arXiv subjects

Xuan Wang

Publications and source records attributed to Xuan Wang.

At least 163 records · Page 9Linked to original sources

arXiv2025

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS). However, 3DGS tends to overfit when trained with sparse views, limiting its generalization to novel viewpoints. In this paper, we address this overfitting issue by introducing Self-Ensembling Gaussian Splatting (SE-GS). We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training. A $\mathbfΔ$-model and a $\mathbfΣ$-model are jointly trained on the available images. The $\mathbfΔ$-model is dynamically perturbed based on rendering uncertainty across training steps, generating diverse perturbed models with negligible computational overhead. Discrepancies between the $\mathbfΣ$-model and these perturbed models are minimized throughout training, forming a robust ensemble of 3DGS models. This ensemble, represented by the $\mathbfΣ$-model, is then used to generate novel-view images during inference. Experimental results on the LLFF, Mip-NeRF360, DTU, and MVImgNet datasets demonstrate that our approach enhances NVS quality under few-shot training conditions, outperforming existing state-of-the-art methods. The code is released at: https://sailor-z.github.io/projects/SEGS.html.

cs.CV↗

arXiv2025

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense

Model Inversion (MI) attacks aim at leveraging the output information of target models to reconstruct privacy-sensitive training data, raising critical concerns regarding the privacy vulnerabilities of Deep Neural Networks (DNNs). Unfortunately, in tandem with the rapid evolution of MI attacks, the absence of a comprehensive benchmark with standardized metrics and reproducible implementations has emerged as a formidable challenge. This deficiency has hindered objective comparison of methodological advancements and reliable assessment of defense efficacy. To address this critical gap, we build the first practical benchmark named MIBench for systematic evaluation of model inversion attacks and defenses. This benchmark bases on an extensible and reproducible modular-based toolbox which currently integrates a total of 19 state-of-the-art attack and defense methods and encompasses 9 standardized evaluation protocols. Capitalizing on this foundation, we conduct extensive evaluation from multiple perspectives to holistically compare and analyze various methods across different scenarios, such as the impact of target resolution, model predictive power, defense performance and adversarial robustness.

cs.CV↗

arXiv2025

Posted Price versus Hybrid Mechanisms in Freight Transportation Marketplaces

We consider a freight platform that serves as an intermediary between shippers and carriers in a truckload transportation network. The platform's objective is to design a policy that determines prices for shippers and payments to carriers, as well as how carriers are matched to loads to be transported, to maximize its long-run average profit. We propose a two-stage decision framework to model carriers' load choice behavior, where carriers choose a lane according to the multinomial logit (MNL) model based on the platform's posted price in the first stage and book a load in the second stage. We analyze two types of carrier-side mechanisms commonly used by freight platforms: a posted price mechanism and a hybrid mechanism where carriers can either book loads at posted price or submit their bids in an auction. The proposed mechanisms are constructed using a fluid approximation model to incorporate carrier interactions in the freight network. We show that the hybrid mechanism has higher profits than the posted price mechanism. We prove tight bounds between these mechanisms for varying market sizes. The findings are validated through a numerical simulation using industry data from the U.S. freight market.

math.OC↗

arXiv2025

Hybrid Explicit Representation for Ultra-Realistic Head Avatars

We introduce a novel approach to creating ultra-realistic head avatars and rendering them in real-time (>30fps at $2048 \times 1334$ resolution). First, we propose a hybrid explicit representation that combines the advantages of two primitive-based efficient rendering techniques. UV-mapped 3D mesh is utilized to capture sharp and rich textures on smooth surfaces, while 3D Gaussian Splatting is employed to represent complex geometric structures. In the pipeline of modeling an avatar, after tracking parametric models based on captured multi-view RGB videos, our goal is to simultaneously optimize the texture and opacity map of mesh, as well as a set of 3D Gaussian splats localized and rigged onto the mesh facets. Specifically, we perform $α$-blending on the color and opacity values based on the merged and re-ordered z-buffer from the rasterization results of mesh and 3DGS. This process involves the mesh and 3DGS adaptively fitting the captured visual information to outline a high-fidelity digital avatar. To avoid artifacts caused by Gaussian splats crossing the mesh facets, we design a stable hybrid depth sorting strategy. Experiments illustrate that our modeled results exceed those of state-of-the-art approaches.

