arXiv subjects

Kai Zhu

Publications and source records attributed to Kai Zhu.

At least 73 records · Page 4Linked to original sources

arXiv2025

Line shape of the $Jψ\to γη_{c}$ decay

An accurate description of the photon spectrum line shape is essential for extracting resonance parameters of the $η_c$ meson through the radiative transition $J/ψ\to γη_{c}$. However, a persistent challenge remains in the form of a divergent tail at high photon energies, arising from the $E_γ^3$ factor in theoretical calculations. Various damping functions have been proposed to mitigate this effect in practical experiments, but their empirical nature lacks a rigorous theoretical basis. In this study, we introduce two key considerations: incorporating full-order contributions of the Bessel function in the overlap integral of charmonium wave functions and the phase space factor neglected in previous experimental studies. By accounting for these factors, we demonstrate a more rational and effective damping function of the divergent tail associated with the $E_γ^3$ term. We present the implications of these findings on experimental measurements and provide further insights through toy Monte Carlo simulations.

hep-ph↗

arXiv2025

VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization

Video colorization aims to transform grayscale videos into vivid color representations while maintaining temporal consistency and structural integrity. Existing video colorization methods often suffer from color bleeding and lack comprehensive control, particularly under complex motion or diverse semantic cues. To this end, we introduce VanGogh, a unified multimodal diffusion-based framework for video colorization. VanGogh tackles these challenges using a Dual Qformer to align and fuse features from multiple modalities, complemented by a depth-guided generation process and an optical flow loss, which help reduce color overflow. Additionally, a color injection strategy and luma channel replacement are implemented to improve generalization and mitigate flickering artifacts. Thanks to this design, users can exercise both global and local control over the generation process, resulting in higher-quality colorized videos. Extensive qualitative and quantitative evaluations, and user studies, demonstrate that VanGogh achieves superior temporal consistency and color fidelity.Project page: https://becauseimbatman0.github.io/VanGogh.

cs.CV↗

arXiv2025

MangaNinja: Line Art Colorization with Precise Reference Following

Derived from diffusion models, MangaNinjia specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases, cross-character colorization, multi-reference harmonization, beyond the reach of existing algorithms.

cs.CV↗

arXiv2025

Dwarf Galaxy Integral-field Survey (DGIS): survey overview and the result of global mass-metallicity relation

Low-mass galaxies are the building blocks of massive galaxies in the framework of hierarchical structure formation. To enable detailed studies of galactic ecosystems in dwarf galaxies by spatially resolving different galactic components, we have carried out the Dwarf Galaxy Integral-field Survey (DGIS). This survey aims to acquire observations with spatial resolutions as high as 10 to 100 pc while maintaining reasonably high signal-to-noise ratios with VLT/MUSE and ANU-2.3m/WiFeS. The whole sample will be composed of 65 dwarf galaxies with $M_{\rm \ast}$ $<$ 10$^{9}$ $\rm M_{\odot}$, selected from the Spitzer Local Volume Legacy Survey. The overall scientific goals include studying baryonic cycles in dwarf galaxies, searching for off-nuclear (intermediate)-massive black holes, and quantifying the inner density profiles of dark matter. In this work, we describe the sample selection, data reduction, and high-level data products. By integrating the spectra over the field of view for each galaxy, we obtained the integrated gas-phase metallicity and discussed its dependence on stellar mass and SFR. We find that the overall relation between metallicity and stellar mass of our DGIS nearly follows the extrapolation from the higher mass end. Its dispersion does not decrease by invoking the dependence on SFR.

astro-ph.GA↗

arXiv2024

Lipschitz Singularities in Diffusion Models

Diffusion models, which employ stochastic differential equations to sample images through integrals, have emerged as a dominant class of generative models. However, the rationality of the diffusion process itself receives limited attention, leaving the question of whether the problem is well-posed and well-conditioned. In this paper, we explore a perplexing tendency of diffusion models: they often display the infinite Lipschitz property of the network with respect to time variable near the zero point. We provide theoretical proofs to illustrate the presence of infinite Lipschitz constants and empirical results to confirm it. The Lipschitz singularities pose a threat to the stability and accuracy during both the training and inference processes of diffusion models. Therefore, the mitigation of Lipschitz singularities holds great potential for enhancing the performance of diffusion models. To address this challenge, we propose a novel approach, dubbed E-TSDM, which alleviates the Lipschitz singularities of the diffusion model near the zero point of timesteps. Remarkably, our technique yields a substantial improvement in performance. Moreover, as a byproduct of our method, we achieve a dramatic reduction in the Fréchet Inception Distance of acceleration methods relying on network Lipschitz, including DDIM and DPM-Solver, by over 33%. Extensive experiments on diverse datasets validate our theory and method. Our work may advance the understanding of the general diffusion process, and also provide insights for the design of diffusion models.

