arXiv subjects

Xinyang Li

Publications and source records attributed to Xinyang Li.

At least 37 records · Page 2Linked to original sources

arXiv2025

Physical Signatures of Supercritical Fluid Boundaries

In the supercritical fluid (SCF) region, at temperatures and pressures above the critical point, the thermodynamic singularity separating liquids and gases no longer exists. Recent arguments based on thermodynamics and critical scalings have revived the proposal that the SCF constitutes an intermediate state of matter, separated from the liquid and gas by two supercritical boundaries, the $L^\pm$ lines. However, until now, the nature of the supercritical state and the physical signatures of these boundaries have remained elusive. Here, we demonstrate that the SCF is characterized by distinct structural, transport, and dynamical behavior. Specifically, the spatial arrangement of particles-captured by the radial distribution function-as well as the diffusion coefficient, shear viscosity, and velocity autocorrelation function in the SCF regime are qualitatively different from those in both the liquid and gas states and exhibit clear physical signatures upon crossing the $L^\pm$ lines. Our theoretical predictions are validated by molecular dynamics simulations of argon and are further supported by existing experimental evidence. These results provide a clear physical foundation for a refined phase diagram of matter in the supercritical region, comprising three distinct states-gas, supercritical fluid, and liquid-separated by two crossover boundaries obeying universal scaling laws.

cond-mat.stat-mech↗

arXiv2025

Influence of Barlens on the Bulge Parameters in the 2D Image Decomposition

Recent observations and simulations have shown that a buckled bar in the face-on view can be considered as a combination of a long flat bar and a short round barlens (corresponding to the boxy/peanut bulge in the edge-on view). However, the barlens component can be misidentified as the bulge, potentially leading to inaccurate bulge parameter measurements in two-dimensional (2D) image decomposition. Our goal is to explore the optimal method for modeling the barlens component and to understand its impact on bulge parameter measurements in 2D image decomposition. We first analyze mock images from two different simulations (with/without bulge) to verify our decomposition method. We then apply the method to two nearby barred galaxies, NGC 1533 and NGC 7329, from the Carnegie-Irvine Galaxy Survey (CGS). Using GALFIT, we conduct 2D image decomposition by gradually increasing the complexity of model configurations. We also explore the effects of inclination by projecting the simulated galaxy to various viewing angles and analyzing the variations in bulge and barlens parameters. From the mock images, we find that the bulge-to-total ratio (B/T) could be overestimated by 50$\%$ without considering the barlens component; the S\'ersic index and effective radius of the bulge are also affected to varying degrees. The decomposition results of the two CGS galaxies are consistent with our mock image tests. Uncertainties of the structural parameters of the bulge and barlens are larger at higher inclination angels due to the strong projection effect in the central region. Our findings underscore the necessity of accurately modeling the barlens, revealing that its inclusion in 2D image decomposition can lead to a decrease in B/T by $\sim$30-50$\%$, with other bulge parameters, such as the S\'ersic index and effective radius, also affected.

astro-ph.GA↗

arXiv2025

XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding

Current auto-regressive models can generate high-quality, topologically precise meshes; however, they necessitate thousands-or even tens of thousands-of next-token predictions during inference, resulting in substantial latency. We introduce XSpecMesh, a quality-preserving acceleration method for auto-regressive mesh generation models. XSpecMesh employs a lightweight, multi-head speculative decoding scheme to predict multiple tokens in parallel within a single forward pass, thereby accelerating inference. We further propose a verification and resampling strategy: the backbone model verifies each predicted token and resamples any tokens that do not meet the quality criteria. In addition, we propose a distillation strategy that trains the lightweight decoding heads by distilling from the backbone model, encouraging their prediction distributions to align and improving the success rate of speculative predictions. Extensive experiments demonstrate that our method achieves a 1.7x speedup without sacrificing generation quality. Our code will be released.

cs.GR↗

arXiv2025

MoDA: Multi-modal Diffusion Architecture for Talking Head Generation

Talking head generation with arbitrary identities and speech audio remains a crucial problem in the realm of the virtual metaverse. Recently, diffusion models have become a popular generative technique in this field with their strong generation capabilities. However, several challenges remain for diffusion-based methods: 1) inefficient inference and visual artifacts caused by the implicit latent space of Variational Auto-Encoders (VAE), which complicates the diffusion process; 2) a lack of authentic facial expressions and head movements due to inadequate multi-modal information fusion. In this paper, MoDA handles these challenges by: 1) defining a joint parameter space that bridges motion generation and neural rendering, and leveraging flow matching to simplify diffusion learning; 2) introducing a multi-modal diffusion architecture to model the interaction among noisy motion, audio, and auxiliary conditions, enhancing overall facial expressiveness. In addition, a coarse-to-fine fusion strategy is employed to progressively integrate different modalities, ensuring effective feature fusion. Experimental results demonstrate that MoDA improves video diversity, realism, and efficiency, making it suitable for real-world applications. Project Page: https://lixinyyang.github.io/MoDA.github.io/

