Search arXiv⌕ Search

arXiv subjects

Xinliang Zhang

Publications and source records attributed to Xinliang Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness

We study the stochastic second-order oracle complexity of solving smooth convex finite-sum optimization with $n$ components. Very recently, Tsedenov \& Kovalev (2026) showed that the minimax optimal complexity under averaged smoothness and convexity is $\tildeΘ(n + n^{6/7} ε^{-2/7})$ by establishing nearly matching upper and lower bounds. In this paper, we show that individual smoothness and convexity provably enable further acceleration, where the lower complexity bound is $Ω(n+ n^{5/7} ε^{-2/7})$ under this stronger assumption. Then, by establishing a novel second-order self-bounding inequality, we design a new Taylor-corrected lazy Newton method, which can lead to a better complexity of $\tilde{\mathcal{O}}(n + n^{5/7} ε^{-2/7})$ by applying the optimal Monteiro-Svaiter acceleration, matching our lower bound up to only logarithmic factors.

math.OC↗
arXiv2026

Near-Optimal Convex Optimization with Lazy Second-Order Oracles

This paper studies the complexity of convex optimization using lazy second-order oracles (Doikov, Chayti, and Jaggi, ICML 2023), where an algorithm queries gradients every iteration and Hessians once per $m$ iterations. Under this setting, we show a lower bound of $Ω(m+ m^{1/7} ε^{-2/7})$ on the number of total iterations to find an $ε$-solution using a novel block zero-chain construction. Then we propose a novel method that achieves a new upper bound of $\tilde{\mathcal{O}}(m+ m^{1/7} ε^{-2/7})$, which significantly improves the prior one (Chen, Liu, Luo, and Zhang, COLT 2026) of $\tilde{\mathcal{O}}(m+ m^{13/21} ε^{-2/7})$ and is tight up to logarithmic factors.

math.OC↗
arXiv2026

SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection

Changes in sensor height and viewpoint alter object-level point distributions, making cross-platform LiDAR unsupervised domain adaptation (UDA) difficult. Self-training uses labeled source scans and unlabeled target scans, yet a retained prediction may provide a useful target location while enclosing sparse foreground returns, background clutter, or points inconsistent with the predicted box. We refer to this mismatch as box-point inconsistency. We introduce SimFuse3D, which preserves the target placement and repairs the associated pseudo object using measured geometry from labeled source scans. Object Memory retrieves a similar labeled source instance. Target Simulation places the retrieved source geometry at the target location, aligns its points with the target viewing geometry, and filters the aligned crop to approximate the target observation. Confidence-Guided Multi-Stage Localization Reweighting (CMLR) maps each target pseudo-object confidence score to a bounded weight shared by RPN localization and R-CNN box regression. All components operate only during adaptation, leaving the detector architecture and inference graph unchanged. Across six cross-platform transfers, SimFuse3D consistently outperforms Pi3DET-Net and achieves the best performance among the compared adaptation methods on nearly all metrics. On nuScenes-to-KITTI, it ranks first among the compared adaptation methods with both evaluated detectors.

cs.CV↗
arXiv2026

Photonic sequential logic circuits for stateful intelligence

By virtue of its high energy efficiency and ultra-low latency, optical computing is regarded as a highly promising computing paradigm in the post-Moore era. However, constructing a Turing-complete optical computing for next-generation AI paradigms, from large language models (LLMs) to real-time autonomous systems, requires not only stateless function mapping units, but also sequential logic circuits capable of storing historical states and processing dynamic data streams. Current photonic processors lack this temporal memory, and the state-of-the-art optical sequential schemes remain impractical due to signal attenuation and the absence of programmable clock control. Here, we propose a photonic sequential logic circuits (PSLC) to resolve this fundamental challenge. Leveraging a uniquely designed active optoelectronic feedback network, we construct a complete family of photonic sequential logic devices, comprehensively encompassing set-reset latches, D latches, and edge-triggered master-slave D flip-flops. We further construct photonic sequence detectors and asynchronous counters, verifying the capability of the architecture to execute both synchronous and asynchronous sequential tasks, alongside its system-level scalability. Ultimately, by combining the constructed PSLC with stateless function mapping units, we establish a universal hardware paradigm for stateful intelligence. We validate this paradigm by executing highly reliable real-time drone obstacle avoidance in the physical domain, alongside Shakespearean-style text generation in the symbolic domain. This work provides the crucial missing piece of the puzzle for optical computing to achieve stateful computing, establishing a definitive hardware foundation for advancing toward Turing-complete optical computing.

