Searcharxiv⌕ Search

arXiv subjects

Jianjun Zhou

Publications and source records attributed to Jianjun Zhou.

At least 37 records · Page 2Linked to original sources
arXiv2025

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning. However, the development of truly general 4D world models remains fundamentally constrained by the availability of high-quality data. Existing datasets and benchmarks often lack the dynamic complexity, multi-domain diversity, and spatial-temporal annotations required to support key tasks such as 4D geometric reconstruction, future prediction, and camera-control video generation. To address this gap, we introduce OmniWorld, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling. OmniWorld consists of a newly collected OmniWorld-Game dataset and several curated public datasets spanning diverse domains. Compared with existing synthetic datasets, OmniWorld-Game provides richer modality coverage, larger scale, and more realistic dynamic interactions. Based on this dataset, we establish a challenging benchmark that exposes the limitations of current state-of-the-art (SOTA) approaches in modeling complex 4D environments. Moreover, fine-tuning existing SOTA methods on OmniWorld leads to significant performance gains across 4D reconstruction and video generation tasks, strongly validating OmniWorld as a powerful resource for training and evaluation. We envision OmniWorld as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines' holistic understanding of the physical world.

cs.CV↗
arXiv2025

WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool

We present WinT3R, a feed-forward reconstruction model capable of online prediction of precise camera poses and high-quality point maps. Previous methods suffer from a trade-off between reconstruction quality and real-time performance. To address this, we first introduce a sliding window mechanism that ensures sufficient information exchange among frames within the window, thereby improving the quality of geometric predictions without large computation. In addition, we leverage a compact representation of cameras and maintain a global camera token pool, which enhances the reliability of camera pose estimation without sacrificing efficiency. These designs enable WinT3R to achieve state-of-the-art performance in terms of online reconstruction quality, camera pose estimation, and reconstruction speed, as validated by extensive experiments on diverse datasets. Code and model are publicly available at https://github.com/LiZizun/WinT3R.

cs.CV↗
arXiv2025

The ALMA-QUARKS Survey: III. Clump-to-core fragmentation and search for high-mass starless cores

The Querying Underlying mechanisms of massive star formation with ALMA-Resolved gas Kinematics and Structures (QUARKS) survey observed 139 infrared-bright (IR-bright) massive protoclusters at 1.3 mm wavelength with ALMA. This study investigates clump-to-core fragmentation and searches for candidate high-mass starless cores within IR-bright clumps using combined ALMA 12-m (C-2) and Atacama Compact Array (ACA) 7-m data, providing $\sim$ 1 arcsec ($\sim\rm0.02~pc$ at 3.7 kpc) resolution and $\sim\rm0.6\,mJy\,beam^{-1}$ continuum sensitivity ($\sim 0.3~M_{\odot}$ at 30 K). We identified 1562 compact cores from 1.3 mm continuum emission using getsf. Observed linear core separations ($λ_{\rm obs}$) are significantly less than the thermal Jeans length ($λ_{\rm J}$), with the $λ_{\rm obs}/λ_{\rm J}$ ratios peaking at $\sim0.2$. This indicates that thermal Jeans fragmentation has taken place within the IR-bright protocluster clumps studied here. The observed low ratio of $λ_{\rm obs}/λ_{\rm J}\ll 1$ could be the result of evolving core separation or hierarchical fragmentation. Based on associated signatures of star formation (e.g., outflows and ionized gas), we classified cores into three categories: 127 starless, 971 warm, and 464 evolved cores. Two starless cores have mass exceeding 16$\,M_{\odot}$, and represent high-mass candidates. The scarcity of such candidates suggests that competitive accretion-type models could be more applicable than turbulent core accretion-type models in high-mass star formation within these IR-bright protocluster clumps.

astro-ph.GA↗
arXiv2025

Aether: Geometric-Aware Unified World Modeling

The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper proposes Aether, a unified framework that enables geometry-aware reasoning in world models by jointly optimizing three core capabilities: (1) 4D dynamic reconstruction, (2) action-conditioned video prediction, and (3) goal-conditioned visual planning. Through task-interleaved feature learning, Aether achieves synergistic knowledge sharing across reconstruction, prediction, and planning objectives. Building upon video generation models, our framework demonstrates zero-shot synthetic-to-real generalization despite never observing real-world data during training. Furthermore, our approach achieves zero-shot generalization in both action following and reconstruction tasks, thanks to its intrinsic geometric modeling. Notably, even without real-world data, its reconstruction performance is comparable with or even better than that of domain-specific models. Additionally, Aether employs camera trajectories as geometry-informed action spaces, enabling effective action-conditioned prediction and visual planning. We hope our work inspires the community to explore new frontiers in physically-reasonable world modeling and its applications.