cs.CV↗

arXiv2024

Improved Video VAE for Latent Video Diffusion Model

Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a pretrained image VAE into the 3D causal structure for temporal-spatial compression, this paper presents two astonishing findings: (1) The initialization from a well-trained image VAE with the same latent dimensions suppresses the improvement of subsequent temporal compression capabilities. (2) The adoption of causal reasoning leads to unequal information interactions and unbalanced performance between frames. To alleviate these problems, we propose a keyframe-based temporal compression (KTC) architecture and a group causal convolution (GCConv) module to further improve video VAE (IV-VAE). Specifically, the KTC architecture divides the latent space into two branches, in which one half completely inherits the compression prior of keyframes from a lower-dimension image VAE while the other half involves temporal compression through 3D group causal convolution, reducing temporal-spatial conflicts and accelerating the convergence speed of video VAE. The GCConv in above 3D half uses standard convolution within each frame group to ensure inter-frame equivalence, and employs causal logical padding between groups to maintain flexibility in processing variable frame video. Extensive experiments on five benchmarks demonstrate the SOTA video reconstruction and generation capabilities of the proposed IV-VAE (https://wpy1999.github.io/IV-VAE/).

cs.CV↗

arXiv2024

LoopSCC: Towards Summarizing Multi-branch Loops within Determinate Cycles

Analyzing programs with loops is a challenging task, suffering from potential issues such as indeterminate number of iterations and exponential growth of control flow complexity. Loop summarization, as a static analysis method for concrete semantic interpretation, receives increasing focuses. It produces symbolic expressions semantically equivalent to the loop program. However, current loop summarization methods are only suitable for single-branch loops or multi-branch loops with simple cycles, without supporting complex loops with irregular branch-to-branch transitions. In this paper, we proposed LoopSCC, a novel loop summarization technique, to achieve concrete semantic interpretation on complex loop. LoopSCC analyzes the control flow at the granularity of single-loop-path and applies the strongly connected components (SCC for short) for contraction and simplification, resulting in the contracted single-loop-path graph (CSG for short). Based on the control flow information provided by the CSG, we can convert the loop summary into a combination of SCC summaries. When an SCC contains irregular branch-to-branch transitions, we propose to explore a convergent range to identify the determinate cycles of different execution paths, referred as oscillatory interval. The loop summarization composed of both iteration conditions and execution operations can eventually be derived recursively. Extensive experiments compared to six state-of-the-art loop interpretation methods are conducted to evaluate the effectiveness of LoopSCC. From the results, LoopSCC outperforms comparative methods in both interpretation accuracy and application effectiveness. Especially, LoopSCC achieves a 100% interpretation accuracy on public common-used benchmark. A systematical study for loop properties on three large-scale programs illustrates that LoopSCC presents outstanding scalability for real-world loop programs.

cs.PL↗

arXiv2024

Resolved properties of classical bulge and pseudo-bulge galaxies

We compare properties of classical and pseudo-bulges and properties of their hosting galaxies selected from the MaNGA survey. Bulge types are identified based on the S$\mathrm{\acute{e}}$rsic index n of bulge component and the position of bulges on the Kormandy diagram. For the 393 classical bulges and 422 pseudo-bulges selected and their hosting galaxies, we study their kinematic properties including a proxy for specific angular momentum and central velocity dispersion, their stellar population properties including stellar age, metallicity, and specific star formation rate, as well as HI fractions of the galaxies. Our results show that at given stellar mass, disc components of pseudo-bulge galaxies are younger, have more active star formation, rotate more, and may contain more HI content compared with those of classical bulge galaxies, and the differences are larger than those between bulges themselves. The correlations between bulge types and disc properties indicate that different types of bulges are shaped by different processes that may regulate both growth of central components and evolution of outer discs in galaxies. In addition, we propose a stellar mass dependent divider of central velocity dispersion to separate galaxies with classical bulges from those with pseudo-bulges in galaxy mass range of $10.4<\mathrm{log}(M_*/M_\odot)<11.4$: $\mathrm{log}(σ_0) = 0.23 \times \mathrm{log}(M_*/M_\odot)-0.46$. Galaxies with larger/smaller $σ_0$ can be classified as hosts of classical/pseudo-bulges.

