arXiv subjects

Yiming Zhou

Publications and source records attributed to Yiming Zhou.

At least 19 recordsLinked to original sources

arXiv2026

TransNRank: Towards Accurate Neoantigen Ranking with Transformer

Personalized neoantigen prediction is challenging due to the scarcity of positive samples, the noise of the experimental data, the severe class imbalance trait and the complex of immunogenicity features. Prior arts, such as linear regression and XGBoost fail to model long-range dependencies and contextual relationships within peptide features, therefore the performance of neoantigen positive recall rate is limited. In this paper, we present a novel deep learning framework based on Transformer, coined as TransNRank. By leveraging the self-attention mechanism, our model captures both local and global feature contexts, enabling more accurate recognition of immunogenic neoantigens. A positive-aware training objective is utilized to handle the class imbalance problem, assigning more weights to those few positive samples. Extensive experiments are performed on NCI, TESLA and HiTIDE datasets. Notably, our TransNRank can push the upper bound top 20 recall rate of neoantigen prediction from 46.9% (45 from 96) to 53.1% (51 from 96), while reducing the training epochs from 200 epochs to 20 epochs. Furthermore, we analyze the features contribution based on TransNRank and find that the mutation at anchor and TCGA expression level play an unexpected important role in neoantigen prediction, and removing insignificant features to reduce the input dimensionality of peptides does not drastically impair the overall performance of the model. Our paradigm not only streamlines the prediction pipeline but also sets a new state-of-the-art for neoantigen discovery, with broad implications for accurate immuno-oncology.

cs.CE↗

arXiv2026

Standardizing Medical Images at Scale for AI

Deep learning has achieved remarkable success in medical image analysis, yet its performance remains highly sensitive to the heterogeneity of clinical data. Differences in imaging hardware, staining protocols, and acquisition conditions produce substantial domain shifts that degrade model generalization across institutions. Here we present a physics-based data preprocessing framework based on the PhyCV (Physics-Inspired Computer Vision) family of algorithms, which standardizes medical images through deterministic transformations derived from optical physics. The framework models images as spatially varying optical fields that undergo a virtual diffractive propagation followed by coherent phase detection. This process suppresses non-semantic variability such as color and illumination differences while preserving diagnostically relevant texture and structural features. When applied to histopathological images from the Camelyon17-WILDS benchmark, PhyCV preprocessing improves out-of-distribution breast-cancer classification accuracy from 70.8% (Empirical Risk Minimization baseline) to 90.9%, matching or exceeding data-augmentation and domain-generalization approaches at negligible computational cost. Because the transform is physically interpretable, parameterizable, and differentiable, it can be deployed as a fixed preprocessing stage or integrated into end-to-end learning. These results establish PhyCV as a generalizable data refinery for medical imaging-one that harmonizes heterogeneous datasets through first-principles physics, improving robustness, interpretability, and reproducibility in clinical AI systems.

eess.IV↗

arXiv2026

Extremal problems in uniformly dense hypergraphs and digraphs

The uniform Tur\'an density $\pi_{u}(F)$ of a $3$-uniform hypergraph (or $3$-graph) $F$ is the supremum of all $d$ such that there exist infinitely many $F$-free $3$-graphs $H$ in which every induced subhypergraph on a linearly sized vertex set has edge density at least $d$. Determining $\pi_{u}(F)$ for a given $3$-graph $F$ was proposed by Erd\H{o}s and S\'os in the 1980s, yet only a few cases are known. In particular, it remains open whether $1/2$ can occur as a value of $\pi_{u}$. In this paper, we establish a novel connection between Tur\'an-type extremal problems for digraphs and uniform Tur\'an densities of $3$-graphs. Using digraph extremal results, we give the first verifiable conditions for $3$-graphs $F$ with $\pi_{u}(F) = (r-1)/r$ and $\pi_{u}(F) = (r-1)^2/r^2$ for all $r \ge 2$, and identify the corresponding $3$-graphs. In particular, these $3$-graph classes contain some specific $3$-graphs, such as $K^{(3)-}_4$. We also present a sufficient condition ensuring $\pi_{u}(F)=4/27$ and construct $3$-graphs satisfying it; in particular, our examples are different from the tight $3$-uniform cycles whose uniform Tur\'an density $4/27$ was determined in [{Trans. Amer. Math. Soc. 376 (2023), 4765-4809}]. Finally, we give a short proof of the existence of $3$-graphs $F$ with $\pi_{u}(F)=1/27$, originally established by Garbe, Kr\'al' and Lamaison [{Israel J. Math. 259 (2024), 701-726}] via the hypergraph regularity method.