cs.GR↗

arXiv2025

Seed-Guided Topic Discovery with Out-of-Vocabulary Seeds

Discovering latent topics from text corpora has been studied for decades. Many existing topic models adopt a fully unsupervised setting, and their discovered topics may not cater to users' particular interests due to their inability of leveraging user guidance. Although there exist seed-guided topic discovery approaches that leverage user-provided seeds to discover topic-representative terms, they are less concerned with two factors: (1) the existence of out-of-vocabulary seeds and (2) the power of pre-trained language models (PLMs). In this paper, we generalize the task of seed-guided topic discovery to allow out-of-vocabulary seeds. We propose a novel framework, named SeeTopic, wherein the general knowledge of PLMs and the local semantics learned from the input corpus can mutually benefit each other. Experiments on three real datasets from different domains demonstrate the effectiveness of SeeTopic in terms of topic coherence, accuracy, and diversity.

cs.CL↗

arXiv2025

Bacterial dimensions sensitively regulate surface diffusivity and residence time

Run-and-tumble is a common but vital strategy that bacteria employ to explore environment suffused with boundaries, as well as to escape from entrapment. In this study we reveal how this strategy and the resulting dynamical behavior can be sensitively regulated by bacterial dimensions. Our results demonstrate that the logarithm of the surface residence time for bacteria with constant tumble bias is linearly related to a dimensionless parameter of bacterial intrinsic size characteristics, where a small variation in bacterial dimensions, which is natural in a suspension, reproduces well the experimentally observed large variation in bacterial residence time. Furthermore, our results predict that the optimal tumble bias corresponding to the maximum surface diffusivity depends strongly on bacterial dimensions, where the same small variation in bacterial dimensions gives rise to a strongly diversified optimal tumble bias and an order of magnitude change in surface diffusivity.

cond-mat.soft↗

arXiv2025

Quantum XYZ cyclic codes for biased noise

In some quantum computing architectures, Pauli noise is highly biased. Tailoring Quantum error-correcting codes to the biased noise may benefit reducing the physical qubit overhead without reducing the logical error rate. In this paper, we propose a family of quantum XYZ cyclic codes, which are the only one family of quantum cyclic codes with code distance increasing with code length to our best knowledge and have good error-correcting performance against biased noise. Our simulation results show that the quantum XYZ cyclic codes have $50\%$ code-capacity thresholds for all three types of pure Pauli noise and around $13\%$ code-capacity threshold for depolarizing noise. In the finite-bias regime, when the noise is biased towards Pauli $Z$ errors with noise bias ratios $η_Z=1000$, the corresponding code-capacity threshold is around $49\%$. Besides, we show that to reach the same code distance, the physical qubit overhead of XYZ cyclic code is much less than that of the XZZX surface code.

quant-ph↗

arXiv2025

SoMa: Identifying, Exploring, and Understanding the DRAM Communication Scheduling Space for DNN Accelerators

Modern Deep Neural Network (DNN) accelerators are equipped with increasingly larger on-chip buffers to provide more opportunities to alleviate the increasingly severe DRAM bandwidth pressure. However, most existing research on buffer utilization still primarily focuses on single-layer dataflow scheduling optimization. As buffers grow large enough to accommodate most single-layer weights in most networks, the impact of single-layer dataflow optimization on DRAM communication diminishes significantly. Therefore, developing new paradigms that fuse multiple layers to fully leverage the increasingly abundant on-chip buffer resources to reduce DRAM accesses has become particularly important, yet remains an open challenge. To address this challenge, we first identify the optimization opportunities in DRAM communication scheduling by analyzing the drawbacks of existing works on the layer fusion paradigm and recognizing the vast optimization potential in scheduling the timing of data prefetching from and storing to DRAM. To fully exploit these optimization opportunities, we develop a Tensor-centric Notation and its corresponding parsing method to represent different DRAM communication scheduling schemes and depict the overall space of DRAM communication scheduling. Then, to thoroughly and efficiently explore the space of DRAM communication scheduling for diverse accelerators and workloads, we develop an end-to-end scheduling framework, SoMa, which has already been developed into a compiler for our commercial accelerator product. Compared with the state-of-the-art (SOTA) Cocco framework, SoMa achieves, on average, a 2.11x performance improvement and a 37.3% reduction in energy cost simultaneously. Then, we leverage SoMa to study optimizations for LLM, perform design space exploration (DSE), and analyze the DRAM communication scheduling space through a practical example, yielding some..(more)

cs.AR↗

arXiv2025

Gravitational deflection of light in polar-axis plane of a moving Kerr-Newman black hole

