arXiv subjects

Li Ma

Publications and source records attributed to Li Ma.

At least 73 records · Page 4Linked to original sources

arXiv2025

Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture

We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial closeups. To achieve this, we employ a novel volumetric capture, reconstruction and rendering pipeline based on Dynamic Gaussian Splatting and Diffusion-based Detail Enhancement. We design our pipeline specifically to meet the demands of high-end media production. We employ two capture rigs: the Scene Rig, which captures multi-actor performances at a resolution which falls short of 4K production quality, and the Face Rig, which records high-fidelity single-actor facial detail to serve as a reference for detail enhancement. We first reconstruct dynamic performances from the Scene Rig using 4D Gaussian Splatting, incorporating new model designs and training strategies to improve reconstruction, dynamic range, and rendering quality. Then to render high-quality images for facial closeups, we introduce a diffusion-based detail enhancement model. This model is fine-tuned with high-fidelity data from the same actors recorded in the Face Rig. We train on paired data generated from low- and high-quality Gaussian Splatting (GS) models, using the low-quality input to match the quality of the Scene Rig, with the high-quality GS as ground truth. Our results demonstrate the effectiveness of this pipeline in bridging the gap between the scalable performance capture of a large-scale rig and the high-resolution standards required for film and media production.

cs.GR↗

arXiv2025

Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures

We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric capture performances re-rendered with diverse camera trajectories via 4D Gaussian Splatting (4DGS), lighting variability obtained with a video relighting model. We fine-tune state-of-the-art open-source video diffusion models on this data to provide strong multi-view identity preservation, precise camera control, and lighting adaptability. Our framework also supports core capabilities for virtual production, including multi-subject generation using two approaches: joint training and noise blending, the latter enabling efficient composition of independently customized models at inference time; it also achieves scene and real-life video customization as well as control over motion and spatial layout during customization. Extensive experiments show improved video quality, higher personalization accuracy, and enhanced camera control and lighting adaptability, advancing the integration of video generation into virtual production. Our project page is available at: https://eyeline-labs.github.io/Virtually-Being.

cs.CV↗

arXiv2025

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequently, our method is agnostic to diffusion model design, requiring no changes to model architectures or training pipelines. Specifically, we propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise derived from optical flow fields, while preserving the spatial Gaussianity. The efficiency of our algorithm enables us to fine-tune modern video diffusion base models using warped noise with minimal overhead, and provide a one-stop solution for a wide range of user-friendly motion control: local object motion control, global camera movement control, and motion transfer. The harmonization between temporal coherence and spatial Gaussianity in our warped noise leads to effective motion control while maintaining per-frame pixel quality. Extensive experiments and user studies demonstrate the advantages of our method, making it a robust and scalable approach for controlling motion in video diffusion models. Video results are available on our webpage: https://eyeline-labs.github.io/Go-with-the-Flow. Source code and model checkpoints are available on GitHub: https://github.com/Eyeline-Labs/Go-with-the-Flow.

cs.CV↗

arXiv2025

Efficient Decision Trees for Tensor Regressions

We proposed the tensor-input tree (TT) method for scalar-on-tensor and tensor-on-tensor regression problems. We first address scalar-on-tensor problem by proposing scalar-output regression tree models whose input variable are tensors (i.e., multi-way arrays). We devised and implemented fast randomized and deterministic algorithms for efficient fitting of scalar-on-tensor trees, making TT competitive against tensor-input GP models. Based on scalar-on-tensor tree models, we extend our method to tensor-on-tensor problems using additive tree ensemble approaches. Theoretical justification and extensive experiments on real and synthetic datasets are provided to illustrate the performance of TT.

cs.LG↗

arXiv2025

FreSca: Scaling in Frequency Space Enhances Diffusion Models

Latent diffusion models (LDMs) have achieved remarkable success in a variety of image tasks, yet achieving fine-grained, disentangled control over global structures versus fine details remains challenging. This paper explores frequency-based control within latent diffusion models. We first systematically analyze frequency characteristics across pixel space, VAE latent space, and internal LDM representations. This reveals that the "noise difference" term, derived from classifier-free guidance at each step t, is a uniquely effective and semantically rich target for manipulation. Building on this insight, we introduce FreSca, a novel and plug-and-play framework that decomposes noise difference into low- and high-frequency components and applies independent scaling factors to them via spatial or energy-based cutoffs. Essentially, FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control. We demonstrate its versatility and effectiveness in improving generation quality and structural emphasis on multiple architectures (e.g., SD3, SDXL) and across applications including image generation, editing, depth estimation, and video synthesis, thereby unlocking a new dimension of expressive control within LDMs.

cs.CV↗

arXiv2025

A partial likelihood approach to tree-based density modeling and its application in Bayesian inference

