arXiv subjects

Xiao Chen

Publications and source records attributed to Xiao Chen.

At least 127 records · Page 7Linked to original sources

arXiv2025

Free fermions under adaptive quantum dynamics

We study free fermion systems under adaptive quantum dynamics consisting of unitary gates and projective measurements followed by corrective unitary operations. We further introduce a classical flag for each site, allowing for an active or inactive status which determines whether or not the unitary gates are allowed to apply. In this dynamics, the individual quantum trajectories exhibit a measurement-induced entanglement transition from critical to area-law scaling above a critical measurement rate, similar to previously studied models of free fermions under continuous monitoring. Furthermore, we find that the corrective unitary operations can steer the system into a state characterized by charge-density-wave order. Consequently, an additional phase transition occurs, which can be observed at both the level of the quantum trajectory and the quantum channel. We establish that the entanglement transition and the steering transition are fundamentally distinct. The latter transition belongs to the parity-conserving (PC) universality class, arising from the interplay between the inherent fermionic parity and classical labelling. We demonstrate both the entanglement and the steering transitions via efficient numerical simulations of free fermion systems, which confirm the PC universality class of the latter.

quant-ph↗

arXiv2025

Reducing CT Metal Artifacts by Learning Latent Space Alignment with Gemstone Spectral Imaging Data

Metal artifacts in CT slices have long posed challenges in medical diagnostics. These artifacts degrade image quality, resulting in suboptimal visualization and complicating the accurate interpretation of tissues adjacent to metal implants. To address these issues, we introduce the Latent Gemstone Spectral Imaging (GSI) Alignment Framework, which effectively reduces metal artifacts while avoiding the introduction of noise information. Our work is based on a key finding that even artifact-affected ordinary CT sequences contain sufficient information to discern detailed structures. The challenge lies in the inability to clearly represent this information. To address this issue, we developed an Alignment Framework that adjusts the representation of ordinary CT images to match GSI CT sequences. GSI is an advanced imaging technique using multiple energy levels to mitigate artifacts caused by metal implants. By aligning the representation to GSI data, we can effectively suppress metal artifacts while clearly revealing detailed structure, without introducing extraneous information into CT sequences. To facilitate the application, we propose a new dataset, Artifacts-GSI, captured from real patients with metal implants, and establish a new benchmark based on this dataset. Experimental results show that our method significantly reduces metal artifacts and greatly enhances the readability of CT slices. All our code and data are available at: https://um-lab.github.io/GSI-MAR/

cs.CV↗

arXiv2025

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging for the open-source community. Existing vision-language models rely on external tools for speech processing, while speech-language models still suffer from limited or totally without vision-understanding capabilities. To address this gap, we propose the EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech abilities while maintaining the leading vision-language performance. With a semantic-acoustic disentangled speech tokenizer, we surprisingly notice that omni-modal alignment can further enhance vision-language and speech abilities compared with the bi-modal aligned counterparts. Moreover, a lightweight style module is introduced for the flexible speech style controls including emotions and pitches. For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks, and meanwhile, supporting omni-modal spoken dialogue with vivid emotions.

cs.CV↗

arXiv2025

Real-time simulations of laser-induced electron excitations in crystalline ZnO

We investigate non-equilibrium electron dynamics in crystalline ZnO induced by ultrashort, relatively intense, infrared laser pulses. Our focus is on understanding the mechanism that facilitates efficient conduction band population in ZnO to enable optically pumped lasing. We consider two different pulse frequencies (in the near-infrared and mid-infrared) for which experimental data are available, and we calculate the electronic response of a ZnO crystal for a wide range of pulse intensities. We apply and compare three complementary theoretical approaches: the analytical Keldysh model, the numerical solution of the semiconductor Bloch equations, and real-time time-dependent density functional theory. We conclude that time-dependent density functional theory is a valid \textit{ab initio} approach for predicting conduction band population, that offers an accurate enough description of static and transient optical properties of solids and provides physics insight into the intermediate excitation regime, where electronic excitations are determined by the interplay of intraband tunneling, a consequence of band bending, and interband multi-photon absorption.

cond-mat.mtrl-sci↗

arXiv2025

A PINN-enriched finite element method for linear elliptic problems

In this paper, we propose a hybrid method that combines finite element method (FEM) and physics-informed neural network (PINN) for solving linear elliptic problems. This method contains three steps: (1) train a PINN and obtain an approximate solution $u_θ$; (2) enrich the finite element space with $u_θ$; (3) obtain the final solution by FEM in the enriched space. In the second step, the enriched space is constructed by addition $v + u_θ$ or multiplication $v \cdot u_θ$, where $v$ belongs to the standard finite element space. We conduct the convergence analysis for the proposed method. Compared to the standard FEM, the same convergence order is obtained and higher accuracy can be achieved when solution derivatives are well approximated in PINN. Numerical examples from one dimension to three dimensions verify these theoretical results. For some examples, the accuracy of the proposed method can be reduced by a couple of orders of magnitude compared to the standard FEM.