cs.CV↗
arXiv2025

Viscosity Solutions for HJB Equations on the Process Space

In this paper we investigate a path dependent optimal control problem on the process space with both drift and volatility controls, with possibly degenerate volatility. The dynamic value function is characterized by a fully nonlinear second order path dependent HJB equation on the process space, which is by nature infinite dimensional. In particular, our model covers mean field control problems with common noise as a special case. We shall introduce a new notion of viscosity solutions and establish both the existence and the comparison principle, under merely Lipschitz/Holder continuity assumptions. The main feature of our notion is that, besides the standard smooth part, the test function consists of an extra singular component which allows us to handle the second order derivatives of the smooth test functions without invoking the Crandall-Ishii lemma. We shall use the doubling variable arguments, combined with the Ekeland-Borwein-Preiss variational principle in order to overcome the noncompactness of the state space. A smooth gauge-type function on the path space is crucial for our estimates.

math.OC↗
arXiv2025

Cloud-cloud collision and star formation in G013.313+0.193

We study the G013.313+0.193 G013.313 region, a complex environment characterized by molecular cloud interactions indicative of cloud-cloud collision (CCC). Observations of the NH3(1,1) and (2,2) inversion transitions were obtained using the Nanshan 26 m radio telescope, while HCO+ (1-0), 12CO, 13CO, and C18O(1-0) transitions from the Purple Mountain Observatory Delingha 14 m telescope. Archival data are also included. We identified key observational signatures of CCC, including complementary spatial distributions, U-shaped structures, bridge features, and V-shaped velocity distributions. The position-velocity diagrams (P-V) reveal clear indications of gas interaction between two velocity components, suggesting an ongoing collision at an estimated angle of approximately 45 degree to the line of sight. The estimated collision timescale is 0.35-1.03 Myr, aligned with the inferred ages of young stellar objects (YSOs) in the region, supporting the hypothesis of collision-induced star formation. Hub-filament system (HFS) are identified in the compressed gas region, where filaments converge toward a dense hub, suggesting the CCC as a potential driver of HFS formation and massive star formation. The high column density suggests favorable conditions for the formation of massive stars. Although alternative kinematic drivers such as longitudinal collapse and shear motion are considered, CCC remains the most plausible explanation for the observed features. Our findings contribute to our understanding of the mechanisms of cloud dynamics and massive star formation in turbulent molecular environments.

astro-ph.GA↗
arXiv2025

DeepVerse: 4D Autoregressive Video Generation as a World Model

World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive models primarily predict visual observations, thereby neglecting crucial hidden states like geometric structures and spatial coherence. This leads to rapid error accumulation and temporal inconsistency. To address these limitations, we introduce DeepVerse, a novel 4D interactive world model explicitly incorporating geometric predictions from previous timesteps into current predictions conditioned on actions. Experiments demonstrate that by incorporating explicit geometric constraints, DeepVerse captures richer spatio-temporal relationships and underlying physical dynamics. This capability significantly reduces drift and enhances temporal consistency, enabling the model to reliably generate extended future sequences and achieve substantial improvements in prediction accuracy, visual realism, and scene rationality. Furthermore, our method provides an effective solution for geometry-aware memory retrieval, effectively preserving long-term spatial consistency. We validate the effectiveness of DeepVerse across diverse scenarios, establishing its capacity for high-fidelity, long-horizon predictions grounded in geometry-aware dynamics.

cs.CV↗
arXiv2025

Physics-informed Deep Diffusion MRI Reconstruction with Synthetic Data: Break Training Data Bottleneck in Artificial Intelligence