Tree-based priors for probability distributions are usually specified using a predetermined, data-independent collection of candidate recursive partitions of the sample space. To characterize an unknown target density in detail over the entire sample space, candidate partitions must have the capacity to expand deeply into all areas of the sample space with potential non-zero sampling probability. Such an expansive system of partitions often incurs prohibitive computational costs and makes inference prone to overfitting, especially in regions with little probability mass. Thus, existing models typically make a compromise and rely on relatively shallow trees. This hampers one of the most desirable features of trees, their ability to characterize local features, and results in reduced statistical efficiency. Traditional wisdom suggests that this compromise is inevitable to ensure coherent likelihood-based reasoning in Bayesian inference, as a data-dependent partition system that allows deeper expansion only in regions with more observations would induce double dipping of the data. We propose a simple strategy to restore coherency while allowing the candidate partitions to be data-dependent, using Cox's partial likelihood. Our partial likelihood approach is broadly applicable to existing likelihood-based methods and, in particular, to Bayesian inference on tree-based models. We give examples in density estimation in which the partial likelihood is endowed with existing priors on tree-based models and compare with the standard, full-likelihood approach. The results show substantial gains in estimation accuracy and computational efficiency from adopting the partial likelihood.

stat.ME↗

arXiv2025

Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset

Video portrait relighting remains challenging because the results need to be both photorealistic and temporally stable. This typically requires a strong model design that can capture complex facial reflections as well as intensive training on a high-quality paired video dataset, such as dynamic one-light-at-a-time (OLAT). In this work, we introduce Lux Post Facto, a novel portrait video relighting method that produces both photorealistic and temporally consistent lighting effects. From the model side, we design a new conditional video diffusion model built upon state-of-the-art pre-trained video diffusion model, alongside a new lighting injection mechanism to enable precise control. This way we leverage strong spatial and temporal generative capability to generate plausible solutions to the ill-posed relighting problem. Our technique uses a hybrid dataset consisting of static expression OLAT data and in-the-wild portrait performance videos to jointly learn relighting and temporal modeling. This avoids the need to acquire paired video data in different lighting conditions. Our extensive experiments show that our model produces state-of-the-art results both in terms of photorealism and temporal consistency.

cs.GR↗

arXiv2025

Measuring Mass of Gas in Central Galaxies using weak lensing and satellite kinematics in MOND

In Milgrom's modified Newtonian dynamics (MOND) framework, the dynamical mass of a galaxy is fully determined by its baryonic matter distribution. We fit the distribution of cold and hot gas halos, focusing on hot gas, around SDSS central galaxies using weak lensing signals from the DECaLS survey in MOND. The central galaxies are classified into two samples, the total galaxies and star-forming galaxies. We find that hot gas halo densities nearly follow Plummer's profile for both samples across all mass bins. The rotation curves of the galaxy samples are also demonstrated. The efficiency of converting gas into stars, $M_*/(M_* + M_{\rm g})$, is between 0.3 and 0.8 in all mass bins of the star-forming sample, which is higher than in the total sample. We also calculate gas mass using the satellite kinematics method in MOND. A constant, mildly radial anisotropy or isotropy in satellite motion leads to good agreement between the satellite kinematics and weak lensing methods. Combining both methods, we observe a baryonic mass to line-of-sight velocity dispersion of satellites ($M_{\rm b}$-$σ_{\rm s}$) relation. In addition, we examine more sophisticated models in MOND, including external field effects and Osipkov-Merritt anisotropy profiles, and find them unnecessary. A simple, mildly radial constant anisotropic model or an isotropic model, even when isolated, already aligns with observations. The strong concordance between the two methods suggests that weak lensing signals reliably measure the dynamical mass of central galaxies and can constrain the distribution of missing baryons in galaxy clusters.

astro-ph.GA↗

arXiv2025

Nitrogen-Vacancy Engineering for Controlled Phase Transitions in CrN(111) Epitaxial Films

The phase transition in CrN epitaxial films is substantially suppressed by epitaxial constraint. Here, we propose that nitrogen (N) vacancies can be taken as a knob to regulate the phase transition of CrN(111) epitaxial films. To validate this concept, a series of CrN(111) films with controlled N concentrations (approximately from 0.0 to 5.0 at.%) were epitaxially grown on Al2O3(0001) substrates. Experimental characterization reveals that higher N vacancy concentrations significantly facilitate the out-of-plane contraction of the films at 273 K (0.8%), reaching up to 60% of the contraction magnitude of CrN powders (1.2%) without compromising the stability and reproducibility of the phase transition. Reducing N vacancy concentrations diminishes the lattice contraction, lowers the phase transition temperature to 193 K, and triggers a metallic to insulator transition in electrical behavior. First-principles calculations corroborate these findings, showing that N vacancies decrease the internal tensile stress within triangular Cr atomic layers, which enhances the out-of-plane contraction, elevates phase transition temperatures, and promotes bandgap closure. These results establish N vacancies as a critical factor governing phase transition dynamics in CrN systems and provide a practical strategy for successively engineering thermally responsive phase transitions in CrN films, advancing their potential for functional device applications.