math.NA↗

arXiv2025

UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation

Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face limitations due to the significant human workload required to design Q&A pairs for visual images, which inherently restricts the scale and scope of evaluations. Although automated MLLM-as-judge approaches attempt to reduce the human workload through automatic evaluations, they often introduce biases. To address these problems, we propose an Unsupervised Peer review MLLM Evaluation framework. It utilizes only image data, allowing models to automatically generate questions and conduct peer review assessments of answers from other models, effectively alleviating the reliance on human workload. Additionally, we introduce the vision-language scoring system to mitigate the bias issues, which focuses on three aspects: (i) response correctness; (ii) visual understanding and reasoning; and (iii) image-text correlation. Experimental results demonstrate that UPME achieves a Pearson correlation of 0.944 with human evaluations on the MMstar dataset and 0.814 on the ScienceQA dataset, indicating that our framework closely aligns with human-designed benchmarks and inherent human preferences.

cs.CV↗

arXiv2025

Quasi-periodic oscillations of GHz-band polarization in a black hole

Relativistic jets from accreting black holes (BHs) radiate non-thermal emission which is highly variable in different time scales. Magnetic fields anchored to a rotating BH or accretion disc accelerate and collimate jets of the BH systems. Previous studies on black holes of different mass scales, including supermassive and stellar-mass black holes, only report flux quasi-periodic oscillations in radio, optical, X-ray and gamma-ray bands. No quasi-periodic variations in polarization have yet been detected in any black hole systems. Here, we report the first detection of GHz radio polarization oscillations in GRS 1915+105, which harbors a spinning stellar-mass BH with a relativistic jet. Our observations show that during the increasing phase of radio emission, linear polarization and flux exhibit similar oscillation periods of $\sim 17$ and $33$ seconds, and their variation patterns anti-correlate with each other. These rare, short-period oscillations in both polarization and flux would be important to understand instabilities and special dynamics in magnetized jets.

astro-ph.HE↗

arXiv2025

Entanglement Transitions in Noisy Quantum Circuits on Trees

Decoherence is ubiquitous, and poses a significant impediment to the observation of quantum phenomena, such as the measurement-induced entanglement phase transition (MIPT). In this work, we study entanglement transitions in quantum circuits on trees, subject to both noise and measurements. We uncover a rich phase diagram that describes the ability of a tree quantum circuit to retain quantum or classical information in the presence of decoherence. By developing a mapping between the dynamics of information on the tree to a classical Markov process -- also defined on the tree -- we obtain exact solutions to the entanglement transitions displayed by the circuit under various noise and measurement strengths. Moreover, we find a host of phenomena, including the MIPT, which are \textit{robust} to decoherence. The analytical tractability facilitated by the method developed in this paper showcases the first example of an exactly solvable noise-robust MIPT, and holds promise for studies on broader, tree-like circuits.

quant-ph↗

arXiv2025

Safe platooning control of connected and autonomous vehicles on curved multi-lane roads

This paper investigates the safe platoon formation tracking and merging control problem of connected and automated vehicles (CAVs) on curved multi-lane roads. The first novelty is the separation of the control designs into two distinct parts: a lateral control law that ensures a geometrical convergence towards the reference path regardless of the translational velocity, and a longitudinal control design for each vehicle to achieve the desired relative arc length and velocity with respect to its neighboring vehicle. The second novelty is exploiting the constructive barrier feedback as an additive term to the nominal tracking control, ensuring both lateral and longitudinal collision avoidance. This constructive barrier feedback acts as a dissipative term, slowing down the relative velocity toward obstacles without affecting the nominal controller's performance. Consequently, our proposed control method enables safe platoon formation of vehicles on curved multi-lane roads, with theoretical guarantees for safety invariance and stability analysis. Simulation and experimental results on connected vehicles are provided to further validate the effectiveness of the proposed method.