Diffusion magnetic resonance imaging (MRI) is the only imaging modality for non-invasive movement detection of in vivo water molecules, with significant clinical and research applications. Diffusion weighted imaging (DWI) MRI acquired by multi-shot techniques can achieve higher resolution, better signal-to-noise ratio, and lower geometric distortion than single-shot, but suffers from inter-shot motion-induced artifacts. These artifacts cannot be removed prospectively, leading to the absence of artifact-free training labels. Thus, the potential of deep learning in multi-shot DWI reconstruction remains largely untapped. To break the training data bottleneck, here, we propose a Physics-Informed Deep DWI reconstruction method (PIDD) to synthesize high-quality paired training data by leveraging the physical diffusion model (magnitude synthesis) and inter-shot motion-induced phase model (motion phase synthesis). The network is trained only once with 100,000 synthetic samples, achieving encouraging results on multiple realistic in vivo data reconstructions. Advantages over conventional methods include: (a) Better motion artifact suppression and reconstruction stability; (b) Outstanding generalization to multi-scenario reconstructions, including multi-resolution, multi-b-value, multi-under-sampling, multi-vendor, and multi-center; (c) Excellent clinical adaptability to patients with verifications by seven experienced doctors (p<0.001). In conclusion, PIDD presents a novel deep learning framework by exploiting the power of MRI physics, providing a cost-effective and explainable way to break the data bottleneck in deep learning medical imaging.

eess.IV↗
arXiv2025

Evidence for Core-Core Collision in Barnard 68

The prestellar core Barnard 68 (B68) is a prototypical source to study the initial conditions and chemical processes of star formation. A previous numerical simulation suggested the southeastern bullet is impacting on the main body of B68. In order to obtain more observational evidence, mapping observations of the ground state SO ($1_0-0_1$) emission line at 30 GHz were made with the Effelsberg 100 m telescope. Based on the velocity field and channel maps derived from SO, three velocity components were clearly detected. The velocity field of the main body indicates rotation and is well fitted by a solid-body rotation model. The measured radial velocity difference between the bullet and the main core is about 0.4 km s$^{-1}$, which is almost equal to the velocity obtained by the previous numerical simulation. Therefore, the bullet is most likely impacting onto the rotating main body of B68. A 1D spherical non-LTE Monte-Carlo radiation transfer RATRAN code is performed to derive the radial abundance profile of SO by analyzing the observed velocity-integrated intensity. SO is depleted inside a 60$^{\prime\prime}$ (0.02 pc) radius from the core. The abundance stays constant at 2.0$\times$10$^{-9}$ for radii larger than 60$^{\prime\prime}$ from the center of the main core. The abundance is enhanced at the interface of the bullet and the main core indicating that shock waves were produced by the collision between the bullet and the main core. In conclusion, based on the kinematical and chemical analysis, our observational results support the previously proposed core-core collision scenario in B68.

astro-ph.GA↗
arXiv2025

Second-order monotonicity conditions and mean field games with volatility control

In this manuscript we study the well-posedness of the master equations for mean field games with volatility control. This infinite dimensional PDE is nonlinear with respect to both the first and second-order derivatives of its solution. For standard mean field games with only drift control, it is well-known that certain monotonicity condition is essential for the uniqueness of mean field equilibria and for the global well-posedness of the master equations. To adapt to the current setting with volatility control, we propose a new notion called second-order monotonicity conditions. Surprisingly, the second-order Lasry-Lions monotonicity is equivalent to its standard (first-order) version, but such an equivalency fails for displacement monotonicity. When the Hamiltonian is separable and the data are Lasry-Lions monotone, we show that the Lasry-Lions monotonicity propagates and the master equation admits a unique classical solution. This is the first work for the well-posedness, both local and global, of master equations when the volatility is controlled.

math.AP↗
arXiv2024

Deep Separable Spatiotemporal Learning for Fast Dynamic Cardiac MRI

Dynamic magnetic resonance imaging (MRI) plays an indispensable role in cardiac diagnosis. To enable fast imaging, the k-space data can be undersampled but the image reconstruction poses a great challenge of high-dimensional processing. This challenge necessitates extensive training data in deep learning reconstruction methods. In this work, we propose a novel and efficient approach, leveraging a dimension-reduced separable learning scheme that can perform exceptionally well even with highly limited training data. We design this new approach by incorporating spatiotemporal priors into the development of a Deep Separable Spatiotemporal Learning network (DeepSSL), which unrolls an iteration process of a 2D spatiotemporal reconstruction model with both temporal low-rankness and spatial sparsity. Intermediate outputs can also be visualized to provide insights into the network behavior and enhance interpretability. Extensive results on cardiac cine datasets demonstrate that the proposed DeepSSL surpasses state-of-the-art methods both visually and quantitatively, while reducing the demand for training cases by up to 75%. Additionally, its preliminary adaptability to unseen cardiac patients has been verified through a blind reader study conducted by experienced radiologists and cardiologists. Furthermore, DeepSSL enhances the accuracy of the downstream task of cardiac segmentation and exhibits robustness in prospectively undersampled real-time cardiac MRI.