cond-mat.mtrl-sci↗

arXiv2025

High-rate continuous-variable quantum key distribution over 100 km fiber with composable security

Quantum key distribution (QKD), providing a way to generate secret keys with information-theoretic security,is arguably one of the most significant achievements in quantum information. The continuous-variable QKD (CV-QKD) offers the potential advantage of achieving a higher secret key rate (SKR) within a metro area, as well as being compatible with the mature telecom industry. However, the SKR and transmission distance of state-of-the-art CV-QKD systems are currently limited. Here, based on the novelly proposed orthogonal-frequency-division-multiplexing (OFDM) CV-QKD protocol, we demonstrate for the first time a high-rate multi-carrier (MC) CV-QKD with a 10 GHz symbol rate that chieves Gbps SKR within 10km and Mbps SKR over 100 km in the finite-size regime under composable security against collective attacks. The record-breaking results are achieved by suitable optimization of subcarrier number and modulation variance, well-controlled excess noise induced by both OFDM mechanism and efficient DSP scheme, and high-performance post-processing capacity realized by heterogeneous computing scheme. The composable finite-size SKR reaches 1779.45 Mbps@5km, 1025.49 Mbps@10km, 370.50 Mbps@25km, 99.93 Mbps@50km, 25.70 Mbps@75km,and 2.25 Mbps@100km, which improves the SKR by two orders of magnitude and quintuples the maximal transmission distance compared to most recently reported CV-QKD results [Nature Communications, 13, 4740 (2022)]. Interestingly, it is experimentally verified that the SKR of the proposed MC CV-QKD can approach five times larger than that of the single-carrier CV-QKD with the same symbol rate without additional hardware costs. Our work constitutes a critical step towards future high-speed quantum metropolitan and access networks.

quant-ph↗

arXiv2025

Flexible manipulation of chiral spin state by chemical bond in Mn triangular lattice magnet

This study investigates the influence of chemical bonds on the magnetic structure of materials, a less explored area compared to their effect on crystal stability. By analyzing the strength and directionality of chemical bonds using the electron localization function (ELF) and charge density difference (CDD) methods, we examine their impact on magnetic exchange interactions and magnetocrystalline anisotropy under specific interstitial conditions in Mn4X compounds. Our findings indicate that these properties can effectively modulate the magnetic ground state. This work not only elucidates the varied magnetism observed in Mn triangular lattice magnets but also proposes an approach for engineering chiral spin states through chemical bonding manipulation.

cond-mat.mtrl-sci↗

arXiv2025

Quantifying the Dynamics of Harm Caused by Retracted Research

Despite enormous efforts devoted to understand the characteristics and impacts of retracted papers, little is known about the mechanisms underlying the dynamics of their harm and the dynamics of its propagation. Here, we propose a citation-based framework to quantify the harm caused by retracted papers, aiming to uncover why their harm persists and spreads so widely. We uncover an ''attention escape'' mechanism, wherein retracted papers postpone significant harm, more prominently affect indirectly citing papers, and inflict greater harm on citations in journals with an impact factor less than 10. This mechanism allows retracted papers to inflict harm outside the attention of authors and publishers, thereby evading their intervention. This study deepens understanding of the harm caused by retracted papers, emphasizes the need to activate and enhance the attention of authors and publishers, and offers new insights and a foundation for strategies to mitigate their harm and prevent its spread.

cs.DL↗

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

Stream-level flow matching with Gaussian processes

Flow matching (FM) is a family of training algorithms for fitting continuous normalizing flows (CNFs). Conditional flow matching (CFM) exploits the fact that the marginal vector field of a CNF can be learned by fitting least-squares regression to the conditional vector field specified given one or both ends of the flow path. In this paper, we extend the CFM algorithm by defining conditional probability paths along ``streams'', instances of latent stochastic paths that connect data pairs of source and target, which are modeled with Gaussian process (GP) distributions. The unique distributional properties of GPs help preserve the ``simulation-free" nature of CFM training. We show that this generalization of the CFM can effectively reduce the variance in the estimated marginal vector field at a moderate computational cost, thereby improving the quality of the generated samples under common metrics. Additionally, adopting the GP on the streams allows for flexibly linking multiple correlated training data points (e.g., time series). We empirically validate our claim through both simulations and applications to image and neural time series data.