physics.optics↗
arXiv2026

Silicon nitride nanophotonics for low-redundancy 3D convolution

Three-dimensional (3D) convolution extracts correlations in high-dimensional data, but overlapping receptive fields introduce substantial redundant data movement. Here, we demonstrate a silicon nitride 3D optical convolution accelerator (3D-OCA) that reconstructs receptive fields through coordinate-aware wavelength-to-group-delay mapping. A deterministically serialized input tensor is broadcast onto multiple wavelength channels, and a chirped waveguide Bragg grating (CWBG) compensates the temporal offsets associated with 3D kernel coordinates. This arrangement continuously forms neighboring receptive fields without repeatedly rearranging and loading their shared input samples. The integrated CWBG provides a differential group delay of 2691 ps and a dispersion of 124.8 ps/nm. At 20 Gbaud, spatial-spectral processing of Indian Pines data yields convolution agreement with a coefficient of determination up to 0.997 and 97.9% classification accuracy, compared with 98.9% digitally. At 10 Gbaud, the optical convolution layer preserves spatiotemporal features and achieves 92.5% accuracy on a four-class KTH video-recognition task. These results establish low-redundancy streaming 3D convolution across spectral and temporal data dimensions using the same optical delay architecture.

physics.optics↗
arXiv2026

Monolithically integrated photonic neural network at driven-dissipative criticality

Artificial intelligence increasingly demands computing architectures capable of adaptive representation, temporal information processing, and robust operation under uncertainty. However, conventional photonic neural architectures typically rely on predefined computational operations and separate functional modules, limiting the ability of physical systems to exploit their intrinsic dynamics for intelligence. Here, we demonstrate a monolithically integrated active photonic neural network (APNN) that harnesses driven-dissipative criticality as a physical computational resource. By balancing optical excitation and dissipation, the system operates near a critical regime where weak input-dependent variations are amplified into separable representations while stable attractor dynamics are preserved. The APNN integrates an optoelectronic nonlinear array and a reconfigurable symmetric optical coupling matrix on a silicon photonic chip, enabling recurrent physical computation within a compact closed loop. We demonstrate nonlinear classification with 95.2% accuracy using only 100 training samples and 44 trainable parameters. And it remains robust at an ultralow signal-to-noise ratio of -30 dB. Beyond static recognition, the same driven-dissipative dynamics enable long-range temporal feature extraction from electrocardiogram signals and associative recovery of corrupted patterns through attractor-based relaxation. These results establish driven-dissipative criticality as a unified mechanism for representation enhancement, temporal information retention, and error-resilient computation, providing a pathway toward scalable photonic systems in which intelligence emerges from intrinsic physical dynamics.

physics.optics↗
arXiv2026

Optimal High-Order Methods for Solving Monotone Variational Inequalities

We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method, NPE, converges at a rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subclass of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved this rate to $\tilde{\mathcal{O}}( T^{-1.75})$. However, the result has a substantial gap compared to the lower bound of $Ω(T^{-2.5})$ established by Chen et al. (2026). In this paper, we propose a novel second-order method that achieves the optimal rate of $\mathcal{O}(T^{-2.5})$. Our algorithm also extends to higher-order methods: for any integer $ p \ge 1$, we obtain a $p$th-order method with a convergence rate of $\mathcal{O}(T^{-(3p-1)/2})$, matching the known lower bounds and therefore establishing optimal rates across all orders.

math.OC↗
arXiv2026

Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks

Many real-world scenarios can be represented using graph-structured data. However, traditional GNNs that transmit messages based on first-order neighbors have long faced several fundamental contradictions: increasing depth leads to over-smoothing, long-range dependencies cause over-compression, fixed neighborhoods restrict the receptive field, and on heterophilous graphs, topological neighbors become a source of noise. Although many works have addressed these issues individually, few mechanisms can simultaneously alleviate all of these challenges. To address the aforementioned problems, we propose a Position Encoding-Based Deformable Spatial Aggregation Module (PEBDSAM) that solves them all in one step. Specifically, we utilize a deformable mechanism in the position space to identify relevant nodes to supplement the original first-order neighbor information of GNNs, allowing traditional GNNs to adapt to heterophilous scenarios. Through diagnostic experiments, we obtained several major findings: current offsets fail to have any effect; subsequently, we analyzed the causes of offset failure and why model performance still improves even after offset failure, pointing out future research directions. Based on these diagnostic experiments, we streamlined the original PEBDSAM, resulting in a simplified version, which we call the Position Encoding-Based Spatial Aggregation Module (PEBSAM). In addition, we propose a PEBSAM-Speed to adapt to large datasets. Finally, we designed the module to be plug-and-play and applied it to GCN, GAT, GIN, and GraphSAGE, achieving desirable results on three homophilous datasets and six heterophilous graph datasets.

