arXiv subjects

Miaomiao Zhang

Publications and source records attributed to Miaomiao Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

TLRN: Temporal Latent Residual Networks For Large Deformation Image Registration

This paper presents a novel approach, termed {\em Temporal Latent Residual Network (TLRN)}, to predict a sequence of deformation fields in time-series image registration. The challenge of registering time-series images often lies in the occurrence of large motions, especially when images differ significantly from a reference (e.g., the start of a cardiac cycle compared to the peak stretching phase). To achieve accurate and robust registration results, we leverage the nature of motion continuity and exploit the temporal smoothness in consecutive image frames. Our proposed TLRN highlights a temporal residual network with residual blocks carefully designed in latent deformation spaces, which are parameterized by time-sequential initial velocity fields. We treat a sequence of residual blocks over time as a dynamic training system, where each block is designed to learn the residual function between desired deformation features and current input accumulated from previous time frames. We validate the effectivenss of TLRN on both synthetic data and real-world cine cardiac magnetic resonance (CMR) image videos. Our experimental results shows that TLRN is able to achieve substantially improved registration accuracy compared to the state-of-the-art. Our code is publicly available at https://github.com/nellie689/TLRN.

cs.CV↗

arXiv2025

Learning Group Actions In Disentangled Latent Image Representations

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-dimensional data space, where group actions apply uniformly across the entire input, making it difficult to disentangle the subspace that varies under transformations. While latent-space methods offer greater flexibility, they still require manual partitioning of latent variables into equivariant and invariant subspaces, limiting the ability to robustly learn and operate group actions within the representation space. To address this, we introduce a novel end-to-end framework that for the first time learns group actions on latent image manifolds, automatically discovering transformation-relevant structures without manual intervention. Our method uses learnable binary masks with straight-through estimation to dynamically partition latent representations into transformation-sensitive and invariant components. We formulate this within a unified optimization framework that jointly learns latent disentanglement and group transformation mappings. The framework can be seamlessly integrated with any standard encoder-decoder architecture. We validate our approach on five 2D/3D image datasets, demonstrating its ability to automatically learn disentangled latent factors for group actions in diverse data, while downstream classification tasks confirm the effectiveness of the learned representations. Our code is publicly available at https://github.com/farhanaswarnali/Learning-Group-Actions-In-Disentangled-Latent-Image-Representations .

cs.CV↗

arXiv2025

The Milky Way Imaging Scroll Painting Survey: Data Release 1

We present the first data release (DR1) of the Milky Way Imaging Scroll Painting (MWISP) survey, a mapping in the J=(1-0) transition lines of 12CO, 13CO, and C18O toward the northern Galactic plane during 2011-2022. The MWISP survey was conducted using the PMO 13.7 m telescope at a spatial resolution of approximately 50" and a velocity resolution of 0.16 km/s at 115 GHz. DR1 fully covered 2310 square degrees within the Galactic longitude (l) and latitude (b) range of 9.75 deg =< l =< 229.75 deg and |b| =< 5.25 deg. The surveyed area was divided into cell units of 30'x30' for practical purposes and On-The-Fly (OTF) mapping was performed toward each target cell unit. The data were regridded into a regular 3D datacube in l-b-V_LSR with a pixel size of 30" in l-b axes and 0.16 km/s in theV_LSR axis. The median rms noise is 0.47 K, 0.25 K, and 0.25 K for 12CO, 13CO, and C18O, respectively. The equivalent 3 sigma sensitivity in 12CO luminosity is approximately 0.23 K km/s, making MWISP the most sensitive survey of its kind. In this paper, we describe the survey data, including the calibration, data cleaning, data mosaic processes, and the data products. The final mosaicked data cubes contain about 3.33x10^7 spectra (pixels) for each CO isotopologue line. Color composite images, made from the intensities of the isotopologue lines, and some concise descriptions are provided. We constructed a molecular cloud catalog based on the mosaicked 12CO data cube using the clustering algorithm DBSCAN, detecting 103,517 molecular clouds, 10,790 of which exhibit 13CO emission and 304 of which show C18O emission. Based on the histogram of voxel brightness temperature, we estimated a total 12CO flux of 7.69+/-0.38x10^7 K km/s arcmin^2, 82% of which is captured by the DBSCAN algorithm. The data, together with the cloud sample, provide unique information on molecular gas in the northern Milky Way.