stat.ML↗

arXiv2024

A tree-based model for addressing sparsity and taxa covariance in microbiome compositional count data

Microbiome compositional data are often high-dimensional, sparse, and exhibit pervasive cross-sample heterogeneity. Generative modeling is a popular approach to analyze such data, and effective generative models must accurately characterize these key features. While high-dimensionality and abundance of zeros have received much attention, existing models often lack flexibility in capturing complex cross-sample variability. This limitation can affect statistical efficiency and lead to misleading conclusions in tasks like differential abundance analysis, clustering, and network analysis. We introduce a generative model, the "logistic-tree normal" (LTN) model, which addresses this issue and effectively captures key characteristics of microbiome data, including abundance of zeros. LTN employs a tree-based decomposition to aggregate sparse taxa counts and uses a (multivariate) logistic-normal distribution at tree splits, allowing for flexible covariance adjustments among taxa as needed. The latent Gaussian structure of LTN enables the incorporation of multivariate analysis tools that enforce sparsity or low-rank covariance assumptions. As a versatile, fully generative model, LTN supports a wide range of applications and offers efficient Bayesian inference computational recipes through conjugate blocked Gibbs sampling with Pólya-Gamma augmentation. We demonstrate application of LTN in a compositional mixed-effects model for differential abundance analysis using numerical experiments and a reanalysis of the infant cohort in the DIABIMMUNE study. Our findings illustrate that LTN, by adequately accounting for cross-sample heterogeneity, appropriately generates the proportion of zeros without requiring an explicit zero-inflation component, confirming a recent viewpoint that "zero-inflation" in count-based sequencing data are often results of unaccounted cross-sample variation.

stat.ME↗

arXiv2024

Mixture of Link Predictors on Graphs

Link prediction, which aims to forecast unseen connections in graphs, is a fundamental task in graph machine learning. Heuristic methods, leveraging a range of different pairwise measures such as common neighbors and shortest paths, often rival the performance of vanilla Graph Neural Networks (GNNs). Therefore, recent advancements in GNNs for link prediction (GNN4LP) have primarily focused on integrating one or a few types of pairwise information. In this work, we reveal that different node pairs within the same dataset necessitate varied pairwise information for accurate prediction and models that only apply the same pairwise information uniformly could achieve suboptimal performance. As a result, we propose a simple mixture of experts model Link-MoE for link prediction. Link-MoE utilizes various GNNs as experts and strategically selects the appropriate expert for each node pair based on various types of pairwise information. Experimental results across diverse real-world datasets demonstrate substantial performance improvement from Link-MoE. Notably, Link-MoE achieves a relative improvement of 18.71\% on the MRR metric for the Pubmed dataset and 9.59\% on the Hits@100 metric for the ogbl-ppa dataset, compared to the best baselines.

cs.LG↗

arXiv2024

Fitting Spherical Gaussians to Dynamic HDRI Sequences

We present a technique for fitting high dynamic range illumination (HDRI) sequences using anisotropic spherical Gaussians (ASGs) while preserving temporal consistency in the compressed HDRI maps. Our approach begins with an optimization network that iteratively minimizes a composite loss function, which includes both reconstruction and diffuse losses. This allows us to represent all-frequency signals with a small number of ASGs, optimizing their directions, sharpness, and intensity simultaneously for an individual HDRI. To extend this optimization into the temporal domain, we introduce a temporal consistency loss, ensuring a consistent approximation across the entire HDRI sequence.

cs.CV↗

arXiv2024

Boosting 3D Object Generation through PBR Materials

Automatic 3D content creation has gained increasing attention recently, due to its potential in various applications such as video games, film industry, and AR/VR. Recent advancements in diffusion models and multimodal models have notably improved the quality and efficiency of 3D object generation given a single RGB image. However, 3D objects generated even by state-of-the-art methods are still unsatisfactory compared to human-created assets. Considering only textures instead of materials makes these methods encounter challenges in photo-realistic rendering, relighting, and flexible appearance editing. And they also suffer from severe misalignment between geometry and high-frequency texture details. In this work, we propose a novel approach to boost the quality of generated 3D objects from the perspective of Physics-Based Rendering (PBR) materials. By analyzing the components of PBR materials, we choose to consider albedo, roughness, metalness, and bump maps. For albedo and bump maps, we leverage Stable Diffusion fine-tuned on synthetic data to extract these values, with novel usages of these fine-tuned models to obtain 3D consistent albedo UV and bump UV for generated objects. In terms of roughness and metalness maps, we adopt a semi-automatic process to provide room for interactive adjustment, which we believe is more practical. Extensive experiments demonstrate that our model is generally beneficial for various state-of-the-art generation methods, significantly boosting the quality and realism of their generated 3D objects, with natural relighting effects and substantially improved geometry.

cs.CV↗