cs.AI↗
arXiv2026

Bridging Object Detection and Segmentation with Polygon Detection Transformers

Box detection and mask segmentation are two dominant paradigms for foreground representation: boxes are efficient but too coarse for object shapes, while masks are accurate but over-modeled for compact geometry. To bridge this gap, we present a Polygon Detection Transformer (Poly-DETR) built upon Polar Representation, where object queries regress a starting point and its fixed number of radial distances to directly construct the contour-approximating polygon. This formulation can be integrated into most DETR-like detectors by linear extension, since box is a degenerate case of Polar Representation with four rays. Furthermore, we propose two simple but necessary designs, Polar Deformable Attention and Position-Aware Training Scheme, to align feature sampling and polygon supervision. As a DETR-oriented advancement of Polar Representation, Poly-DETR outperforms existing polar-based methods by 4.7 mAP on MS COCO. Moreover, we explore the application regimes of polygon detection in geometry-driven domains, including remote sensing, medical imaging, and autonomous driving. In particular, Poly-DETR shows stronger scalability than its mask-based counterpart in high-resolution scenarios. Additional experiments show that, owing to its Transformer structure, Poly-DETR can be naturally extended to recent DETR variants equipped with foundation-model priors.

cs.CV↗
arXiv2026

Halpern Iteration Achieves $\tilde{\mathcal{O}}(ε^{-1/p})$ $p$th-Order Oracle Complexity for Monotone Variational Inequalities

We study second- and higher-order methods for solving smooth monotone variational inequalities (MVI). Monteiro and Svaiter (SIAM J. Optim., 2012) showed that a second-order method, NPE, converges at the rate of $\mathcal{O}(T^{-1.5})$. For convex-concave minimax optimization, a subset of MVI problems, Chen, Liu, Luo, and Zhang (COLT 2025) recently improved the complexity to $\tilde{\mathcal{O}}( T^{-1.75})$ . However, it is open whether the conjectured complexity for MVI can be improved. In this paper, by using a large-step inexact Halpern iteration, we propose a novel Halpern-NPE method that achieves an even faster rate of $\tilde{\mathcal{O}}(T^{-2})$ for solving MVIs. We also provide the $p$th-order generalization of our method. We first introduce an Anchored Tensor Method (ATM) that achieves the rate of $\mathcal{O}(T^{-(p-1)})$, and then combine it with the Halpern iteration to achieve a faster convergence rate of $\tilde{\mathcal{O}}(T^{-p})$. This improves all prior results for $p \ge 2$ and matches the classical extragradient method for $p=1$.

math.OC↗
arXiv2026

Smooth-Curvature Bend Design Guided by Variational Analysis for Adiabatic Multimode Integrated Photonics

Multimode photonic integrated circuits enable ultralow-loss on-chip optical interconnects and microwave-photonic processing, yet waveguide bends dominate both chip footprint and excess loss. A high-performance multimode waveguide bend (MWB) must transmit the working mode with low loss while suppressing intermodal coupling, forcing a trade-off among bending radius, operating bandwidth, and fabrication tolerance. Here we formulate constant-width MWB design as a curvature-dependent variational problem. By constructing a figure of merit that incorporates higher-order-mode excitation, fundamental-mode mismatch, and sidewall field intensity, we derive a necessary condition for adiabatic optimality: the curvature profile must approach infinite differentiability throughout the bend, including its junctions with the input and output straight waveguides. This condition explains the limitations of circular and Euler bends and motivates a smooth polynomial curvature (SPC) family with a closed-form beta-function representation. We further introduce an optimized SPC hybrid (SPCh) bend that balances junction smoothness and the interior curvature gradient. On the 220 nm silicon-on-insulator platform, SPCh bends achieve a mode extinction ratio below $-37$ dB from 1500-1600 nm at an effective radius of $16\,μ\mathrm{m}$, providing more than 22 dB stronger mode suppression than a representative Euler bend at the same radius. The simulated response remains robust to $\pm 60$ nm waveguide-width deviations. Fabricated SPCh-based microring resonators reach an intrinsic quality factor of up to $7.53 \times 10^6$ and a free spectral range of up to 100 GHz through a standard silicon foundry process. The resulting design strategy provides compact, broadband, and fabrication-tolerant multimode bends for high-density optical interconnects and microwave-photonic systems.