eess.IV↗
arXiv2024

CloudBrain-ReconAI: An Online Platform for MRI Reconstruction and Image Quality Evaluation

Efficient collaboration between engineers and radiologists is important for image reconstruction algorithm development and image quality evaluation in magnetic resonance imaging (MRI). Here, we develop CloudBrain-ReconAI, an online cloud computing platform, for algorithm deployment, fast and blind reader study. This platform supports online image reconstruction using state-of-the-art artificial intelligence and compressed sensing algorithms with applications to fast imaging and high-resolution diffusion imaging. Through visiting the website, radiologists can easily score and mark the images. Then, automatic statistical analysis will be provided. CloudBrain-ReconAI is now open accessed at https://csrc.xmu.edu.cn/CloudBrain.html and will be continually improved to serve the MRI research community.

eess.IV↗
arXiv2024

Kinematics and star formation of hub-filament systems in W49A

W49A is a prominent giant molecular cloud (GMC) that exhibits strong star formation activities, yet its structural and kinematic properties remain uncertain. Our study aims to investigate the large-scale structure and kinematics of W49A, and elucidate the role of filaments and hub-filament systems (HFSs) in its star formation activity. We utilized continuum data from Herschel and the James Clerk Maxwell Telescope (JCMT) as well as the molecular lines 12CO (3-2), 13CO (3-2), and C18O (3-2) to identify filaments and HFS structures within W49A. Further analysis focused on the physical properties, kinematics, and mass transport within these structures. Additionally, recombination line emission from the H I/OH/Recombination (THOR) line survey was employed to trace the central H II region and ionized gas. Our findings reveal that W49A comprises one blue-shifted (B-S) HFS and one red-shifted (R-S) HFS, each with multiple filaments and dense hubs. Notably, significant velocity gradients were detected along these filaments, indicative of material transport toward the hubs. High mass accretion rates along the filaments facilitate the formation of massive stars in the HFSs. Furthermore, the presence of V-shaped structures around clumps in position-velocity diagrams suggests ongoing gravitational collapse and local star formation within the filaments. Our results indicate that W49A consists of one R-S HFS and one B-S HFS, and that the material transport from filaments to the hub promotes the formation of massive stars in the hub. These findings underscore the significance of HFSs in shaping the star formation history of W49A.

astro-ph.GA↗
arXiv2024

Simultaneous Deep Learning of Myocardium Segmentation and T2 Quantification for Acute Myocardial Infarction MRI

In cardiac Magnetic Resonance Imaging (MRI) analysis, simultaneous myocardial segmentation and T2 quantification are crucial for assessing myocardial pathologies. Existing methods often address these tasks separately, limiting their synergistic potential. To address this, we propose SQNet, a dual-task network integrating Transformer and Convolutional Neural Network (CNN) components. SQNet features a T2-refine fusion decoder for quantitative analysis, leveraging global features from the Transformer, and a segmentation decoder with multiple local region supervision for enhanced accuracy. A tight coupling module aligns and fuses CNN and Transformer branch features, enabling SQNet to focus on myocardium regions. Evaluation on healthy controls (HC) and acute myocardial infarction patients (AMI) demonstrates superior segmentation dice scores (89.3/89.2) compared to state-of-the-art methods (87.7/87.9). T2 quantification yields strong linear correlations (Pearson coefficients: 0.84/0.93) with label values for HC/AMI, indicating accurate mapping. Radiologist evaluations confirm SQNet's superior image quality scores (4.60/4.58 for segmentation, 4.32/4.42 for T2 quantification) over state-of-the-art methods (4.50/4.44 for segmentation, 3.59/4.37 for T2 quantification). SQNet thus offers accurate simultaneous segmentation and quantification, enhancing cardiac disease diagnosis, such as AMI.