The gravitational deflection of light signals restricted in the polar-axis plane of a moving Kerr-Newman (KN) black hole with a constant velocity along the polar axis is studied within the second post-Minkowskian (PM) approximation. For this purpose, the Lorentz boosting technique is adopted to obtain the exact metric of a moving KN black hole with an arbitrary constant velocity in Kerr-Schild coordinates for the first time. Based on the weak field limit of the exact metric, we then derive the equations of motion of test particles constrained in the polar-axis plane of a moving KN source whose velocity is along the polar axis and collinear with its angular momentum. An iterative technique is utilized subsequently in the calculations of the null deflection angle up to the 2PM order caused by the moving lens, and this deflection angle is found to be spin-independent. Finally, we discuss the influence of the motion of the lens on the gravitational deflection and estimate the possibility to detect this kinematical effect. Our work might be helpful for future astronomical observations.

gr-qc↗

arXiv2024

User-Aware Prefix-Tuning is a Good Learner for Personalized Image Captioning

Image captioning bridges the gap between vision and language by automatically generating natural language descriptions for images. Traditional image captioning methods often overlook the preferences and characteristics of users. Personalized image captioning solves this problem by incorporating user prior knowledge into the model, such as writing styles and preferred vocabularies. Most existing methods emphasize the user context fusion process by memory networks or transformers. However, these methods ignore the distinct domains of each dataset. Therefore, they need to update the entire caption model parameters when meeting new samples, which is time-consuming and calculation-intensive. To address this challenge, we propose a novel personalized image captioning framework that leverages user context to consider personality factors. Additionally, our framework utilizes the prefix-tuning paradigm to extract knowledge from a frozen large language model, reducing the gap between different language domains. Specifically, we employ CLIP to extract the visual features of an image and align the semantic space using a query-guided mapping network. By incorporating the transformer layer, we merge the visual features with the user's contextual prior knowledge to generate informative prefixes. Moreover, we employ GPT-2 as the frozen large language model. With a small number of parameters to be trained, our model performs efficiently and effectively. Our model outperforms existing baseline models on Instagram and YFCC100M datasets across five evaluation metrics, demonstrating its superiority, including twofold improvements in metrics such as BLEU-4 and CIDEr.

cs.CV↗

arXiv2024

Generating Unseen Nonlinear Evolution in Sea Surface Temperature Using a Deep Learning-Based Latent Space Data Assimilation Framework

Advances in data assimilation (DA) methods have greatly improved the accuracy of Earth system predictions. To fuse multi-source data and reconstruct the nonlinear evolution missing from observations, geoscientists are developing future-oriented DA methods. In this paper, we redesign a purely data-driven latent space DA framework (DeepDA) that employs a generative artificial intelligence model to capture the nonlinear evolution in sea surface temperature. Under variational constraints, DeepDA embedded with nonlinear features can effectively fuse heterogeneous data. The results show that DeepDA remains highly stable in capturing and generating nonlinear evolutions even when a large amount of observational information is missing. It can be found that when only 10% of the observation information is available, the error increase of DeepDA does not exceed 40%. Furthermore, DeepDA has been shown to be robust in the fusion of real observations and ensemble simulations. In particular, this paper provides a mechanism analysis of the nonlinear evolution generated by DeepDA from the perspective of physical patterns, which reveals the inherent explainability of our DL model in capturing multi-scale ocean signals.

physics.ao-ph↗

arXiv2024

Semiparametric Joint Modeling to Estimate the Treatment Effect on a Longitudinal Surrogate with Application to Chronic Kidney Disease Trials