eess.SY↗

arXiv2025

TorchResist: Open-Source Differentiable Resist Simulator

Recent decades have witnessed remarkable advancements in artificial intelligence (AI), including large language models (LLMs), image and video generative models, and embodied AI systems. These advancements have led to an explosive increase in the demand for computational power, challenging the limits of Moore's Law. Optical lithography, a critical technology in semiconductor manufacturing, faces significant challenges due to its high costs. To address this, various lithography simulators have been developed. However, many of these simulators are limited by their inadequate photoresist modeling capabilities. This paper presents TorchResist, an open-source, differentiable photoresist simulator.TorchResist employs an analytical approach to model the photoresist process, functioning as a white-box system with at most twenty interpretable parameters. Leveraging modern differentiable programming techniques and parallel computing on GPUs, TorchResist enables seamless co-optimization with other tools across multiple related tasks. Our experimental results demonstrate that TorchResist achieves superior accuracy and efficiency compared to existing solutions. The source code is publicly available.

cs.LG↗

arXiv2025

Possible $D_{1}D_{1}$, $D_{1} \bar D_{1} $, $B_{1}B_{1}$ and $B_{1} \bar B_{1} $ molecular states and the recoil corrections

Recoil correction appears at $O(\frac{1}{M})$, which turns out to be very essential for the hadronic molecules with heavy flavor. In the past, we always thought that the recoil corrections were unfavorable to the formation of the molecular states, but our research reveals its importance to form the di-hadron bound states. In some cases, we are unable to find the bound states without considering the recoil corrections. Under SU(2) chiral symmetry, we have studied the $D_1 D_1$, $D_1 \bar D_1$, $B_1 B_1$ and $B_1 \bar B_1$ systems in the framework of the one-boson exchange (OBE) model with the treatments of the $S$\--{}$D$ wave mixing effect and the recoil corrections. Our results indicate that both the $D_1 D_1$ system with $I(J^P)=0(1^+)$ and $I(J^P)=1(2^+)$ can form the molecular states whether with the recoil corrections or not, while the $D_1 D_1$ system with $I(J^P)=1(0^+)$ fail to form a hadronic molecule without the recoil corrections but it turns out to be a loosely bound state after the inclusion of the recoil corrections. And we have found the deuteron-like states for the $D_1 \bar D_1$, $B_1 B_1$ and $B_1 \bar B_1$ systems, whether considering the recoil corrections or not.

hep-ph↗

arXiv2025

Quantum Entanglement Phase Transitions and Computational Complexity: Insights from Ising Models

In this paper, we construct 2-dimensional bipartite cluster states and perform single-qubit measurements on the bulk qubits. We explore the entanglement scaling of the unmeasured 1-dimensional boundary state and show that under certain conditions, the boundary state can undergo a volume-law to an area-law entanglement transition driven by variations in the measurement angle. We bridge this boundary state entanglement transition and the measurement-induced phase transition in the non-unitary 1+1-dimensional circuit via the transfer matrix method. We also explore the application of this entanglement transition on the computational complexity problems. Specifically, we establish a relation between the boundary state entanglement transition and the sampling complexity of the bipartite $2$d cluster state, which is directly related to the computational complexity of the corresponding Ising partition function with complex parameters. By examining the boundary state entanglement scaling, we numerically identify the parameter regime for which the $2$d quantum state can be efficiently sampled, which indicates that the Ising partition function can be evaluated efficiently in such a region.

quant-ph↗

arXiv2025

Label-Efficient Data Augmentation with Video Diffusion Models for Guidewire Segmentation in Cardiac Fluoroscopy

The accurate segmentation of guidewires in interventional cardiac fluoroscopy videos is crucial for computer-aided navigation tasks. Although deep learning methods have demonstrated high accuracy and robustness in wire segmentation, they require substantial annotated datasets for generalizability, underscoring the need for extensive labeled data to enhance model performance. To address this challenge, we propose the Segmentation-guided Frame-consistency Video Diffusion Model (SF-VD) to generate large collections of labeled fluoroscopy videos, augmenting the training data for wire segmentation networks. SF-VD leverages videos with limited annotations by independently modeling scene distribution and motion distribution. It first samples the scene distribution by generating 2D fluoroscopy images with wires positioned according to a specified input mask, and then samples the motion distribution by progressively generating subsequent frames, ensuring frame-to-frame coherence through a frame-consistency strategy. A segmentation-guided mechanism further refines the process by adjusting wire contrast, ensuring a diverse range of visibility in the synthesized image. Evaluation on a fluoroscopy dataset confirms the superior quality of the generated videos and shows significant improvements in guidewire segmentation.