astro-ph.GA↗

arXiv2025

Learning Geodesics of Geometric Shape Deformations From Images

This paper presents a novel method, named geodesic deformable networks (GDN), that for the first time enables the learning of geodesic flows of deformation fields derived from images. In particular, the capability of our proposed GDN being able to predict geodesics is important for quantifying and comparing deformable shape presented in images. The geodesic deformations, also known as optimal transformations that align pairwise images, are often parameterized by a time sequence of smooth vector fields governed by nonlinear differential equations. A bountiful literature has been focusing on learning the initial conditions (e.g., initial velocity fields) based on registration networks. However, the definition of geodesics central to deformation-based shape analysis is blind to the networks. To address this problem, we carefully develop an efficient neural operator to treat the geodesics as unknown mapping functions learned from the latent deformation spaces. A composition of integral operators and smooth activation functions is then formulated to effectively approximate such mappings. In contrast to previous works, our GDN jointly optimizes a newly defined geodesic loss, which adds additional benefits to promote the network regularizability and generalizability. We demonstrate the effectiveness of GDN on both 2D synthetic data and 3D real brain magnetic resonance imaging (MRI).

cs.CV↗

arXiv2025

Hierarchical Structure and Self-gravity in the Rosette Molecular Cloud

We analyze the hierarchical structure in the Rosette Molecular Cloud (RMC) using $^{13}$CO J=1-0 data from the Milky Way Imaging Scroll Painting (MWISP) survey with a non-binary Dendrogram algorithm that allows multiple branches to emerge from parent structures. A total of 588 substructures are identified, including 458 leaves and 130 branches. The physical parameters of the substructures, including peak brightness temperature ($T_{\rm peak}$), brightness temperature difference ($T_{\rm diff}$), radius ($R$), mass ($M$), velocity dispersion ($σ_v$), and surface density ($Σ$), are characterized. The $T_{\rm peak}$ and $T_{\rm diff}$ distributions follow exponential functions with characteristic values above $5σ_{\rm RMS}$. The statistical properties and scaling relations, i.e., $σ_v$-$R$, $M$-$R$, and $σ_v$-$RΣ$ relations are in general consistent with those from traditional segmentation methods. The mass and radius follow power-law distributions with exponents of 2.2-2.5, with slightly flatter slopes for substructures inside the HII region. The velocity dispersion scales weakly with radius ($σ_v \propto R^{0.45\pm 0.03}$, $r = 0.58$), but shows a tighter correlation with the product of surface density and size ($σ_v \propto (ΣR)^{0.29\pm 0.01}$, $r = 0.73$). Self-gravitating substructures are found across scales from $\sim$0.2 to 10 pc, and nearly all structures with peak brightness above 4 K are gravitationally bound ($α_{\rm vir} < 2$). The fraction of bound structures increases with mass, size, and surface density, supporting the scenario of global hierarchical collapse (GHC) for the evolution of molecular clouds, in which molecular clouds and their substructures are undergoing multiscale collapse.

astro-ph.GA↗

arXiv2025

Dust extinction map of the Galactic plane based on the UKIDSS survey data

Dust plays a critical role in the study of the interstellar medium (ISM). Extinction maps derived from optical surveys often fail to capture regions with high column density due to the limited photometric depth in optical wavelengths. To address these limitations, we developed the XPNICER method based on near-infrared (NIR) photometric survey data. This method combines the previously established PNICER and Xpercentile techniques, enabling effective mitigation of foreground contamination and improved handling of complex dust structures in the Galactic plane, which thus can provide more accurate extinction estimates, particularly in highly obscured regions. By applying XPNICER to the Galactic Plane Survey from the UKIRT Infrared Deep Sky Survey, we have generated a series of two-dimensional (2D) dust extinction maps that span roughly 1800 deg2 of the Galactic plane (0< l < 110deg and 140< l < 232deg, |b| < 5deg). These maps, with spatial resolutions between 30arcsec and 300arcsec, can trace extinction up to Av ~ 30-40 mag. This new approach offers higher spatial resolution and better detection of high-extinction regions compared to previous large-scale dust-based maps of the Galactic plane, providing an independent and complementary measure of dust column densities.

astro-ph.GA↗

arXiv2025

Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition

There is growing interest in applying artificial intelligence (AI) to automate and support complex decision-making tasks. However, it remains unclear how algorithms compare to human judgment in contexts requiring semantic understanding and domain expertise. We examine this in the context of the judge assignment problem, matching submissions to suitably qualified judges. Specifically, we tackled this problem at the Harvard President's Innovation Challenge, the university's premier venture competition awarding over \$500,000 to student and alumni startups. This represents a real-world environment where high-quality judge assignment is essential. We developed an AI-based judge-assignment algorithm, Hybrid Lexical-Semantic Similarity Ensemble (HLSE), and deployed it at the competition. We then evaluated its performance against human expert assignments using blinded match-quality scores from judges on $309$ judge-venture pairs. Using a Mann-Whitney U statistic based test, we found no statistically significant difference in assignment quality between the two approaches ($AUC=0.48, p=0.40$); on average, algorithmic matches are rated $3.90$ and manual matches $3.94$ on a 5-point scale, where 5 indicates an excellent match. Furthermore, manual assignments that previously required a full week could be automated in several hours by the algorithm during deployment. These results demonstrate that HLSE achieves human-expert-level matching quality while offering greater scalability and efficiency, underscoring the potential of AI-driven solutions to support and enhance human decision-making for judge assignment in high-stakes settings.

