arXiv subjects

Kexin Zhang

Publications and source records attributed to Kexin Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs

Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary measures, including query identity and diversity, are treated as controllable objectives. Building on this view, we introduce AP-REASONER, an Affinity-Propagation-based factor-graph approach. With evolution-aware unary factors, exemplar-consistency factors, and two control knobs, AP-REASONER performs factor-graph reasoning through message passing to infer a fixed-budget MSA subset. Experiments on long-range contact prediction and conformational ensemble prediction show that AP-REASONER outperforms baseline subsamplers on structure-sensitive downstream tasks and enables controllable recovery of alternative protein conformations. These results highlight the value of modeling MSA subsampling as a controllable optimization problem, where factor-graph reasoning offers an effective alternative to heuristic selection.

cs.LG↗

arXiv2026

Intrinsically low thermal conductivity of stoichiometric lithium niobate:Experimental measurement and microscopic origin

With the rapid development of integrated electro-optic and nonlinear optical devices based on lithium niobate (LiNbO$_3$, LN), thermal management is becoming a critical area of focus. However, experimental measurement of thermal transport in stoichiometric LiNbO$_3$ (sLN) remains scarce, and the intrinsic microscopic mechanisms remain to be established. Here, we combine the laser pump-probe technique of frequency-domain thermoreflectance (FDTR) with state-of-the-art machine-learned atomistic simulations to comprehensively investigate thermal transport in sLN. The measured and simulated room-temperature thermal conductivity ($κ$) values of sLN agree well, which are orders-of-magnitude lower than that of many classic and emerging semiconductors such as silicon. Furthermore, the temperature-dependent $κ$ exhibits a $T^{-α}$ scaling with $α$ near unity, suggesting that thermal transport is dominated by intrinsic phonon-phonon scattering. By comparing sLN with cubic boron arsenide (cBAs) which serves as an ultrahigh-$κ$ benchmark, we reveal that harmonic properties are not responsible for the low $κ$ of sLN, which feature phonon heat capacity and group velocities that are either higher than or comparable to those in cBAs. Instead, the low $κ$ originates from substantially stronger anharmonicity and larger scattering phase space. These two factors collectively suppress phonon lifetimes by 1-2 orders of magnitude, leading to a maximum phonon mean free path of approximately 140 nm. As a result, notable size effects emerge in thin-film sLN below 1 $μ$m, with $κ$ dropping to half the bulk value at 10 nm. Altogether, our findings establish a fundamental understanding of thermal transport in sLN and provide atomistic insights for thermal management in advanced lithium niobate technologies.

cond-mat.mtrl-sci↗

arXiv2026

Parallel Complex Diffusion for Scalable Time Series Generation

Diffusion models learn data distributions indirectly through denoising, making the difficulty of generative modeling closely tied to the dependency structure of data. For time series, strong temporal dependence forces the noise / score estimator to recover highly entangled cross-time relationships, leading to the curse of entanglement. We mitigate this burden by changing the topology of the diffusion space: the Discrete Fourier Transform (DFT) decomposes temporal dependencies into spectral modes, diagonalizing second-order dependency structure and better aligning the data manifold with isotropic Gaussian noise and homogeneous diffusion dynamics. However, existing frequency-aware diffusion methods mainly use the DFT to design estimator blocks under temporal DDPM/SDE frameworks, while frequency-native diffusion paths face a mathematical barrier from complex-valued dynamics. We propose PaCoDi (Parallel Complex Diffusion), a frequency-native diffusion framework that constructs the diffusion path in the spectral domain while replacing the complex-valued estimator with parallel real-valued estimators for real and imaginary components. Theoretically, we prove the statistical orthogonality of spectral Gaussian noise, establish quadrature forward transitions and conditional reverse factorization, and extend discrete PaCoDi to continuous-time spectral SDEs through a Spectral Wiener Process. We further introduce a Mean Field Theory approximation with an Interactive Correction Branch to handle marginal coupling, and exploit Hermitian symmetry to reduce 50% attention FLOPs without information loss. Extensive experiments on unconditional and conditional time series generation demonstrate superior generative quality and computational efficiency against 5 SOTA baselines in 5 benchmarks, respectively. Code is available at https://github.com/RongyaoCai/PaCoDi.