In clinical trials where long follow-up is required to measure the primary outcome of interest, there is substantial interest in using an accepted surrogate outcome that can be measured earlier in time or with less cost to estimate a treatment effect. For example, in clinical trials of chronic kidney disease (CKD), the effect of a treatment is often demonstrated on a surrogate outcome, the longitudinal trajectory of glomerular filtration rate (GFR). However, estimating the effect of a treatment on the GFR trajectory is complicated by the fact that GFR measurement can be terminated by the occurrence of a terminal event, such as death or kidney failure. Thus, to estimate this effect, one must consider both the longitudinal outcome of GFR, and the terminal event process. Available estimation methods either impose restrictive parametric assumptions with corresponding maximum likelihood estimation that is computationintensive or other assumptions not appropriate for the GFR setting. In this paper, we build a semiparametric framework to jointly model the longitudinal outcome and the terminal event, where the model for the longitudinal outcome is semiparametric, and the relationship between the longitudinal outcome and the terminal event is nonparametric. The proposed semiparametric joint model is flexible and can be extended to include nonlinear trajectory of the longitudinal outcome easily. An estimating equation based method is proposed to estimate the treatment effect on the slope of the longitudinal outcome (e.g., GFR slope). Theoretical properties of the proposed estimators are derived. Finite sample performance of the proposed method is evaluated through simulation studies. We illustrate the proposed method using data from the Reduction of Endpoints in NIDDM with the Angiotensin II Antagonist Losartan (RENAAL) trail to examine the effect of Losartan on GFR slope.

stat.ME↗

arXiv2024

Model-free Approach to Evaluate a Censored Intermediate Outcome as a Surrogate for Overall Survival

Clinical trials or studies oftentimes require long-term and/or costly follow-up of participants to evaluate a novel treatment/drug/vaccine. There has been increasing interest in the past few decades in using short-term surrogate outcomes as a replacement of the primary outcome i.e., in using the surrogate outcome, which can potentially be observed sooner, to make inference about the treatment effect on the long-term primary outcome. Very few of the available statistical methods to evaluate a surrogate are applicable to settings where both the surrogate and the primary outcome are time-to-event outcomes subject to censoring. Methods that can handle this setting tend to require parametric assumptions or be limited to assessing only the restricted mean survival time. In this paper, we propose a non-parametric approach to evaluate a censored surrogate outcome, such as time to progression, when the primary outcome is also a censored time-to-event outcome, such as time to death, and the treatment effect of interest is the difference in overall survival. Specifically, we define the proportion of the treatment effect on the primary outcome that is explained (PTE) by the censored surrogate outcome in this context, and estimate this proportion by defining and deriving an optimal transformation of the surrogate information. Our approach provides the added advantage of relaxed assumptions to guarantee that the true PTE is within (0,1), along with being model-free. Finite sample performance of our estimators are illustrated via extensive simulation studies and a real data application examining progression-free survival as a surrogate for overall survival for patients with metastatic colorectal cancer.

stat.ME↗

arXiv2024

SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation

The rapid growth of the financial sector and the rising focus on Environmental, Social, and Governance (ESG) considerations highlight the need for advanced NLP tools. However, open-source LLMs proficient in both finance and ESG domains remain scarce. To address this gap, we introduce SusGen-30K, a category-balanced dataset comprising seven financial NLP tasks and ESG report generation, and propose TCFD-Bench, a benchmark for evaluating sustainability report generation. Leveraging this dataset, we developed SusGen-GPT, a suite of models achieving state-of-the-art performance across six adapted and two off-the-shelf tasks, trailing GPT-4 by only 2% despite using 7-8B parameters compared to GPT-4's 1,700B. Based on this, we propose the SusGen system, integrated with Retrieval-Augmented Generation (RAG), to assist in sustainability report generation. This work demonstrates the efficiency of our approach, advancing research in finance and ESG.

cs.CL↗

arXiv2024

Task Scheduling for Efficient Inference of Large Language Models on Single Moderate GPU Systems