cs.HC↗

arXiv2025

Efficient Decomposition Identification of Deterministic Finite Automata from Examples

The identification of deterministic finite automata (DFAs) from labeled examples is a cornerstone of automata learning, yet traditional methods focus on learning monolithic DFAs, which often yield a large DFA lacking simplicity and interoperability. Recent work addresses these limitations by exploring DFA decomposition identification problems (DFA-DIPs), which model system behavior as intersections of multiple DFAs, offering modularity for complex tasks. However, existing DFA-DIP approaches depend on SAT encodings derived from Augmented Prefix Tree Acceptors (APTAs), incurring scalability limitations due to their inherent redundancy. In this work, we advance DFA-DIP research through studying two variants: the traditional Pareto-optimal DIP and the novel states-optimal DIP, which prioritizes a minimal number of states. We propose a novel framework that bridges DFA decomposition with recent advancements in automata representation. One of our key innovations replaces APTA with 3-valued DFA (3DFA) derived directly from labeled examples. This compact representation eliminates redundancies of APTA, thus drastically reducing variables in the improved SAT encoding. Experimental results demonstrate that our 3DFA-based approach achieves significant efficiency gains for the Pareto-optimal DIP while enabling a scalable solution for the states-optimal DIP.

cs.SE↗

arXiv2025

Control Synthesis of Cyber-Physical Systems for Real-Time Specifications through Causation-Guided Reinforcement Learning

In real-time and safety-critical cyber-physical systems (CPSs), control synthesis must guarantee that generated policies meet stringent timing and correctness requirements under uncertain and dynamic conditions. Signal temporal logic (STL) has emerged as a powerful formalism of expressing real-time constraints, with its semantics enabling quantitative assessment of system behavior. Meanwhile, reinforcement learning (RL) has become an important method for solving control synthesis problems in unknown environments. Recent studies incorporate STL-based reward functions into RL to automatically synthesize control policies. However, the automatically inferred rewards obtained by these methods represent the global assessment of a whole or partial path but do not accumulate the rewards of local changes accurately, so the sparse global rewards may lead to non-convergence and unstable training performances. In this paper, we propose an online reward generation method guided by the online causation monitoring of STL. Our approach continuously monitors system behavior against an STL specification at each control step, computing the quantitative distance toward satisfaction or violation and thereby producing rewards that reflect instantaneous state dynamics. Additionally, we provide a smooth approximation of the causation semantics to overcome the discontinuity of the causation semantics and make it differentiable for using deep-RL methods. We have implemented a prototype tool and evaluated it in the Gym environment on a variety of continuously controlled benchmarks. Experimental results show that our proposed STL-guided RL method with online causation semantics outperforms existing relevant STL-guided RL methods, providing a more robust and efficient reward generation framework for deep-RL.

cs.AI↗

arXiv2025

Magnetic Fields in the Bones of the Milky Way

Stars primarily form in galactic spiral arms within dense, filamentary molecular clouds. The largest and most elongated of these molecular clouds are referred to as ``bones," which are massive, velocity-coherent filaments (lengths ~20 to >100 pc, widths ~1-2 pc) that run approximately parallel and in close proximity to the Galactic plane. While these bones have been generally well characterized, the importance and structure of their magnetic fields (B-fields) remain largely unconstrained. Through the SOFIA Legacy program FIELDMAPS, we mapped the B-fields of 10 bones in the Milky Way. We found that their B-fields are varied, with no single preferred alignment along the entire spine of the bones. At higher column densities, the spines of the bones are more likely to align perpendicularly to the B-fields, although this is not ubiquitous, and the alignment shows no strong correlation with the locations of identified young stellar objects. We estimated the B-field strengths across the bones and found them to be ~30-150 $μ$G at pc scales. Despite the generally low virial parameters, the B-fields are strong compared to the local gravity, suggesting that B-fields play a significant role in resisting global collapse. Moreover, the B-fields may slow and guide gas flow during dissipation. Recent star formation within the bones may be due to high-density pockets at smaller scales, which could have formed before or simultaneously with the bones.