cs.LG↗

arXiv2026

From Observations to States: Latent Time Series Forecasting

Deep learning has achieved strong performance in Time Series Forecasting (TSF). However, we identify a critical representation paradox, termed Latent Chaos: models with accurate predictions often learn latent representations that are temporally disordered and lack continuity. We attribute this to the dominant observation-space forecasting paradigm, where minimizing point-wise errors on noisy and partially observed data encourages shortcut solutions instead of the recovery of underlying system dynamics. To address this, we propose Latent Time Series Forecasting (LatentTSF), a paradigm that shifts TSF from observation regression to latent state prediction. LatentTSF employs an AutoEncoder to project each observation into a learned latent state space and performs forecasting entirely in this space, allowing the model to focus on learning structured temporal dynamics. We provide an information-theoretic analysis showing that the latent objectives can be motivated as surrogates for maximizing mutual information between predicted and ground-truth latent states and future observations. Extensive experiments on widely-used benchmarks confirm that LatentTSF effectively mitigates latent chaos, yielding consistent improvements in both forecasting accuracy and representation quality. Our code is available at https://github.com/Muyiiiii/LatentTSF.

cs.LG↗

arXiv2026

On Privacy-Preserving Image Transmission in Low-Altitude Networks: A Swin Transformer-Based Framework with Federated Learning

The rapid development of low-altitude economy has driven the proliferation of Unmanned Aerial Vehicle (UAV) applications, including logistics, inspection, and emergency response. However, transmitting high-volume image data from UAVs to ground stations faces significant challenges due to limited bandwidth and stringent privacy requirements. To address these issues, a Semantic Communication (SC) framework based on Federated Learning (FL) is proposed for efficient and privacy-preserving image transmission. A Swin Transformer-based Semantic Communication (STSC) architecture is designed to extract multi-scale semantic features under constrained bandwidth conditions. Dedicated communication and computing nodes are deployed on UAVs to enhance real-time coverage and flexibility. Meanwhile, a FL mechanism enables global model training across distributed devices without sharing raw data, thus preserving user privacy. Simulation experiments conducted on the CIFAR-10 dataset demonstrate that the proposed STSC framework achieves at least 5.7 dB improvement in Peak Signal-to-Noise Ratio (PSNR) compared to DeepJSCC baselines, while also showing superior convergence and generalization performance. The framework effectively integrates UAV-assisted deployment with SC and privacy protection, offering a practical solution for bandwidth-constrained image transmission in low-altitude networks.

eess.IV↗

arXiv2026

The Procrustean Bed of Time Series: The Optimization Bias in Point-wise Loss Functions

Intuitively, a more deterministic time series should be easier to forecast. However, point-wise loss functions (e.g., MSE and MAE), serving as differentiable surrogates for the ideal optimization target, score each timestamp independently and therefore disregard temporal dependence. This mismatch induces a systematic optimization bias that cannot be eliminated merely by improving model expressiveness or optimizer. To formalize this issue, we define the Expectation of Optimization Bias (EOB) as the Kullback--Leibler divergence between the true joint distribution and the factorized i.i.d. surrogate induced by the point-wise paradigm. Under covariance-stationary Gaussian assumptions, we derive closed-form expressions for the stochastic component of EOB, establishing it as an irreducible lower bound on the total bias in linear systems, and further extend it to nonlinear regimes through a Gaussian mixture model lower bound. Crucially, we prove this bias is governed intrinsically by two data properties, i.e., sequence length and Structural Signal-to-Noise Ratio (SSNR), regardless of specific model architecture, optimizer, or point-wise loss forms. This theory motivates a principled debiasing program based on sequence length reduction and structural orthogonalization, which we instantiate through DFT/DWT combined with a novel harmonized $\ell_p$ norm. Extensive experiments validate the predicted SSNR--horizon dynamics, resolve the classic trigonometric fitting failure as an objective-induced pathology, and demonstrate substantial plug-and-play gains. Notably, on iTransformer, our proposed objective reduces average MSE/MAE by 5.2%/5.0% in forecasting across 11 datasets and by 27.4%/19.4% in imputation across 9 datasets.