math.CO↗

arXiv2026

Percolation-driven $\beta$ -relaxation enables resonant acceleration of crystallization in amorphous phase-change materials

Amorphous phase-change materials enable fast and reversible switching in optical and electronic devices, yet crystallization kinetics are still controlled primarily through empirical thermal protocols. Here we identify a microscopic picture governing crystallization in the prototypical phase-change material Ge2Sb2Te5, in which crystallization pathways are organized by the percolation of mobile atomic networks associated with $\beta$-relaxation. We show that this percolation transition distinguishes the dominance of diffusion-driven and diffusionless nucleation and growth during crystallization processes. We further demonstrate that frequency-selected ultrasonic excitation, applied in conjunction with heating, accelerates crystallization by enhancing percolation-mediated atomic dynamics. This acceleration is maximized near the $\beta$-relaxation frequency, consistent with resonant excitation of mobile atoms. Our results establish a direct link between glassy relaxation, atomic-scale percolation, and crystallization, and introduce a new route to modulating phase-change kinetics through targeted excitation of fundamental glassy dynamics.

cond-mat.mtrl-sci↗

arXiv2026

Differentially Private Perturbed Push-Sum Protocol and Its Application in Non-Convex Optimization

In decentralized networks, nodes cannot ensure that their shared information will be securely preserved by their neighbors, making privacy vulnerable to inference by curious nodes. Adding calibrated random noise before communication to satisfy differential privacy offers a proven defense; however, most existing methods are tailored to specific downstream tasks and lack a general, protocol-level privacy-preserving solution. To bridge this gap, we propose Differentially Private Perturbed Push-Sum (DPPS), a lightweight differential privacy protocol for decentralized communication. Since protocol-level differential privacy introduces the unique challenge of obtaining the sensitivity for each communication round, DPPS introduces a novel sensitivity estimation mechanism that requires each node to compute and broadcast only one scalar per round, enabling rigorous differential privacy guarantees. This design allows DPPS to serve as a plug-and-play, low-cost privacy-preserving solution for downstream applications built on it. To provide a concrete instantiation of DPPS and better balance the privacy-utility trade-off, we design PartPSP, a privacy-preserving decentralized algorithm for non-convex optimization that integrates a partial communication mechanism. By partitioning model parameters into local and shared components and applying DPPS only to the shared parameters, PartPSP reduces the dimensionality of consensus data, thereby lowering the magnitude of injected noise and improving optimization performance. We theoretically prove that PartPSP converges under non-convex objectives and, with partial communication, achieves better optimization performance under the same privacy budget. Experimental results validate the effectiveness of DPPS's privacy-preserving and demonstrate that PartPSP outperforms existing privacy-preserving decentralized optimization algorithms.

cs.DC↗

arXiv2026

Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data

Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on RGB inputs. Recent efficient variants reduce computation but still depend on large-scale training. We propose a lightweight RGB-D fusion framework that augments EfficientViT-SAM with monocular depth priors. Depth maps are generated with a pretrained estimator and fused mid-level with RGB features through a dedicated depth encoder. Trained on only 11.2k samples (less than 0.1\% of SA-1B), our method achieves higher accuracy than EfficientViT-SAM, showing that depth cues provide strong geometric priors for segmentation.

cs.CV↗

arXiv2026

PiXTime: A Model for Federated Time Series Forecasting with Heterogeneous Data across Nodes

While collaborative forecasting on distributed time series is highly desirable, directly pooling localized datasets is often impractical due to data sharing constraints. Federated learning offers a promising alternative, yet conventional federated learning algorithms require homogeneous model architectures, which are incompatible with the structural discrepancies, such as unaligned temporal resolutions and mismatched variable channels, commonly observed across decentralized nodes. To bridge this gap, we introduce PiXTime, a novel Transformer-based framework designed to natively accommodate and leverage structurally heterogeneous temporal data. At its core, PiXTime adopts a parameter-decoupling architecture, strategically partitioning the model into localized personalized modules and a globally aggregated shared backbone. Specifically, node-specific local modules act as dimensional adapters, projecting raw sequences of diverse lengths into a unified representation space. Concurrently, a globally synchronized VE Table injects consistent categorical identities into the feature space, allowing the shared backbone to collaboratively learn and generalize representations across inconsistent variable distributions. Comprehensive evaluations on multiple benchmarks demonstrate that PiXTime achieves state-of-the-art performance in heterogeneous federated environments, while maintaining robust superiority in standard homogeneous and centralized forecasting settings.