eess.IV↗
arXiv2024

Magnetic Field of Molecular Gas Measured with the Velocity Gradient Technique II: Curved Magnetic Field in kpc-Scale Bubble of NGC\,628

We report the detection of the ordered alignment between the magnetic field and kpc-scale bubbles in the nearby spiral galaxy, NGC\,628. Applying the Velocity Gradient Technique (VGT) on CO spectroscopic data from the ALMA-PHANGS, the magnetic field of NGC\,628 is measured at the scale of 191\,pc ($\sim$ 4\,$''$). The large-scale magnetic field is oriented parallel to the spiral arms and curves around the galactic bubble structures in the mid-infrared emission observed by the James Webb Space Telescope (JWST). Twenty-one bubble structures have been identified at the edges of spiral arms with scales over 300\,pc, which includes two kpc-scale structures. These bubbles are caused by supernova remnants and prolonged star formation and are similar to the outflow chimneys found in neutral hydrogen in galactic disks. At the edge of the bubbles, the shocks traced by the OIII emission present a curved magnetic field that parallels the bubble's shell. The magnetic field follows the bubble expansion and binds the gas in the shell to trigger further star formation. By analyzing the larger sample of 1694 bubbles, we found a distinct radial-size distribution of bubbles in NGC\,628 indicating the star formation history in the galaxy.

astro-ph.GA↗
arXiv2024

One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstruction

Magnetic resonance imaging (MRI) is a widely used radiological modality renowned for its radiation-free, comprehensive insights into the human body, facilitating medical diagnoses. However, the drawback of prolonged scan times hinders its accessibility. The k-space undersampling offers a solution, yet the resultant artifacts necessitate meticulous removal during image reconstruction. Although Deep Learning (DL) has proven effective for fast MRI image reconstruction, its broader applicability across various imaging scenarios has been constrained. Challenges include the high cost and privacy restrictions associated with acquiring large-scale, diverse training data, coupled with the inherent difficulty of addressing mismatches between training and target data in existing DL methodologies. Here, we present a novel Physics-Informed Synthetic data learning framework for Fast MRI, called PISF. PISF marks a breakthrough by enabling generalized DL for multi-scenario MRI reconstruction through a single trained model. Our approach separates the reconstruction of a 2D image into many 1D basic problems, commencing with 1D data synthesis to facilitate generalization. We demonstrate that training DL models on synthetic data, coupled with enhanced learning techniques, yields in vivo MRI reconstructions comparable to or surpassing those of models trained on matched realistic datasets, reducing the reliance on real-world MRI data by up to 96%. Additionally, PISF exhibits remarkable generalizability across multiple vendors and imaging centers. Its adaptability to diverse patient populations has been validated through evaluations by ten experienced medical professionals. PISF presents a feasible and cost-effective way to significantly boost the widespread adoption of DL in various fast MRI applications.

eess.IV↗
arXiv2024

Optimal Control of Unbounded Functional Stochastic Evolution Systems in Hilbert Spaces: Second-Order Path-dependent HJB Equation

Optimal control and the associated second-order path-dependent Hamilton-Jacobi-Bellman (PHJB) equation are studied for unbounded functional stochastic evolution systems in Hilbert spaces. The notion of viscosity solution without B-continuity is introduced in the sense of Crandall and Lions, and is shown to coincide with the classical solutions and to satisfy a stability property. The value functional is proved to be the unique continuous viscosity solution to the associated PHJB equation, without assuming any B-continuity on the coefficients. In particular, in the Markovian case, our result provides a new theory of viscosity solutions to the Hamilton-Jacobi-Bellman equation for optimal control of stochastic evolutionary equations -- driven by a linear unbounded operator -- in a Hilbert space, and removes the B-continuity assumption on the coefficients, which was initially introduced for first-order equations by Crandall and Lions (see J. Func. Anal. 90 (1990), 237-283; 97 (1991), 417-465), and was subsequently used by Swiech (Comm. Partial Differential Equations 19 (1994), 1999-2036) and Fabbri, Gozzi, and Swiech (Probability Theory and Stochastic Modelling 82, 2017, Springer, Berlin).

math.OC↗