astro-ph.GA↗

arXiv2024

ViViD: Video Virtual Try-on using Diffusion Models

Video virtual try-on aims to transfer a clothing item onto the video of a target person. Directly applying the technique of image-based try-on to the video domain in a frame-wise manner will cause temporal-inconsistent outcomes while previous video-based try-on solutions can only generate low visual quality and blurring results. In this work, we present ViViD, a novel framework employing powerful diffusion models to tackle the task of video virtual try-on. Specifically, we design the Garment Encoder to extract fine-grained clothing semantic features, guiding the model to capture garment details and inject them into the target video through the proposed attention feature fusion mechanism. To ensure spatial-temporal consistency, we introduce a lightweight Pose Encoder to encode pose signals, enabling the model to learn the interactions between clothing and human posture and insert hierarchical Temporal Modules into the text-to-image stable diffusion model for more coherent and lifelike video synthesis. Furthermore, we collect a new dataset, which is the largest, with the most diverse types of garments and the highest resolution for the task of video virtual try-on to date. Extensive experiments demonstrate that our approach is able to yield satisfactory video try-on results. The dataset, codes, and weights will be publicly available. Project page: https://becauseimbatman0.github.io/ViViD.

cs.CV↗

arXiv2024

MaNGA DynPop -- V. The dark-matter fraction versus stellar velocity dispersion relation and stellar initial mass function variations in galaxies: dynamical models and full spectrum fitting of integral-field spectroscopy

Using the final MaNGA sample of 10K galaxies, we investigate the dark matter fraction $f_{\rm DM}$ within one half-light radius $R_{\rm e}$ for about 6K galaxies with good kinematics spanning a wide range of morphologies and stellar velocity dispersion. We employ two techniques to estimate $f_{\rm DM}$: (i) Jeans Anisotropic Modelling (JAM), which performs dark matter decomposition based on stellar kinematics and (ii) comparing the total dynamical mass-to-light ratios $(M/L)_{\rm JAM}$ and $(M_{\ast}/L)_{\rm SPS}$ from Stellar Population Synthesis (SPS). We find that both methods consistently show a significant trend of increasing $f_{\rm DM}$ with decreasing $σ_{\rm e}$ and low $f_{\rm DM}$ at larger $σ_{\rm e}$. For 235 early-type galaxies with the best models, we explore the variation of stellar initial mass function (IMF) by comparing the stellar mass-to-light ratios from JAM and SPS. We confirm that the stellar mass excess factor $α_{\rm IMF}$ increases with $σ_{\rm e}$, consistent with previous studies that reported a transition from Chabrier-like to Salpeter IMF among galaxies. We show that the $α_{\rm IMF}$ trend cannot be driven by $M_{\ast}/L$ or IMF gradients as it persists when allowing for radial gradients in our model. We find no evidence for the total $M/L$ increasing toward the centre. We detect weak positive correlations between $α_{\rm IMF}$ and age, but no correlations with metallicity. We stack galaxy spectra according to their $α_{\rm IMF}$ to search for differences in IMF-sensitive spectral features (e.g. the $\rm Na_{\rm I}$ doublet). We only find marginal evidence for such differences, which casts doubt on the validity of one or both methods to measure the IMF.

astro-ph.GA↗

arXiv2024

InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

3D Gaussians have recently emerged as an efficient representation for novel view synthesis. This work studies its editability with a particular focus on the inpainting task, which aims to supplement an incomplete set of 3D Gaussians with additional points for visually harmonious rendering. Compared to 2D inpainting, the crux of inpainting 3D Gaussians is to figure out the rendering-relevant properties of the introduced points, whose optimization largely benefits from their initial 3D positions. To this end, we propose to guide the point initialization with an image-conditioned depth completion model, which learns to directly restore the depth map based on the observed image. Such a design allows our model to fill in depth values at an aligned scale with the original depth, and also to harness strong generalizability from largescale diffusion prior. Thanks to the more accurate depth completion, our approach, dubbed InFusion, surpasses existing alternatives with sufficiently better fidelity and efficiency under various complex scenarios. We further demonstrate the effectiveness of InFusion with several practical applications, such as inpainting with user-specific texture or with novel object insertion.