physics.optics↗
arXiv2026

Bridging Information Asymmetry: A Hierarchical Framework for Deterministic Blind Face Restoration

Blind face restoration remains a persistent challenge due to the inherent ill-posedness of reconstructing holistic structures from severely constrained observations. Current generative paradigms, while capable of synthesizing realistic facial details, remain limited by the under-constrained nature of blind restoration, where severely degraded inputs can be mapped to plausible yet identity-inconsistent outputs. To address this issue, we present Pref-Restore, a hierarchical framework for deterministic BFR. Our design is organized around three complementary principles: (1) Semantic Information Augmentation, where an auto-regressive semantic branch converts image and text cues into structured tokens that provide a stable high-level anchor; (2) Texture-level Fidelity Alignment, where the diffusion generator is trained under this anchor to recover identity-relevant details; and (3) Fidelity-constrained Preference Optimization, where a face-aware reward refines the diffusion trajectory while controlling the quality-fidelity trade-off. Extensive experiments on synthetic and real-world benchmarks show that Pref-Restore achieves state-of-the-art performance, with stronger identity-sensitive fidelity and lower restoration uncertainty across repeated sampling. Systematic ablations further attribute these gains to the proposed hierarchical design, showing the necessity of staged training, the robustness of the text pathway under deployment-faithful conditions, and the benefit of fidelity-constrained preference optimization.

cs.CV↗
arXiv2026

Solving Convex-Concave Problems with $\tilde{\mathcal{O}}(ε^{-4/(3p+1)})$ $p$th-Order Oracle Complexity

When the objective has Lipschitz continuous $p$th-order derivatives, it is known that convex-concave minimax problems can be solved with $\mathcal{O}(ε^{-2/(p+1)})$ $p$th-order oracle calls. This complexity upper bound was speculated to be optimal as it is achieved by a natural generalization of the optimal first-order method. In this work, we show an improved upper bound of $\tilde{\mathcal{O}}(ε^{-4/(3p+1)})$ by applying the Monteiro-Svaiter acceleration. We also establish a lower complexity bound of $Ω(ε^{-2/(3p-1)})$, suggesting a gap still exists for $p \ge 2$.

math.OC↗
arXiv2026

RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation

Deep learning has greatly advanced medical image segmentation, but its success relies heavily on fully supervised learning, which requires dense annotations that are costly and time-consuming for 3D volumetric scans. Barely-supervised learning reduces annotation burden by using only a few labeled slices per volume. Existing methods typically propagate sparse annotations to unlabeled slices through geometric continuity to generate pseudo-labels, but this strategy lacks semantic understanding, often resulting in low-quality pseudo-labels. Furthermore, medical image segmentation is inherently a pixel-level visual understanding task, where accuracy fundamentally depends on the quality of local, fine-grained visual features. Inspired by this, we propose RADA, a novel Region-Aware Dual-encoder Auxiliary learning pipeline which introduces a dual-encoder framework pre-trained on Alpha-CLIP to extract fine-grained, region-specific visual features from the original images and limited annotations. The framework combines image-level fine-grained visual features with text-level semantic guidance, providing region-aware semantic supervision that bridges image-level semantics and pixel-level segmentation. Integrated into a triple-view training framework, RADA achieves SOTA performance under extremely sparse annotation settings on LA2018, KiTS19 and LiTS, demonstrating robust generalization across diverse datasets.