cs.GR↗

arXiv2025

DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion

Reconstructing 3D objects from a single image remains challenging, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they typically assume fully visible inputs and fail when parts of the object are occluded, resulting in degraded 3D reconstruction quality. We propose DeOcc-1-to-3, an end-to-end framework for occlusion-aware multi-view generation that synthesizes six structurally consistent novel views directly from a single occluded image, enabling reliable 3D reconstruction without prior inpainting or manual annotations. Our self-supervised training pipeline leverages occluded-unoccluded image pairs and pseudo-ground-truth views to teach the model structure-aware completion and view consistency. Without modifying the original architecture, we fully fine-tune the view synthesis model to jointly learn completion and multi-view generation. Additionally, we introduce the first benchmark for occlusion-aware reconstruction, covering diverse occlusion levels, object categories, and masking patterns, providing a standardized protocol for future evaluation.

cs.CV↗

arXiv2025

From Black Boxes to Transparent Minds: Evaluating and Enhancing the Theory of Mind in Multimodal Large Language Models

As large language models evolve, there is growing anticipation that they will emulate human-like Theory of Mind (ToM) to assist with routine tasks. However, existing methods for evaluating machine ToM focus primarily on unimodal models and largely treat these models as black boxes, lacking an interpretative exploration of their internal mechanisms. In response, this study adopts an approach based on internal mechanisms to provide an interpretability-driven assessment of ToM in multimodal large language models (MLLMs). Specifically, we first construct a multimodal ToM test dataset, GridToM, which incorporates diverse belief testing tasks and perceptual information from multiple perspectives. Next, our analysis shows that attention heads in multimodal large models can distinguish cognitive information across perspectives, providing evidence of ToM capabilities. Furthermore, we present a lightweight, training-free approach that significantly enhances the model's exhibited ToM by adjusting in the direction of the attention head.

cs.AI↗

arXiv2025

Universal supercritical thermodynamics for black holes

We investigate thermodynamic crossovers for black holes in the supercritical regime beyond the critical point, where small and large black holes become indistinguishable from the conventional viewpoint. We establish a refined supercritical phase diagram that comprehensively characterizes the phases of small, large, and indistinguishable black holes, delineated by two supercritical crossover lines. The universal scaling laws of these crossover lines are fully verified using the thermodynamics of RN-AdS black holes in both the standard framework and the extended thermodynamic phase space, where the cosmological constant is treated as pressure, as well as in four other black hole systems. Analogies with supercritical crossovers observed in liquid-gas and liquid-liquid phase transitions are discussed. This work can be extended to more complex black hole backgrounds and offers valuable insights into the fundamental nature of black hole thermodynamics.

gr-qc↗

arXiv2025

Voyager: Real-Time Splatting City-Scale Gaussians on Resource-Constrained Devices

3D Gaussian splatting (3DGS) is an emerging technique for photorealistic 3D scene rendering. However, rendering city-scale 3DGS scenes on resource-constrained mobile devices in real-time remains a significant challenge due to two compute-intensive stages: level-of-detail (LoD) search and rasterization. In this paper, we propose Voyager, an effective solution to accelerate city-scale 3DGS rendering on mobile devices. Our key insight is that, under normal user motion, the number of newly visible Gaussians within the view frustum remains roughly constant. Leveraging this temporal correlation, we propose a temporal-aware LoD search to identify the necessary Gaussians for the remaining rendering stages. For the remaining rendering process, we accelerate the bottleneck stage, rasterization, via preemptive $\alpha$-filtering. With all optimizations above, our system can deliver low-latency, city-scale 3DGS rendering on mobile devices. Compared to existing solutions, Voyager achieves up to 6.6$\times$ speedup and 85\% energy savings with superior rendering quality.

cs.GR↗

arXiv2025

Toward Robust Single-Photon Perception for Robots: A Condition-Aware Active Learning Approach