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can shrink model sizes but often impair accuracy, making them unsuitable for practical applications. In this work, we introduce \modelname{}, a high-performance inference engine designed to speed up LLM inference without compromising model accuracy. \modelname{} incorporates three innovative methods to increase inference efficiency: 1) model partitioning to allow asynchronous processing of tasks across CPU computation, GPU computation, and CPU-GPU communication, 2) an adaptive partition algorithm to optimize the use of CPU, GPU, and PCIe communication capabilities, and 3) a token assignment strategy to handle diverse prompt and generation tasks during LLM inference. Comprehensive experiments were conducted with various LLMs such as Mixtral, LLaMA-2, Qwen, and PhiMoE across three test environments featuring different CPUs and GPUs. The experimental findings demonstrate that \modelname{} achieves speeds between $1.11\times$ to $1.80\times$ faster in decoding and $1.69\times$ to $6.33\times$ faster in pre-filling, leading to an overall speedup ranging from $1.25\times$ to $2.04\times$ compared to state-of-the-art solutions, llama.cpp and Fiddler.

cs.CE↗

arXiv2024

Distinguishing super-Nyquist frequencies via their temporal variation in $γ$ Doradus stars from continuous photometry

As mixed with real pulsations, the reflection of super-Nyquist frequencies (SNFs) pose a threat to asteroseismic properties. Although SNFs have been studied in several pulsating stars, a systematic survey remains scarcely explored. Here we propose a method to identify SNFs from Kepler and TESS photometry by characterizing their periodic frequency modulations using a sliding Fourier transform. After analyzing long cadence photometry in the Kepler legacy, we have identified 304 SNFs in 56 stars from 45607 frequencies in $\sim600$ $γ$ Doradus stars, corresponding to a fraction of approximately $0.67\%$ and $9.2\%$, respectively. Most SNFs are detected in the frequency range of pressure mode over 120 $μ$Hz and the fraction of SNF detection increases as frequency up to $\sim7\%$. We barely found two potential SNFs mixed with gravity modes in two $γ$ Doradus stars. These findings indicate that SNFs have a negligible impact on the global seismic properties, such as those derived from period spacing in $γ$ Doradus stars. However, we stress that SNFs must be carefully and systematically examined by this method in other pulsating stars, particularly $δ$ Scuti and hot B subdwarf stars, to establish a solid foundation for precise asteroseismolgy of various types of pulsators.

astro-ph.SR↗

arXiv2024

Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models

Food image composition requires the use of existing dish images and background images to synthesize a natural new image, while diffusion models have made significant advancements in image generation, enabling the construction of end-to-end architectures that yield promising results. However, existing diffusion models face challenges in processing and fusing information from multiple images and lack access to high-quality publicly available datasets, which prevents the application of diffusion models in food image composition. In this paper, we introduce a large-scale, high-quality food image composite dataset, FC22k, which comprises 22,000 foreground, background, and ground truth ternary image pairs. Additionally, we propose a novel food image composition method, Foodfusion, which leverages the capabilities of the pre-trained diffusion models and incorporates a Fusion Module for processing and integrating foreground and background information. This fused information aligns the foreground features with the background structure by merging the global structural information at the cross-attention layer of the denoising UNet. To further enhance the content and structure of the background, we also integrate a Content-Structure Control Module. Extensive experiments demonstrate the effectiveness and scalability of our proposed method.

cs.CV↗

arXiv2024

Heterogeneous Team Coordination on Partially Observable Graphs with Realistic Communication

Team Coordination on Graphs with Risky Edges (\textsc{tcgre}) is a recently proposed problem, in which robots find paths to their goals while considering possible coordination to reduce overall team cost. However, \textsc{tcgre} assumes that the \emph{entire} environment is available to a \emph{homogeneous} robot team with \emph{ubiquitous} communication. In this paper, we study an extended version of \textsc{tcgre}, called \textsc{hpr-tcgre}, with three relaxations: Heterogeneous robots, Partial observability, and Realistic communication. To this end, we form a new combinatorial optimization problem on top of \textsc{tcgre}. After analysis, we divide it into two sub-problems, one for robots moving individually, another for robots in groups, depending on their communication availability. Then, we develop an algorithm that exploits real-time partial maps to solve local shortest path(s) problems, with a A*-like sub-goal(s) assignment mechanism that explores potential coordination opportunities for global interests. Extensive experiments indicate that our algorithm is able to produce team coordination behaviors in order to reduce overall cost even with our three relaxations.

cs.RO↗