cs.LG↗

arXiv2025

FUSCO: High-Performance Distributed Data Shuffling via Transformation-Communication Fusion

Large-scale Mixture-of-Experts (MoE) models rely on \emph{expert parallelism} for efficient training and inference, which splits experts across devices and necessitates distributed data shuffling to route each token to its assigned experts. However, existing communication libraries handle this shuffling poorly; its overhead can account for over half of end-to-end runtime. We present FUSCO, an MoE-friendly communication library that achieves efficient and lightweight data shuffling through fused data transformation and communication, based on the key observation that MoE's expert-major data layout conflicts with the device-major layout expected by communication operations. FUSCO captures the fine-grained data layout, which is then interpreted by a pipelined communication engine that performs the required shuffling efficiently along the communication path. Lightweight planning and load-balancing mechanisms complement the engine by eliminating redundant communication and dispersing traffic. Evaluations on representative benchmarks illustrate that FUSCO achieves up to 3.84$\times$ and 2.01$\times$ speedups over NCCL and DeepEP (the state-of-the-art MoE communication library), respectively. In end-to-end MoE tasks, compared to NCCL and DeepEP, FUSCO reduces the training latency by 1.17-1.39$\times$ and 1.10-1.19$\times$, and lowers the first-token generation latency in inference by 1.09-1.25$\times$ and 1.06-1.16$\times$.

cs.DC↗

arXiv2025

Vertex-distinguishing edge coloring of graphs

Let $k \ge 1$ be an integer and let $G$ be a nonempty simple graph. An \emph{edge-$k$-coloring} $\varphi$ of $G$ is an assignment of colors from $\{1,\ldots,k\}$ to the edges of $G$ such that no two adjacent edges receive the same color. For a vertex $v \in V(G)$, we write $\varphi(v)$ for the set of colors assigned to the edges incident with $v$. The coloring $\varphi$ is called \emph{vertex-distinguishing} if $\varphi(u) \ne \varphi(v)$ for every pair of distinct vertices $u,v \in V(G)$. A vertex-distinguishing edge-$k$-coloring exists if and only if $G$ has at most one isolated vertex and no isolated edge. The least integer $k$ for which such a coloring exists is called the \emph{vertex-distinguishing chromatic index} of $G$, denoted $\chi'_{vd}(G)$. In 1997, Burris and Schelp conjectured that for every graph $G$ with at most one isolated vertex and no isolated edge, $ k(G) \;\le\; \chi'_{vd}(G) \;\le\; k(G)+1$, where $k(G)$ is the natural lower bound required for a vertex-distinguishing coloring in $G$. In 2004, Balister, Kostochka, Li, and Schelp verified the conjecture for graphs $G$ satisfying $\Delta(G) \ge \sqrt{2|V(G)|} + 4 $ and $\delta(G) \ge 5$. For graphs that do not satisfy these conditions, the best known general upper bound on $\chi'_{vd}(G)$ remains $|V(G)| + 1$, established in 1999 by Bazgan, Harkat-Benhamdine, Li, and Wo\'zniak. In this paper, we prove that $\chi'_{vd}(G) \le \floor{5.5k(G)+6.5}$, which represents a substantial improvement over the bound $|V(G)| + 1$ whenever $k(G) = o(|V(G)|)$. We further show that $\chi'_{vd}(G) \le k(G) + 3$, for all $d$-regular graphs $G$ with $d \ge \log_2 |V(G)|\geq 8$.

math.CO↗

arXiv2025

Classifier-Centric Adaptive Framework for Open-Vocabulary Camouflaged Object Segmentation

Open-vocabulary camouflaged object segmentation requires models to segment camouflaged objects of arbitrary categories unseen during training, placing extremely high demands on generalization capabilities. Through analysis of existing methods, it is observed that the classification component significantly affects overall segmentation performance. Accordingly, a classifier-centric adaptive framework is proposed to enhance segmentation performance by improving the classification component via a lightweight text adapter with a novel layered asymmetric initialization. Through the classification enhancement, the proposed method achieves substantial improvements in segmentation metrics compared to the OVCoser baseline on the OVCamo benchmark: cIoU increases from 0.443 to 0.493, cSm from 0.579 to 0.658, and cMAE reduces from 0.336 to 0.239. These results demonstrate that targeted classification enhancement provides an effective approach for advancing camouflaged object segmentation performance.

cs.CV↗

arXiv2025

Scalable Hessian-free Proximal Conjugate Gradient Method for Nonconvex and Nonsmooth Optimization