cs.LG↗

arXiv2026

Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso Regression

We propose using a modified conductance-based method to study the mixing time of an important class of two-block Gibbs samplers, the data augmentation (DA) algorithm. %, which is of prominent interest in both theoretical and empirical research. Using this method, we prove the first non-asymptotic polynomial upper bounds on mixing times of three important DA algorithms: DA algorithms for Bayesian Probit regression (Albert and Chib, 1993, ProbitDA) and Bayesian Logit regression (Polson, Scott, and Windle, 2013, LogitDA), and Bayesian Lasso Regression (Park and Casella, 2008, Rajaratnam et al., 2015, LassoDA). Concretely, for ProbitDA and LogitDA, we demonstrate a tight bound that explicitly depends on the design matrix and prior covariance matrix. Under the assumption that data are independently generated from either a sub-Gaussian or log-concave distribution and properly scaled, the bound implies that with $η$-warm start, parameter dimension $d$, and sample size $n$, with high probability over data, the two algorithms require $\mathcal{O}\left(n\log \left(\frac{\log η}ε\right)\right)$ steps to obtain samples with at most $ε$ error in TV, KL, or $χ^2$ distance. Meanwhile, we show that under minimal data assumptions, LassoDA requires $\mathcal{O}\left(d^2(d\log d +n \log n)^2 \log \left(\fracηε\right)\right)$ steps to achieve $ε$-accuracy in TV distance. The results are generally applicable to settings with large $n$ and large $d$, including settings with highly imbalanced response data in Probit and Logit regression. We compare them with the best known guarantees of Langevin Monte Carlo and Metropolis Adjusted Langevin Algorithm. We evaluate our theoretical results using numerical examples, and discuss the mixing times of the three algorithms under feasible initialization.

math.ST↗

arXiv2026

AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report

This report presents an overview of the AIM 2025 RipSeg Challenge, a competition designed to advance techniques for automatic rip current segmentation in still images. Rip currents are dangerous, fast-moving flows that pose a major risk to beach safety worldwide, making accurate visual detection an important and underexplored research task. The challenge builds on RipVIS, the largest available rip current dataset, and focuses on single-class instance segmentation, where precise delineation is critical to fully capture the extent of rip currents. The dataset spans diverse locations, rip current types, and camera orientations, providing a realistic and challenging benchmark. In total, $75$ participants registered for this first edition, resulting in $5$ valid test submissions. Teams were evaluated on a composite score combining $F_1$, $F_2$, $AP_{50}$, and $AP_{[50:95]}$, ensuring robust and application-relevant rankings. The top-performing methods leveraged deep learning architectures, domain adaptation techniques, pretrained models, and domain generalization strategies to improve performance under diverse conditions. This report outlines the dataset details, competition framework, evaluation metrics, and final results, providing insights into the current state of rip current segmentation. We conclude with a discussion of key challenges, lessons learned from the submissions, and future directions for expanding RipSeg.

cs.CV↗

arXiv2026

MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents

Shortcuts such as APIs and deep-links have emerged as efficient complements to flexible GUI operations, fostering a promising hybrid paradigm for MLLM-based mobile automation. However, systematic evaluation of GUI-shortcut hybrid agents remains largely underexplored. To bridge this gap, we introduce MAS-Bench, a benchmark that pioneers the evaluation of GUI-shortcut hybrid agents with a specific focus on the mobile domain. Beyond merely using predefined shortcuts, MAS-Bench assesses an agent's capability to autonomously generate shortcuts by discovering and creating reusable, low-cost workflows. It features 139 complex tasks across 11 real-world applications, a knowledge base of 88 predefined shortcuts (APIs, deep-links, RPA scripts), and 9 evaluation metrics. Experiments demonstrate that hybrid agents achieve up to 68.3% success rate and 39% greater execution efficiency than GUI-only counterparts. Furthermore, our evaluation framework effectively reveals the quality gap between predefined and agent-generated shortcuts, validating its capability to assess shortcut generation methods. MAS-Bench addresses the lack of systematic benchmarks for GUI-shortcut hybrid mobile agents, providing a foundational platform for future advancements in creating more efficient and robust intelligent agents. Project page: https://pengxiang-zhao.github.io/MAS-Bench.

cs.AI↗

arXiv2026

A Variable-Spot-Size and Multi-Frequency Square-Pulsed Source (SPS) Approach for Comprehensive Characterization of Anisotropic Thermal Transport Properties in Multilayered Thin Films