LiDAR-based perception plays a fundamental role in modern robotic systems for environment understanding and navigation. Single-photon LiDAR (SPL) extends conventional LiDAR by enabling photon-efficient 3D sensing under challenging conditions such as long-range operation, low-albedo targets, and limited signal returns. However, developing SPL perception models for real-world robotic applications remains difficult because annotated SPL data are costly to obtain and model performance can vary substantially across imaging conditions. In this paper, we present the first active learning framework tailored to the SPL sensing modality rather than a specific downstream task. Our method introduces a physics-grounded, imaging condition-aware sampling strategy that uses synthetic SPL variants to characterize how candidate samples respond to changes in sensing conditions. By jointly modeling prediction uncertainty, sample diversity, and sensitivity to photon-level imaging variations, the proposed approach prioritizes samples that are informative for improving labeling efficiency and robustness. Extensive experiments on synthetic and real-world SPL datasets demonstrate that our method substantially reduces annotation requirements while maintaining strong performance across image-level and dense prediction settings. On synthetic data, our approach achieves 97% classification accuracy using only 1.5% labeled samples. On real-world data, it maintains 90% accuracy with 8.2% labeled samples, outperforming the strongest baseline by 6%. Segmentation results further show that the same condition-aware acquisition principle improves annotation efficiency and robustness across imaging conditions. These results establish a modality-aware active learning strategy for data-efficient SPL perception, with the potential to extend to a broader range of downstream tasks.

eess.IV↗

arXiv2025

SynergyAmodal: Deocclude Anything with Text Control

Image deocclusion (or amodal completion) aims to recover the invisible regions (\ie, shape and appearance) of occluded instances in images. Despite recent advances, the scarcity of high-quality data that balances diversity, plausibility, and fidelity remains a major obstacle. To address this challenge, we identify three critical elements: leveraging in-the-wild image data for diversity, incorporating human expertise for plausibility, and utilizing generative priors for fidelity. We propose SynergyAmodal, a novel framework for co-synthesizing in-the-wild amodal datasets with comprehensive shape and appearance annotations, which integrates these elements through a tripartite data-human-model collaboration. First, we design an occlusion-grounded self-supervised learning algorithm to harness the diversity of in-the-wild image data, fine-tuning an inpainting diffusion model into a partial completion diffusion model. Second, we establish a co-synthesis pipeline to iteratively filter, refine, select, and annotate the initial deocclusion results of the partial completion diffusion model, ensuring plausibility and fidelity through human expert guidance and prior model constraints. This pipeline generates a high-quality paired amodal dataset with extensive category and scale diversity, comprising approximately 16K pairs. Finally, we train a full completion diffusion model on the synthesized dataset, incorporating text prompts as conditioning signals. Extensive experiments demonstrate the effectiveness of our framework in achieving zero-shot generalization and textual controllability. Our code, dataset, and models will be made publicly available at https://github.com/imlixinyang/SynergyAmodal.

cs.CV↗

arXiv2025

Computation of Capacity-Distortion-Cost Functions for Continuous Memoryless Channels

This paper aims at computing the capacity-distortion-cost (CDC) function for continuous memoryless channels, which is defined as the supremum of the mutual information between channel input and output, constrained by an input cost and an expected distortion of estimating channel state. Solving the optimization problem is challenging because the input distribution does not lie in a finite-dimensional Euclidean space and the optimal estimation function has no closed form in general. We propose to adopt the Wasserstein proximal point method and parametric models such as neural networks (NNs) to update the input distribution and estimation function alternately. To implement it in practice, the importance sampling (IS) technique is used to calculate integrals numerically, and the Wasserstein gradient descent is approximated by pushing forward particles. The algorithm is then applied to an integrated sensing and communications (ISAC) system, validating theoretical results at minimum and maximum distortion as well as the random-deterministic trade-off.

cs.IT↗

arXiv2025

Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs

Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives. The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities and providing a structured foundation for open-vocabulary understanding. Based on the graph structure, we design an efficient reprojection strategy that lifts 2D semantic features onto the superpoints, avoiding costly multi-view iterative training. The resulting representation ensures strong 3D semantic coherence and naturally supports hierarchical understanding, enabling both coarse- and fine-grained open-vocabulary perception within a unified semantic field. Extensive experiments demonstrate that our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over $30\times$ faster. Our code will be available at https://github.com/Atrovast/THGS.

cs.CV↗

arXiv2025

AnomalyPainter: Vision-Language-Diffusion Synergy for Zero-Shot Realistic and Diverse Industrial Anomaly Synthesis

While existing anomaly synthesis methods have made remarkable progress, achieving both realism and diversity in synthesis remains a major obstacle. To address this, we propose AnomalyPainter, a zero-shot framework that breaks the diversity-realism trade-off dilemma through synergizing Vision Language Large Model (VLLM), Latent Diffusion Model (LDM), and our newly introduced texture library Tex-9K. Tex-9K is a professional texture library containing 75 categories and 8,792 texture assets crafted for diverse anomaly synthesis. Leveraging VLLM's general knowledge, reasonable anomaly text descriptions are generated for each industrial object and matched with relevant diverse textures from Tex-9K. These textures then guide the LDM via ControlNet to paint on normal images. Furthermore, we introduce Texture-Aware Latent Init to stabilize the natural-image-trained ControlNet for industrial images. Extensive experiments show that AnomalyPainter outperforms existing methods in realism, diversity, and generalization, achieving superior downstream performance.