This work studies a composite minimization problem involving a differentiable function q and a nonsmooth function h, both of which may be nonconvex. This problem is ubiquitous in signal processing and machine learning yet remains challenging to solve efficiently, particularly when large-scale instances, poor conditioning, and nonconvexity coincide. To address these challenges, we propose a proximal conjugate gradient method (PCG) that matches the fast convergence of proximal (quasi-)Newton algorithms while reducing computation and memory complexity, and is especially effective for spectrally clustered Hessians. Our key innovation is to form, at each iteration, an approximation to the Newton direction based on CG iterations to build a majorization surrogate. We define this surrogate in a curvature-aware manner and equip it with a CG-derived isotropic weight, guaranteeing majorization of a local second-order model of q along the given direction. To better preserve majorization after the proximal step and enable further approximation refinement, we scale the CG direction by the ratio between the Cauchy step length and a step size derived from the largest Ritz value of the CG tridiagonal. All curvature is accessed via Hessian-vector products computed by automatic differentiation, keeping the method Hessian-free. Convergence to first-order critical points is established. Numerical experiments on CS-MRI with nonconvex regularization and on dictionary learning, against benchmark methods, demonstrate the efficiency of the proposed approach.

eess.SP↗

arXiv2025

Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments

Current Simultaneous Localization and Mapping (SLAM) methods based on Neural Radiance Fields (NeRF) or 3D Gaussian Splatting excel in reconstructing static 3D scenes but struggle with tracking and reconstruction in dynamic environments, such as real-world scenes with moving elements. Existing NeRF-based SLAM approaches addressing dynamic challenges typically rely on RGB-D inputs, with few methods accommodating pure RGB input. To overcome these limitations, we propose Dy3DGS-SLAM, the first 3D Gaussian Splatting (3DGS) SLAM method for dynamic scenes using monocular RGB input. To address dynamic interference, we fuse optical flow masks and depth masks through a probabilistic model to obtain a fused dynamic mask. With only a single network iteration, this can constrain tracking scales and refine rendered geometry. Based on the fused dynamic mask, we designed a novel motion loss to constrain the pose estimation network for tracking. In mapping, we use the rendering loss of dynamic pixels, color, and depth to eliminate transient interference and occlusion caused by dynamic objects. Experimental results demonstrate that Dy3DGS-SLAM achieves state-of-the-art tracking and rendering in dynamic environments, outperforming or matching existing RGB-D methods.

cs.CV↗

arXiv2025

An experimental study of using artificial reefs as scour protection around an offshore wind monopile

Artificial reefs (ARs) are man-made structures deployed on the seabed to support benthic marine ecosystems. Their presence significantly damps the local flow and therefore can be used for scour protection of offshore wind monopiles. Although the concept appears feasible, the underlying flow-sediment process is very complex and has yet been systematically investigated. To fill in this gap, a set of fixed-bed flume tests were conducted to reveal the hydrodynamic details of two typical AR shapes (cubic and hemisphere) tightly placed around a monopile in a 3x3 pattern. In parallel, a set of live-bed tests were conducted to demonstrate the AR's efficiency in scour protection. The cubic ARs almost eliminate the downward flow on the upstream side of the monopile and reduces the wake flow by 50-80%. The hemisphere ARs also significantly weaken the wake flow but guide descending flow in front of the monopile. While cubic ARs decrease upstream and downstream scour depth by up to 100%, their edge scour can lead to ARs displacement and hence reduce scour protection. The hemisphere ARs provided less scour reduction, but also less edge scour, making them more adaptive to morphology changes. Based on these findings, an optimized AR layout was proposed.

physics.flu-dyn↗

arXiv2024

Adaptive Weighting Push-SUM for Decentralized Optimization with Statistical Diversity

Statistical diversity is a property of data distribution and can hinder the optimization of a decentralized network. However, the theoretical limitations of the Push-SUM protocol reduce the performance in handling the statistical diversity of optimization algorithms based on it. In this paper, we theoretically and empirically mitigate the negative impact of statistical diversity on decentralized optimization using the Push-SUM protocol. Specifically, we propose the Adaptive Weighting Push-SUM protocol, a theoretical generalization of the original Push-SUM protocol where the latter is a special case of the former. Our theoretical analysis shows that, with sufficient communication, the upper bound on the consensus distance for the new protocol reduces to $O(1/N)$, whereas it remains at $O(1)$ for the Push-SUM protocol. We adopt SGD and Momentum SGD on the new protocol and prove that the convergence rate of these two algorithms to statistical diversity is $O(N/T)$ on the new protocol, while it is $O(Nd/T)$ on the Push-SUM protocol, where $d$ is the parameter size of the training model. To address statistical diversity in practical applications of the new protocol, we develop the Moreau weighting method for its generalized weight matrix definition. This method, derived from the Moreau envelope, is an approximate optimization of the distance penalty of the Moreau envelope. We verify that the Adaptive Weighting Push-SUM protocol is practically more efficient than the Push-SUM protocol via deep learning experiments.