Multilayered thin-film structures are frequently encountered in industrial applications, where accurate thermal property characterization is essential for performance optimization. These films, typically ranging from nanometers to micrometers in thickness, often exhibit anisotropic thermal conductivity and non-bulk heat capacity, which are challenging to measure. In this study, we introduce a variable-spot-size and multi-frequency square-pulsed source (SPS) method for the simultaneous determination of anisotropic thermal conductivities, heat capacities, and interfacial thermal conductance in multilayered systems. By leveraging a broad modulation frequency range (1 Hz to 10 MHz) and tunable laser spot sizes, the SPS method enhances sensitivity to different thermal parameters across layers. We validate this approach on a silicon-on-insulator (SOI) sample comprising a 1.59 um Si layer, 1.03 um SiO2 layer, and a silicon substrate with a 122 nm aluminum (Al) transducer. The SPS method successfully extracts seven key thermal parameters, including the in-plane and cross-plane thermal conductivities and heat capacity of the Si film, the thermal conductivity and heat capacity of the SiO2 layer, the thermal conductivity of the substrate, and the interfacial thermal conductance between Al and Si. Temperature-dependent measurements from 80 to 500 K showed excellent agreement with literature values and first-principles predictions, confirming the method's accuracy and reliability. These results demonstrate the SPS method as a powerful tool for comprehensive thermal characterization of complex multilayered structures, with implications for both fundamental research and practical applications.

physics.app-ph↗

arXiv2026

Depth-Resolved Thermal Conductivity of HFCVD Diamond Films via Square-Pulsed Thermometry

The integration of high-thermal-conductivity diamond films onto silicon carbide (SiC) substrates offers a promising pathway for thermal management in high-power electronic devices. Here, we investigate the depth-dependent thermal conductivity of a ~5 μm-thick diamond film grown on SiC by hot-filament chemical vapor deposition (HFCVD) using square-pulsed source (SPS) thermometry. Electron backscatter diffraction (EBSD) and transmission electron microscopy (TEM) reveal pronounced grain coarsening from the nucleation interface to the film surface. By combining frequency-dependent thermal penetration with a depth-resolved thermal transport model, we quantitatively reconstruct the thermal conductivity profile. The thermal conductivity increases sharply from ~60 W m^(-1) K^(-1) near the nucleation region to ~200 W m^(-1) K^(-1) at the surface, directly reflecting the underlying microstructural evolution. These results provide a physically grounded understanding of graded heat transport in HFCVD diamond and offer practical guidance for engineering diamond-based thermal management layers for next-generation power devices.

cond-mat.mtrl-sci↗

arXiv2026

Towards Training-Free Scene Text Editing

Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and adaptability. In this paper, we propose TextFlow, a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS) to enable flexible, high-fidelity text manipulation without additional training. Specifically, FMS preserves the structural and style consistency by modeling the visual flow of characters and background regions, while AttnBoost enhances the rendering of textual content through attention-based guidance. By jointly leveraging these complementary modules, our approach performs end-to-end text editing through semantic alignment and spatial refinement in a plug-and-play manner. Extensive experiments demonstrate that our framework achieves visual quality and text accuracy comparable to or superior to those of training-based counterparts, generalizing well across diverse scenes and languages. This study advances scene text editing toward a more efficient, generalizable, and training-free paradigm. Code is available at https://github.com/lyb18758/TextFlow

cs.CV↗

arXiv2026

Asymptotics of the principal eigenvalue of an elliptic operator on closed and orientable Riemannian manifolds

This paper investigates the asymptotic behavior of the principal eigenvalue $λ(s)$, as $s\to+\infty$, for the following elliptic eigenvalue problem \begin{equation*}\label{E} -Δ_{M}u-s\langle \nabla_M f, \nabla_M u\rangle_g +c u=λ(s)u, \end{equation*} defined on an orientable and closed Riemannian manifold $(M,g)$. Assuming $f$ is a Morse function defined on $M$, we find that the limit $\lim\limits_{s\to+\infty} λ(s)$ is determined by the minimum value of the function $c$ over the set of the maximum points of $f$, a result that is independent of the curvature of manifold.

math.AP↗

arXiv2026

OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations. Prior approaches rely on offline preference optimization and static metric aggregation, which are often non-interpretable and prone to pseudo-diversity under strong conditioning. We propose OARS, a process-aware online alignment framework built on COMPASS, a MLLM-based reward that evaluates the LR to SR transition by jointly modeling fidelity preservation and perceptual gain with an input-quality-adaptive trade-off. To train COMPASS, we curate COMPASS-20K spanning synthetic and real degradations, and introduce a three-stage perceptual annotation pipeline that yields calibrated, fine-grained training labels. Guided by COMPASS, OARS performs progressive online alignment from cold-start flow matching to full-reference and finally reference-free RL via shallow LoRA optimization for on-policy exploration. Extensive experiments and user studies demonstrate consistent perceptual improvements while maintaining fidelity, achieving state-of-the-art performance on Real-ISR benchmarks.

cs.CV↗

arXiv2026

Breaking Smooth-Motion Assumptions: A UAV Benchmark for Multi-Object Tracking in Complex and Adverse Conditions