cs.CV↗

arXiv2025

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization

Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size.

cs.CV↗

arXiv2025

Learning to Predict Global Atrial Fibrillation Dynamics from Sparse Measurements

Catheter ablation of Atrial Fibrillation (AF) consists of a one-size-fits-all treatment with limited success in persistent AF. This may be due to our inability to map the dynamics of AF with the limited resolution and coverage provided by sequential contact mapping catheters, preventing effective patient phenotyping for personalised, targeted ablation. Here we introduce FibMap, a graph recurrent neural network model that reconstructs global AF dynamics from sparse measurements. Trained and validated on 51 non-contact whole atria recordings, FibMap reconstructs whole atria dynamics from 10% surface coverage, achieving a 210% lower mean absolute error and an order of magnitude higher performance in tracking phase singularities compared to baseline methods. Clinical utility of FibMap is demonstrated on real-world contact mapping recordings, achieving reconstruction fidelity comparable to non-contact mapping. FibMap's state-spaces and patient-specific parameters offer insights for electrophenotyping AF. Integrating FibMap into clinical practice could enable personalised AF care and improve outcomes.

cs.LG↗

arXiv2025

Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting

Recent advancements in 3D scene editing have been propelled by the rapid development of generative models. Existing methods typically utilize generative models to perform text-guided editing on 3D representations, such as 3D Gaussian Splatting (3DGS). However, these methods are often limited to texture modifications and fail when addressing geometric changes, such as editing a character's head to turn around. Moreover, such methods lack accurate control over the spatial position of editing results, as language struggles to precisely describe the extent of edits. To overcome these limitations, we introduce DYG, an effective 3D drag-based editing method for 3D Gaussian Splatting. It enables users to conveniently specify the desired editing region and the desired dragging direction through the input of 3D masks and pairs of control points, thereby enabling precise control over the extent of editing. DYG integrates the strengths of the implicit triplane representation to establish the geometric scaffold of the editing results, effectively overcoming suboptimal editing outcomes caused by the sparsity of 3DGS in the desired editing regions. Additionally, we incorporate a drag-based Latent Diffusion Model into our method through the proposed Drag-SDS loss function, enabling flexible, multi-view consistent, and fine-grained editing. Extensive experiments demonstrate that DYG conducts effective drag-based editing guided by control point prompts, surpassing other baselines in terms of editing effect and quality, both qualitatively and quantitatively. Visit our project page at https://quyans.github.io/Drag-Your-Gaussian.

cs.GR↗

arXiv2025

SE(3)-Based Trajectory Optimization and Target Tracking in UAV-Enabled ISAC Systems

This paper presents a novel approach to enhance sensing capabilities in UAV-enabled MIMO-OFDM ISAC systems by leveraging UAV mobility as a mono-static radar. By integrating uniform planar arrays (UPAs) and modeling the UAV dynamics in $SE(3)$, we address key challenges such as 3D space sensing and trajectory design. We propose a target tracking scheme using extended Kalman filtering (EKF) in $SE(3)$, along with trajectory optimization based on the conditional Posterior Cramer-Rao bound (CPCRB). Numerical results demonstrate the effectiveness of the proposed trajectory design in enhancing performance of target tracking and physical parameter estimation in UAV-enabled MIMO-OFDM ISAC systems.

eess.SP↗

arXiv2025

A Simultaneous Decoding Approach to Joint State and Message Communications

The capacity-distortion (C-D) trade-offs for joint state and message communications (JSMC) over single- and multi-user channels are investigated, where the transmitters have access to generalized state information and feedback while the receivers jointly decode the messages and estimate the channel state. A coding scheme is proposed based on backward simultaneous decoding of messages and compressed state descriptions without the need for the Wyner-Ziv random binning technique. For the point-to-point channel, the proposed scheme results in the optimal C-D function. For the state-dependent discrete memoryless degraded broadcast channel (SD-DMDBC), the successive refinement method is adopted for designing multi-stage state descriptions. With the simultaneous decoding approach, the derived achievable region is shown to be larger than the region obtained by the sequential decoding approach that is utilized in existing works. As for the state-dependent discrete memoryless multiple access channel (SD-DMMAC), in addition to the proposed method, Willem's coding strategy is applied to enable partial collaboration between transmitters through the feedback links. Moreover, the state descriptions are shown to enhance both communication and state estimation performance. Examples are provided for the derived results to verify the analysis, either numerically or analytically. With particular focus, simple but representative integrated sensing and communications (ISAC) systems are also considered, and their fundamental performance limits are studied.

cs.IT↗