cs.CV↗

arXiv2025

LSU-Net: Lightweight Automatic Organs Segmentation Network For Medical Images

UNet and its variants have widespread applications in medical image segmentation. However, the substantial number of parameters and computational complexity of these models make them less suitable for use in clinical settings with limited computational resources. To address this limitation, we propose a novel Lightweight Shift U-Net (LSU-Net). We integrate the Light Conv Block and the Tokenized Shift Block in a lightweight manner, combining them with a dynamic weight multi-loss design for efficient dynamic weight allocation. The Light Conv Block effectively captures features with a low parameter count by combining standard convolutions with depthwise separable convolutions. The Tokenized Shift Block optimizes feature representation by shifting and capturing deep features through a combination of the Spatial Shift Block and depthwise separable convolutions. Dynamic adjustment of the loss weights at each layer approaches the optimal solution and enhances training stability. We validated LSU-Net on the UWMGI and MSD Colon datasets, and experimental results demonstrate that LSU-Net outperforms most state-of-the-art segmentation architectures.

eess.IV↗

arXiv2025

Exponentially slow thermalization in 1D fragmented dynamics

We investigate the thermalization dynamics of 1D systems with local constraints coupled to an infinite temperature bath at one boundary. The coupling to the bath eventually erases the effects of the constraints, causing the system to tend towards a maximally mixed state at long times. We show that for a large class of local constraints, the time at which thermalization occurs can be extremely long. In particular, we present evidence for the following conjecture: when the constrained dynamics displays strong Hilbert space fragmentation, the thermalization time diverges exponentially with system size. We show that this conjecture holds for a wide range of dynamical constraints, including dipole-conserving dynamics, the $tJ_z$ model, and a large class of group-based dynamics, and relate a general proof of our conjecture to a different conjecture about the existence of certain expander graphs.

quant-ph↗

arXiv2024

DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering

Digitally reconstructed radiographs (DRRs) are simulated 2D X-ray images generated from 3D CT volumes, widely used in preoperative settings but limited in intraoperative applications due to computational bottlenecks, especially for accurate but heavy physics-based Monte Carlo methods. While analytical DRR renderers offer greater efficiency, they overlook anisotropic X-ray image formation phenomena, such as Compton scattering. We present a novel approach that marries realistic physics-inspired X-ray simulation with efficient, differentiable DRR generation using 3D Gaussian splatting (3DGS). Our direction-disentangled 3DGS (DDGS) method separates the radiosity contribution into isotropic and direction-dependent components, approximating complex anisotropic interactions without intricate runtime simulations. Additionally, we adapt the 3DGS initialization to account for tomography data properties, enhancing accuracy and efficiency. Our method outperforms state-of-the-art techniques in image accuracy. Furthermore, our DDGS shows promise for intraoperative applications and inverse problems such as pose registration, delivering superior registration accuracy and runtime performance compared to analytical DRR methods.

cs.CV↗

arXiv2024

Scrambling Transition in Free Fermion Systems Induced by a Single Impurity

In quantum many-body systems, interactions play a crucial role in the emergence of information scrambling. When particles interact throughout the system, the entanglement between them can lead to a rapid and chaotic spreading of quantum information, typically probed by the growth in operator size in the Heisenberg picture. In this study, we explore whether the operator undergoes scrambling when particles interact solely through a single impurity in generic spatial dimensions, focusing on fermion systems with spatial and temporal random hoppings. By connecting the dynamics of the operator to the symmetric exclusion process with a source term, we demonstrate the presence of an escape-to-scrambling transition when tuning the interaction strength for fermions in three dimensions. As a comparison, systems in lower dimensions are proven to scramble at arbitrarily weak interactions unless the hopping becomes sufficiently long-ranged. Our predictions are validated using both a Brownian circuit with a single Majorana fermion per site and a solvable Brownian SYK model with a large local Hilbert space dimension. This suggests the universality of the theoretical picture for free fermion systems with spatial and temporal randomness.

quant-ph↗

arXiv2024

SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality

Foundation models like ChatGPT and Sora that are trained on a huge scale of data have made a revolutionary social impact. However, it is extremely challenging for sensors in many different fields to collect similar scales of natural images to train strong foundation models. To this end, this work presents a simple and effective framework, SimCMF, to study an important problem: cross-modal fine-tuning from vision foundation models trained on natural RGB images to other imaging modalities of different physical properties (e.g., polarization). In SimCMF, we conduct a thorough analysis of different basic components from the most naive design and ultimately propose a novel cross-modal alignment module to address the modality misalignment problem. We apply SimCMF to a representative vision foundation model Segment Anything Model (SAM) to support any evaluated new imaging modality. Given the absence of relevant benchmarks, we construct a benchmark for performance evaluation. Our experiments confirm the intriguing potential of transferring vision foundation models in enhancing other sensors' performance. SimCMF can improve the segmentation performance (mIoU) from 22.15% to 53.88% on average for evaluated modalities and consistently outperforms other baselines. The code is available at https://github.com/mt-cly/SimCMF

cs.CV↗