cs.CV↗
arXiv2026

Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context

Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and inpainting, which accumulate errors during inference due to incorrect intermediary outputs, non-differentiable processes, and separate models. To overcome these limitations, we introduce ``geometry-as-context". It iteratively completes the following steps using an autoregressive camera-controlled video generation model: (1) estimates the geometry of the current view necessary for 3D reconstruction, and (2) simulates and restores novel view images rendered by the 3D scene. Under this multi-task framework, we develop the camera gated attention module to enhance the model's capability to effectively leverage camera poses. During the training phase, text contexts are utilized to ascertain whether geometric or RGB images should be generated. To ensure that the model can generate RGB-only outputs during inference, the geometry context is randomly dropped from the interleaved text-image-geometry training sequence. The method has been tested on scene video generation with one-direction and forth-and-back trajectories. The results show its superiority over previous approaches in maintaining scene consistency and camera control.

cs.CV↗
arXiv2025

Inter- and Intra-image Refinement for Few Shot Segmentation

Deep neural networks for semantic segmentation rely on large-scale annotated datasets, leading to an annotation bottleneck that motivates few shot semantic segmentation (FSS) which aims to generalize to novel classes with minimal labeled exemplars. Most existing FSS methods adopt a prototype-based paradigm, which generates query prior map by extracting masked-area features from support images and then makes predictions guided by the prior map. However, they suffer from two critical limitations induced by inter- and intra-image discrepancies: 1) The intra-class gap between support and query images, caused by single-prototype representation, results in scattered and noisy prior maps; 2) The inter-class interference from visually similar but semantically distinct regions leads to inconsistent support-query feature matching and erroneous predictions. To address these issues, we propose the Inter- and Intra-image Refinement (IIR) model. The model contains an inter-image class activation mapping based method that generates two prototypes for class-consistent region matching, including core discriminative features and local specific features, and yields an accurate and robust prior map. For intra-image refinement, a directional dropout mechanism is introduced to mask inconsistent support-query feature pairs in cross attention, thereby enhancing decoder performance. Extensive experiments demonstrate that IIR achieves state-of-the-art performance on 9 benchmarks, covering standard FSS, part FSS, and cross-domain FSS. Our source code is available at \href{https://github.com/forypipi/IIR}{https://github.com/forypipi/IIR}.

cs.CV↗
arXiv2025

Soliton-Assisted Massive Signal Broadcasting via Exceptional Points

Chip-scale all-optical signal broadcasting enables data replication from an optical signal to a large number of wavelength channels, playing a critical role in enabling massive-throughput optical communication and computing systems. The underlying process is four-wave mixing between an optical signal and a multi-wavelength pump source via optical Kerr nonlinearity. To enhance the generally weak nonlinearity, high-quality (Q) microcavities are commonly used to achieve practical efficiency. However, the ultra-narrow linewidths of high Q cavities prohibit achieving massive throughput broadcasting due to Fourier reciprocity. Here, we overcome this challenge by harnessing a parity-time symmetric coupled-cavity system that supports equally spaced exceptional points in the frequency domain. This design seamlessly integrates generation of dissipative Kerr soliton comb source and all-optical signal broadcasting into a unified nonlinear process. As a result, we realize soliton-assisted intracavity massive signal broadcasting with a channel count exceeding 100 over 200 nm wavelength range, resulting in Terabit-per-second aggregated rates. This throughput surpasses the intrinsic microcavity linewidth constraint (~200 MHz) by over three orders of magnitude. We further demonstrate the utility of this approach through an optical convolutional accelerator, highlighting its potential to enable transformative capabilities in photonic computing. Our work establishes a new paradigm for chip-scale photonic processing devices based on non-Hermitian optical design.

physics.optics↗
arXiv2025

AdaTok: Adaptive Token Compression with Object-Aware Representations for Efficient Multimodal LLMs

Multimodal Large Language Models (MLLMs) have demonstrated substantial value in unified text-image understanding and reasoning, primarily by converting images into sequences of patch-level tokens that align with their architectural paradigm. However, patch-level tokenization leads to a quadratic growth in image tokens, burdening MLLMs' understanding and reasoning with enormous computation and memory. Additionally, the traditional patch-wise scanning tokenization workflow misaligns with the human vision cognition system, further leading to hallucination and computational redundancy. To address this issue, we propose an object-level token merging strategy for Adaptive Token compression, revealing the consistency with human vision system. The experiments are conducted on multiple comprehensive benchmarks, which show that our approach averagely, utilizes only 10% tokens while achieving almost 96% of the vanilla model's performance. More extensive experimental results in comparison with relevant works demonstrate the superiority of our method in balancing compression ratio and performance. Our code will be available.

cs.CV↗