cs.CV↗

arXiv2024

MaNGA DynPop -- VI. Matter density slopes from dynamical models of 6000 galaxies versus cosmological simulations: the interplay between baryonic and dark matter

We try to understand the trends in the mass density slopes as a function of galaxy properties. We use the results from the best Jeans Anisotropic Modelling (JAM) of the integral-field stellar kinematics for near 6000 galaxies from the MaNGA DynPop project, with stellar masses of $10^{9-12}\ {\rm M_{\odot}}$, including both early-type and late-type galaxies. We use the mass-weighted density slopes for the stellar $\overlineγ_*$, dark $\overlineγ_{\rm DM}$, and total $\overlineγ_{\rm T}$ mass from the MaNGA DynPop project. The $\overlineγ_{\rm T}$ approaches a constant value of 2.2 for high $σ_{\rm e}$ galaxies, and flattens for lg$(σ_{\rm e}/{\rm km\ s^{-1}})\lesssim2.3$, reaching 1.5 for lg$(σ_{\rm e}/{\rm km\ s^{-1}})\approx1.8$. The total and stellar slopes track each other tightly, with $\overlineγ_{\rm T}\approx\overlineγ_*-0.174$ over the full $σ_{\rm e}$ range. This confirms the dominance of stellar matter within $R_{\rm e}$. We also show that there is no perfect conspiracy between baryonic and dark matter, as $\overlineγ_*$ and $\overlineγ_{\rm DM}$ do not vary inversely within the $σ_{\rm e}$ range. We find that the central galaxies from TNG50 and TNG100 simulations do not reproduce the observed galaxy mass distribution, which we attribute to the overestimated dark matter fraction, possibly due to a constant IMF and excessive adiabatic contraction effects in the simulations. Finally, we present the stacked dark matter density profiles and show that they are slightly steeper than the pure dark matter simulation prediction of $\overlineγ_{\rm DM}\approx1$, suggesting moderate adiabatic contraction in the central region of galaxies. Our work demonstrate the power of stellar dynamics modelling for probing the interaction between stellar and dark matter and testing galaxy formation theories.

astro-ph.GA↗

arXiv2024

Bilateral Unsymmetrical Graph Contrastive Learning for Recommendation

Recent methods utilize graph contrastive Learning within graph-structured user-item interaction data for collaborative filtering and have demonstrated their efficacy in recommendation tasks. However, they ignore that the difference relation density of nodes between the user- and item-side causes the adaptability of graphs on bilateral nodes to be different after multi-hop graph interaction calculation, which limits existing models to achieve ideal results. To solve this issue, we propose a novel framework for recommendation tasks called Bilateral Unsymmetrical Graph Contrastive Learning (BusGCL) that consider the bilateral unsymmetry on user-item node relation density for sliced user and item graph reasoning better with bilateral slicing contrastive training. Especially, taking into account the aggregation ability of hypergraph-based graph convolutional network (GCN) in digging implicit similarities is more suitable for user nodes, embeddings generated from three different modules: hypergraph-based GCN, GCN and perturbed GCN, are sliced into two subviews by the user- and item-side respectively, and selectively combined into subview pairs bilaterally based on the characteristics of inter-node relation structure. Furthermore, to align the distribution of user and item embeddings after aggregation, a dispersing loss is leveraged to adjust the mutual distance between all embeddings for maintaining learning ability. Comprehensive experiments on two public datasets have proved the superiority of BusGCL in comparison to various recommendation methods. Other models can simply utilize our bilateral slicing contrastive learning to enhance recommending performance without incurring extra expenses.

cs.IR↗

arXiv2024

Intention-driven Ego-to-Exo Video Generation

Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages action intention consisting of human movement and action description as view-independent representation to guide video generation, preserving the consistency of content and motion. Specifically, the egocentric head trajectory is first estimated through multi-view stereo matching. Then, cross-view feature perception module is introduced to establish correspondences between exo- and ego- views, guiding the trajectory transformation module to infer human full-body movement from the head trajectory. Meanwhile, we present an action description unit that maps the action semantics into the feature space consistent with the exocentric image. Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i.e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video. We conduct extensive experiments on the relevant dataset with diverse exo-ego video pairs, and our IDE outperforms state-of-the-art models in both subjective and objective assessments, demonstrating its efficacy in ego-to-exo video generation.

cs.CV↗

arXiv2024

Acousto-electric tomography by the convergence of Kaczamrz two-point gradient-$Θ$ method

