic digital tooth and image reconstruction of tooth root

Imaging of teeth is very important to doctors in the diagnosis and treatment of dental diseases. The main imaging modality currently used is Cone-Beam Computed Tomography (CBCT), which however suffers from ionizing radiation causing potential damage to human body. In this work, photoacoustic imaging is proposed for the imaging of tooth, specifically the tooth root. A photoacoustic digital phantom of the tooth is generated based on clinical CBCT data. The roots encased by alveolar bone are imaged by using the realistic photoacoustic digital phantom in the simulation study. Several image reconstruction algorithms are used and compared to remove the artifacts caused by heterogeneous acoustic velocity distribution.

physics.med-ph↗

arXiv2023

Non-line-of-sight photoacoustic imaging

Photoacoustic imaging is a promising imaging technique for human brain due to its high sensitivity and functional imaging ability. However, the skull would cause strong attenuation and distortion to the photoacoustic signals, which makes non-invasive transcranial imaging difficult. In this work, the temporal bone is selected as an imaging window to minimize the influence of the skull. Moreover, non-line-of-sight photoacoustic imaging is introduced to enhance the field of view, where the skull is considered as a reflector. Simulation studies are carried out to show that the image quality can be improved with reflected signal considered.

physics.med-ph↗

arXiv2022

Passive Photoacoustic Effect

Photoacoustic effect refers to the acoustic generation induced by laser irradiation, where nanosecond pulsed laser source is normally used to provide instantaneous heating and thermoelastic expansion of the sample. More generally, photoacoustic generation requires active intensity modulation of laser source to produce sharp temperature gradient, which is key to generate acoustic wave. In this paper, we propose a novel photoacoustic effect from moving droplet, which generates photoacoustic wave by a non-modulated continuous-wave laser. When the droplet moves through the laser spot area, it can be heated up and cooled down instantaneously, generating photoacoustic waves. We name it passive photoacoustic effect. Theoretical analysis and simulation study validated the existence of passive photoacoustic effect. This phenomenon may find potential application in high-throughput photoacoustic cytometry.

physics.app-ph↗

arXiv2022

FPGA Acceleration of Image Reconstruction for Real-Time Photoacoustic Tomography

Photoacoustic (PA) imaging has been widely applied in both preclinical and clinical applications. With a significantly increasing number of data acquisition channels, fast and high-quality image reconstruction for real-time PA imaging is an open challenge in this community. In this paper, we propose a FPGA-accelerated method to achieve a much faster image reconstruction speed by 20~60 times compared with using CPU, with much-reduced system cost and power budget, from dozens of Watt (CPU) to 1~2 Watt (FPGA). Equivalently, the energy efficiency ratio (EER) is improved by ~1000 times. This FPGA acceleration method can be easily adapted to the most widely used algorithms, such as delay-and-sum (DAS) and its variants (e.g. DMAS, DAS-CF). We have performed in-vivo human finger experiments to demonstrate the feasibility and potential of the proposed method. To our best knowledge, this is the first study of accelerating PA image reconstruction based on FPGA platform.

physics.med-ph↗

arXiv2022

Hand-held 3D Photoacoustic Imager with GPS

As an emerging medical diagnostic technology, photoacoustic imaging has been implemented for both preclinical and clinical applications. For clinical convenience, a handheld free scan photoacoustic tomography (PAT) system providing 3D imaging capability is essentially needed, which has potential for surgical navigation and disease diagnosis. In this paper, we proposed a free scan 3D PAT (fsPAT) system based on a handheld linear array ultrasound probe. A global positioning system (GPS) is applied for ultrasound probes coordinate acquisition. The proposed fsPAT can simultaneously realize real time 2D imaging, and large field of view 3D volumetric imaging, which is reconstructed from the multiple 2D images with coordinate information acquired by the GPS. To form a high quality 3D image, a dedicated space transformation method and reconstruction algorithm are used and validated by the proposed system. Both simulation and experimental studies have been performed to prove the feasibility of the proposed fsPAT. To explore its clinical potential, in vivo 3D imaging of human wrist vessels is also conducted, showing clear subcutaneous vessel network with high image contrast.

physics.med-ph↗

arXiv2016

Defects as a factor limiting carrier mobility in WSe2: a spectroscopic investigation

The electrical performance of two dimensional transitional metal dichalcogenides (TMDs) is strongly influenced by the amount of structural defects inside. In this work, we provide an optical spectroscopic characterization approach to correlate the amount of structural defects and the electrical performance of WSe2 devices. Low temperature photoluminescence (PL) spectra of electron beam lithography (EBL) processed WSe2 presents a clear defect-induced PL emission due to excitons bound to defects, which would strongly degrade the electrical performance. By adopting an e-beam-free transfer-electrode technique, we are able to prepare backgated WSe2 device with limited amount of defects. A maximum hole-mobility of about 200 cm2/Vs was achieved due to reduced scattering sources, which is the highest reported value among its type. This work would not only provide a versatile and nondestructive method to monitor the defects in TMDs, but also a new route to approach the room temperature phonon-limited mobility in high performance TMDs devices.

cond-mat.mtrl-sci↗

arXiv2014

Tuning the catalytic activity of graphene nanosheets for oxygen reduction reaction via size and thickness reduction

Currently, the fundamental factors that control the oxygen reduction reaction (ORR) activity of graphene itself, in particular the dependence of the ORR activity on the number of exposed edge sites remain elusive, mainly due to limited synthesis routes of achieving small size graphene. In this work, the synthesis of low oxygen content (< 2.5 +/-0.2 at %), few layer graphene nanosheets with lateral dimensions smaller than a few hundred nm was achieved using a combination of ionic liquid assisted grinding of high purity graphite coupled with sequential centrifugation. We show for the first time, that the graphene nanosheets possessing a plethora of edges exhibited considerably higher electron transfer numbers compared to the thicker graphene nanoplatelets. This enhanced ORR activity was accomplished by successfully exploiting the plethora of edges of the nanosized graphene as well as the efficient electron communication between the active edge sites and the electrode substrate. The graphene nanosheets were characterized by an onset potential of -0.13 V vs. Ag/AgCl and a current density of -3.85 mA/cm2 at -1 V, which represent the best ORR performance ever achieved from an undoped carbon based catalyst. This work demonstrates how low oxygen content nanosized graphene synthesized by a simple route can considerably impact the ORR catalytic activity and hence it is of significance in designing and optimizing advanced metal-free ORR electrocatalysts.

cond-mat.mtrl-sci↗

arXiv2014

Towards Intrinsic Charge Transport in Monolayer Molybdenum Disulfide by Defect and Interface Engineering

Molybdenum disulfide is considered as one of the most promising two-dimensional semiconductors for electronic and optoelectronic device applications. So far, the charge transport in monolayer molybdenum disulfide is dominated by extrinsic factors such as charged impurities, structural defects and traps, leading to much lower mobility than the intrinsic limit. Here, we develop a facile low-temperature thiol chemistry to repair the sulfur vacancies and improve the interface, resulting in significant reduction of the charged impurities and traps. High mobility greater than 80cm2 V-1 s-1 is achieved in backgated monolayer molybdenum disulfide field-effect transistors at room temperature. Furthermore, we develop a theoretical model to quantitatively extract the key microscopic quantities that control the transistor performances, including the density of charged impurities, short-range defects and traps. Our combined experimental and theoretical study provides a clear path towards intrinsic charge transport in two-dimensional dichalcogenides for future high-performance device applications.

cond-mat.mtrl-sci↗