astro-ph.GA↗

arXiv2025

Interior Object Geometry via Fitted Frames

We propose a means of computing fitted frames on the boundary and in the interior of objects and using them to provide the basis for producing geometric features from them that are not only alignment-free but most importantly can be made to correspond locally across a population of objects. We describe a representation targeted for anatomic objects which is designed to enable this strong locational correspondence within object populations and thus to provide powerful object statistics. It accomplishes this by understanding an object as the diffeomorphic deformation of the closure of the interior of an ellipsoid and by using a skeletal representation fitted throughout the deformation to produce a model of the target object, where the object is provided initially in the form of a boundary mesh. Via classification performance on hippocampi shape between individuals with a disorder vs. others, we compare our method to two state-of-theart methods for producing object representations that are intended to capture geometric correspondence across a population of objects and to yield geometric features useful for statistics, and we show notably improved classification performance by this new representation, which we call the evolutionary s-rep. The geometric features that are derived from each of the representations, especially via fitted frames, are discussed.

cs.CV↗

arXiv2025

On Synthesis of Timed Regular Expressions

Timed regular expressions serve as a formalism for specifying real-time behaviors of Cyber-Physical Systems. In this paper, we consider the synthesis of timed regular expressions, focusing on generating a timed regular expression consistent with a given set of system behaviors including positive and negative examples, i.e., accepting all positive examples and rejecting all negative examples. We first prove the decidability of the synthesis problem through an exploration of simple timed regular expressions. Subsequently, we propose our method of generating a consistent timed regular expression with minimal length, which unfolds in two steps. The first step is to enumerate and prune candidate parametric timed regular expressions. In the second step, we encode the requirement that a candidate generated by the first step is consistent with the given set into a Satisfiability Modulo Theories (SMT) formula, which is consequently solved to determine a solution to parametric time constraints. Finally, we evaluate our approach on benchmarks, including randomly generated behaviors from target timed models and a case study.

cs.FL↗

arXiv2025

CU-JADE: A Method for Traversing Extinction Jumps along the Line of Sight

Although interstellar dust extinction serves as a powerful distance estimator, the solar system's location within the Galactic plane complicates distance determinations, especially for molecular clouds (MCs) at varying distances along the line of sight (LoS). The presence of complex extinction patterns along the LoS introduces degeneracies, resulting in less accurate distance measurements to overlapping MCs in crowded regions of the Galactic plane. In this study, we develop the CUSUM-based Jump-point Analysis for Distance Estimation (CU-JADE), a novel method designed to help mitigate these observational challenges. The key strengths of CU-JADE include: (1) sensitivity to detect abrupt jumps in Distance-$A_λ$ ($D$-$A$) datasets, (2) minimal systematic errors as demonstrated on both mock and observed data, and (3) the ability to combine CUSUM analysis with multiwavelength data to improve the completeness of distance measurements for nearby gas structures, even for extinction values as low as $ΔA_{V} \gtrsim 0.15$ mag. By combining CO survey data with a large sample of stars characterized by high-precision parallaxes and extinctions, we uncovered the multilayered molecular gas distribution in the high-latitude Cepheus region. We also determined accurate distances to MCs beyond the Cygnus Rift by analyzing the intricate structure of gas and extinction within the Galactic plane. Additionally, we constructed a full-sky 3D extinction map extending to 4 kpc, which provides critical insights into dense interstellar medium components dominated by molecular hydrogen. These results advance our understanding of the spatial distribution and physical properties of MCs across the Milky Way.

astro-ph.GA↗

arXiv2025

Unsupervised Cardiac Video Translation Via Motion Feature Guided Diffusion Model

This paper presents a novel motion feature guided diffusion model for unpaired video-to-video translation (MFD-V2V), designed to synthesize dynamic, high-contrast cine cardiac magnetic resonance (CMR) from lower-contrast, artifact-prone displacement encoding with stimulated echoes (DENSE) CMR sequences. To achieve this, we first introduce a Latent Temporal Multi-Attention (LTMA) registration network that effectively learns more accurate and consistent cardiac motions from cine CMR image videos. A multi-level motion feature guided diffusion model, equipped with a specialized Spatio-Temporal Motion Encoder (STME) to extract fine-grained motion conditioning, is then developed to improve synthesis quality and fidelity. We evaluate our method, MFD-V2V, on a comprehensive cardiac dataset, demonstrating superior performance over the state-of-the-art in both quantitative metrics and qualitative assessments. Furthermore, we show the benefits of our synthesized cine CMRs improving downstream clinical and analytical tasks, underscoring the broader impact of our approach. Our code is publicly available at https://github.com/SwaksharDeb/MFD-V2V.