cs.DC↗

arXiv2024

Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods

Exploring the capabilities of Neural Radiance Fields (NeRF) and Gaussian-based methods in the context of 3D scene reconstruction, this study contrasts these modern approaches with traditional Simultaneous Localization and Mapping (SLAM) systems. Utilizing datasets such as Replica and ScanNet, we assess performance based on tracking accuracy, mapping fidelity, and view synthesis. Findings reveal that NeRF excels in view synthesis, offering unique capabilities in generating new perspectives from existing data, albeit at slower processing speeds. Conversely, Gaussian-based methods provide rapid processing and significant expressiveness but lack comprehensive scene completion. Enhanced by global optimization and loop closure techniques, newer methods like NICE-SLAM and SplaTAM not only surpass older frameworks such as ORB-SLAM2 in terms of robustness but also demonstrate superior performance in dynamic and complex environments. This comparative analysis bridges theoretical research with practical implications, shedding light on future developments in robust 3D scene reconstruction across various real-world applications.

cs.CV↗

arXiv2024

Physical Data Embedding for Memory Efficient AI

Deep neural networks (DNNs) have achieved exceptional performance across various fields by learning complex, nonlinear mappings from large-scale datasets. However, they face challenges such as high memory requirements and computational costs with limited interpretability. This paper introduces an approach where master equations of physics are converted into multilayered networks that are trained via backpropagation. The resulting general-purpose model effectively encodes data in the properties of the underlying physical system. In contrast to existing methods wherein a trained neural network is used as a computationally efficient alternative for solving physical equations, our approach directly treats physics equations as trainable models. We demonstrate this physical embedding concept with the Nonlinear Schr\"odinger Equation (NLSE), which acts as trainable architecture for learning complex patterns including nonlinear mappings and memory effects from data. The network embeds data representation in orders of magnitude fewer parameters than conventional neural networks when tested on time series data. Notably, the trained "Nonlinear Schr\"odinger Network" is interpretable, with all parameters having physical meanings. This interpretability offers insight into the underlying dynamics of the system that produced the data. The proposed method of replacing traditional DNN feature learning architectures with physical equations is also extended to the Gross-Pitaevskii Equation, demonstrating the broad applicability of the framework to other master equations of physics. Among our results, an ablation study quantifies the relative importance of physical terms such as dispersion, nonlinearity, and potential energy for classification accuracy. We also outline the limitations of this approach as it relates to generalizability.

cs.LG↗

arXiv2024

Mapping New Realities: Ground Truth Image Creation with Pix2Pix Image-to-Image Translation

Generative Adversarial Networks (GANs) have significantly advanced image processing, with Pix2Pix being a notable framework for image-to-image translation. This paper explores a novel application of Pix2Pix to transform abstract map images into realistic ground truth images, addressing the scarcity of such images crucial for domains like urban planning and autonomous vehicle training. We detail the Pix2Pix model's utilization for generating high-fidelity datasets, supported by a dataset of paired map and aerial images, and enhanced by a tailored training regimen. The results demonstrate the model's capability to accurately render complex urban features, establishing its efficacy and potential for broad real-world applications.

cs.CV↗

arXiv2024

Integrating AI in NDE: Techniques, Trends, and Further Directions

The digital transformation is fundamentally changing our industries, affecting planning, execution as well as monitoring of production processes in a wide range of application fields. With product line-ups becoming more and more versatile and diverse, the necessary inspection and monitoring sparks significant novel requirements on the corresponding Nondestructive Evaluation (NDE) systems. The establishment of increasingly powerful approaches to incorporate Artificial Intelligence (AI) may provide just the needed innovation to solve some of these challenges. In this paper we provide a comprehensive survey about the usage of AI methods in NDE in light of the recent innovations towards NDE 4.0. Since we cannot discuss each NDE modality in one paper, we limit our attention to magnetic methods, ultrasound, thermography, as well as optical inspection. In addition to reviewing recent AI developments in each field, we draw common connections by pointing out NDE-related tasks that have a common underlying mathematical problem and categorizing the state of the art according to the corresponding sub-tasks. In so doing, interdisciplinary connections are drawn that provide a more complete overall picture.

eess.SP↗