We study the numerical reconstruction problem in acousto-electric tomography (AET) of recovering the conductivity distribution in a bounded domain from multiple interior power density data. The Two-Point-Gradient-$Θ$ (TPG-$Θ$) in Kaczmarz type is proposed, with a general convex penalty term $Θ$, the algorithm can be utilized in AET problem for recovering sparse and discontinuous conductivity distributions. We establish the convergence of such iterative regularized method. Extensive numerical experiments are presented to illustrate the feasibility and effectiveness of the proposed approach.

math.NA↗

arXiv2024

Assessing Mass Loss and Stellar-to-Halo Mass Ratio of Satellite Galaxies: A Galaxy-Galaxy Lensing Approach Utilizing DECaLS DR8 Data

The galaxy-galaxy lensing technique allows us to measure the subhalo mass of satellite galaxies, studying their mass loss and evolution within galaxy clusters and providing direct observational validation for theories of galaxy formation. In this study, we use the weak gravitational lensing observations from DECaLS DR8, in combination with the redMaPPer galaxy cluster catalog from Sloan Digital Sky Survey data (SDSS) DR8 to accurately measure the dark matter halo mass of satellite galaxies. We confirm a significant increase in the stellar-to-halo mass ratio of satellite galaxies with their halo-centric radius, indicating clear evidence of mass loss due to tidal stripping. Additionally, we find that this mass loss is strongly dependent on the mass of the satellite galaxies, with satellite galaxies above $10^{11}~{\rm M_{\odot}/h}$ experiencing more pronounced mass loss compared to lower mass satellites, reaching 86\% at projected halo-centric radius $0.5R_{\rm 200c}$. The average mass loss rate, when not considering halo-centric radius, displays a U-shaped variation with stellar mass, with galaxies of approximately $4\times10^{10}~{\rm M_{\odot}/h}$ exhibiting the least mass loss, around 60\%. We compare our results with state-of-the-art hydrodynamical numerical simulations and find that the satellite galaxy stellar-to-halo mass ratio in the outskirts of galaxy clusters is higher compared to the predictions of the Illustris-TNG project about factor 5. Furthermore, the Illustris-TNG project's numerical simulations did not predict the observed dependence of satellite galaxy mass loss rate on satellite galaxy mass.

astro-ph.GA↗

arXiv2024

A Data-driven dE/dx Simulation with Normalizing Flow

In high-energy physics, precise measurements rely on highly reliable detector simulations. Traditionally, these simulations involve incorporating experiment data to model detector responses and fine-tuning them. However, due to the complexity of the experiment data, tuning the simulation can be challenging. One crucial aspect for charged particle identification is the measurement of energy deposition per unit length (referred to as dE/dx). This paper proposes a data-driven dE/dx simulation method using the Normalizing Flow technique, which can learn the dE/dx distribution directly from experiment data. By employing this method, not only can the need for manual tuning of the dE/dx simulation be eliminated, but also high-precision simulation can be achieved.

hep-ex↗

arXiv2023

MaNGA DynPop -- IV. Stacked total density profile of galaxy groups and clusters from combining dynamical models of integral-field stellar kinematics and galaxy-galaxy lensing

We present the measurement of total and stellar/dark matter decomposed mass density profile around a sample of galaxy groups and clusters with dynamical masses derived from integral-field stellar kinematics from the MaNGA survey in Paper I and weak lensing derived from the DECaLS imaging survey. Combining the two data sets enables accurate measurement of the radial density distribution from several kpc to Mpc scales. Intriguingly, we find that the excess surface density derived from stellar kinematics in the inner region cannot be explained by simply adding an NFW dark matter halo extrapolated from lensing measurement at a larger scale to a stellar mass component derived from the NASA-Sloan Atlas (NSA) catalogue. We find that a good fit to both data sets requires a stellar mass normalization about 3 times higher than that derived from the NSA catalogue, which would require an unrealistically too-heavy initial mass function for stellar mass estimation. If we keep the stellar mass normalization to that of the NSA catalogue but allow a varying inner dark matter density profile, we obtain an asymptotic slope of $γ_{\rm gnfw}$= $1.82_{-0.25}^{+0.15}$ and $γ_{\rm gnfw}$= $1.48_{-0.41}^{+0.20}$ for the group bin and the cluster bin respectively, significantly steeper than the NFW case. We also compare the total mass inner density slopes with those from TNG300 and find that the values from the simulation are lower than the observation by about $2σ$ level.

astro-ph.GA↗