eess.IV↗

arXiv2025

A Glimpse of Satellite Galaxies in the Milky Way with the 2.5-meter Wide Field Survey Telescope (WFST): Bootes III and Draco

We carry out deep imaging of the Milky Way satellite galaxies, Bootes III and Draco, with WFST as one pilot observing program to demonstrate the capability of WFST. Combining catalogs with PS1 DR2 and Gaia DR3, we derive proper motions for candidate member stars in these two satellite galaxies over a 12-year time baseline, yielding uncertainties of ~1.8 mas/yr at 21 mag and ~3.0 mas/yr at 22 mag in the r band. The proper motions derived from bright and faint stars are consistent, indicating no significant variation in proper motion across stellar luminosity as these galaxies undergo tidal interactions with the MW. Meanwhile, we suggest that Bootes III represents the bound remnant of the progenitor galaxy that gave rise to the Styx stream, as evidenced by its elongated density profile and overdensity in both spatial and kinematic space. This is the first paper to use WFST to measure the proper motions of faint stars in Milky Way satellite galaxies. More detailed analyses will be presented in forthcoming papers from the wide field survey (WFS) program.

astro-ph.GA↗

arXiv2025

IrrMap: A Large-Scale Comprehensive Dataset for Irrigation Method Mapping

We introduce IrrMap, the first large-scale dataset (1.1 million patches) for irrigation method mapping across regions. IrrMap consists of multi-resolution satellite imagery from LandSat and Sentinel, along with key auxiliary data such as crop type, land use, and vegetation indices. The dataset spans 1,687,899 farms and 14,117,330 acres across multiple western U.S. states from 2013 to 2023, providing a rich and diverse foundation for irrigation analysis and ensuring geospatial alignment and quality control. The dataset is ML-ready, with standardized 224x224 GeoTIFF patches, the multiple input modalities, carefully chosen train-test-split data, and accompanying dataloaders for seamless deep learning model training andbenchmarking in irrigation mapping. The dataset is also accompanied by a complete pipeline for dataset generation, enabling researchers to extend IrrMap to new regions for irrigation data collection or adapt it with minimal effort for other similar applications in agricultural and geospatial analysis. We also analyze the irrigation method distribution across crop groups, spatial irrigation patterns (using Shannon diversity indices), and irrigated area variations for both LandSat and Sentinel, providing insights into regional and resolution-based differences. To promote further exploration, we openly release IrrMap, along with the derived datasets, benchmark models, and pipeline code, through a GitHub repository: https://github.com/Nibir088/IrrMap and Data repository: https://huggingface.co/Nibir/IrrMap, providing comprehensive documentation and implementation details.

cs.CV↗

arXiv2025

Compositional Abstraction for Timed Systems with Broadcast Synchronization

Simulation-based compositional abstraction effectively mitigates state space explosion in model checking, particularly for timed systems. However, existing approaches do not support broadcast synchronization, an important mechanism for modeling non-blocking one-to-many communication in multi-component systems. Consequently, they also lack a parallel composition operator that simultaneously supports broadcast synchronization, binary synchronization, shared variables, and committed locations. To address this, we propose a simulation-based compositional abstraction framework for timed systems, which supports these modeling concepts and is compatible with the popular UPPAAL model checker. Our framework is general, with the only additional restriction being that the timed automata are prohibited from updating shared variables when receiving broadcast signals. Through two case studies, our framework demonstrates superior verification efficiency compared to traditional monolithic methods.

cs.FL↗

arXiv2025

IGG: Image Generation Informed by Geodesic Dynamics in Deformation Spaces

Generative models have recently gained increasing attention in image generation and editing tasks. However, they often lack a direct connection to object geometry, which is crucial in sensitive domains such as computational anatomy, biology, and robotics. This paper presents a novel framework for Image Generation informed by Geodesic dynamics (IGG) in deformation spaces. Our IGG model comprises two key components: (i) an efficient autoencoder that explicitly learns the geodesic path of image transformations in the latent space; and (ii) a latent geodesic diffusion model that captures the distribution of latent representations of geodesic deformations conditioned on text instructions. By leveraging geodesic paths, our method ensures smooth, topology-preserving, and interpretable deformations, capturing complex variations in image structures while maintaining geometric consistency. We validate the proposed IGG on plant growth data and brain magnetic resonance imaging (MRI). Experimental results show that IGG outperforms the state-of-the-art image generation/editing models with superior performance in generating realistic, high-quality images with preserved object topology and reduced artifacts. Our code is publicly available at https://github.com/nellie689/IGG.

cs.GR↗