The rapid movements and agile maneuvers of unmanned aerial vehicles (UAVs) induce significant observational challenges for multi-object tracking (MOT). However, existing UAV-perspective MOT benchmarks often lack these complexities, featuring predominantly predictable camera dynamics and linear motion patterns. To address this gap, we introduce DynUAV, a new benchmark for dynamic UAV-perspective MOT, characterized by intense ego-motion and the resulting complex apparent trajectories. The benchmark comprises 42 video sequences with over 1.7 million bounding box annotations, covering vehicles, pedestrians, and specialized industrial categories such as excavators, bulldozers and cranes. Compared to existing benchmarks, DynUAV introduces substantial challenges arising from ego-motion, including drastic scale changes and viewpoint changes, as well as motion blur. Comprehensive evaluations of state-of-the-art trackers on DynUAV reveal their limitations, particularly in managing the intertwined challenges of detection and association under such dynamic conditions, thereby establishing DynUAV as a rigorous benchmark. We anticipate that DynUAV will serve as a demanding testbed to spur progress in real-world UAV-perspective MOT, and we will make all resources available at link.

cs.CV↗

arXiv2026

SeedProteo: Accurate De Novo All-Atom Design of Protein Binders

We present SeedProteo, a diffusion-based model for de novo all-atom protein design. We demonstrate how to repurpose a cutting-edge folding architecture into a powerful generative design framework by effectively integrating self-conditioning features. Extensive benchmarks highlight the model's capabilities across two distinct tasks: in unconditional generation, SeedProteo exhibits superior length generalization and structural diversity, maintaining robustness for long sequences and complex topologies; in binder design, it achieves state-of-the-art performance among open-source methods, attaining the highest in-silico design success rates, structural diversity and novelty. Finally, we validate SeedProteo through wet-lab assays on two therapeutic targets, achieving hit rates of 70%-80% and picomolar-level binding affinities, establishing leading results. To facilitate community adoption, we provide public access to SeedProteo via a webserver (https://seedfold.io/proteinDesign).

q-bio.BM↗

arXiv2026

How Well Can 3D Accessibility Guidelines Support XR Development? An Interview Study with XR Practitioners in Industry

While accessibility (a11y) guidelines exist for 3D games and virtual worlds, their applicability to extended reality (XR)'s unique interaction paradigms (e.g., spatial tracking, kinesthetic interactions) remains unexplored. XR practitioners need practical guidance to successfully implement a11y guidelines under real-world constraints. We present the first evaluation of existing 3D a11y guidelines applied to XR development through semi-structured interviews with 25 XR practitioners across diverse organization contexts. We assessed 20 commonly-agreed a11y guidelines from six major resources across visual, motor, cognitive, speech, and hearing domains, comparing practitioners' development practices against guideline applicability to XR. Our investigation reveals that guidelines can be highly effective when designed as transformation catalysts rather than compliance checklists, but fundamental mismatches exist between existing 3D guidelines and XR requirements, creating both implementation barriers and design gaps. This work provides foundational insights towards developing a11y guidelines and support tools that address XR's distinct characteristics.

cs.HC↗

arXiv2026

GenDR: Lighten Generative Detail Restoration

Although recent research applying text-to-image (T2I) diffusion models to real-world super-resolution (SR) has achieved remarkable progress, the misalignment of their targets leads to a suboptimal trade-off between inference speed and detail fidelity. Specifically, the T2I task requires multiple inference steps to synthesize images matching to prompts and reduces the latent dimension to lower generating difficulty. Contrariwise, SR can restore high-frequency details in fewer inference steps, but it necessitates a more reliable variational auto-encoder (VAE) to preserve input information. However, most diffusion-based SRs are multistep and use 4-channel VAEs, while existing models with 16-channel VAEs are overqualified diffusion transformers, e.g., FLUX (12B). To align the target, we present a one-step diffusion model for generative detail restoration, GenDR, distilled from a tailored diffusion model with a larger latent space. In detail, we train a new SD2.1-VAE16 (0.9B) via representation alignment to expand the latent space without increasing the model size. Regarding step distillation, we propose consistent score identity distillation (CiD) that incorporates SR task-specific loss into score distillation to leverage more SR priors and align the training target. Furthermore, we extend CiD with adversarial learning and representation alignment (CiDA) to enhance perceptual quality and accelerate training. We also polish the pipeline to achieve a more efficient inference. Experimental results demonstrate that GenDR achieves state-of-the-art performance in both quantitative metrics and visual fidelity.

cs.CV↗