Search arXiv⌕ Search

arXiv subjects

Shuhang Chen

Publications and source records attributed to Shuhang Chen.

At least 19 recordsLinked to original sources

Multipole Decomposition of Moving Sources

Cartesian multipole moments are widely used to analyze and engineer radiation, but the usual relations for their radiated fields assume a wavevector-independent source frequency. For moving sources, Doppler shifts make the frequency depend on the wavevector, so the radiated fields predicted from the moments generally carry errors proportional to v/c. From charge conservation in the laboratory frame, we derive a multipole decomposition of moving sources that retains the usual moments but evaluates their contributions at Doppler-shifted wavenumbers and adds a convection-current term. Requiring no rest frame, it applies to moving matter and to excitation patterns in synthetic motion through media at rest, including superluminal ones. The decomposition also extends to nonuniform translation and to nonrigid patterns with curved spectral supports. Exact calculations for moving electric, magnetic, and toroidal dipoles confirm the decomposition and attribute the different radiation of a dipole in moving matter and in synthetic motion to the laboratory moments that each kind of motion induces. For an anapole, these moments decide whether it radiates. An anapole carried by uniformly moving matter remains nonradiating, whereas an excitation pattern with the same electric and toroidal dipoles radiates in synthetic motion. The decomposition thus makes multipolar analysis available for moving matter and for excitation patterns in synthetic motion, and it opens the way to designing their radiation.

physics.optics↗

Length-Preserving Vessel Trajectory Simplification With Controllable Compression-Precision Bound

Vessel trajectory data from the Automatic Identification System (AIS) is important for a wide range of maritime analysis and management applications. As AIS datasets continue to grow in scale, trajectory simplification (or compression) algorithms have become indispensable tools for managing their computational demands. Existing approaches, however, largely overlook the preservation of trajectory length, a critical metric of direct relevance to maritime environmental auditing and voyage management. We address this gap by framing trajectory simplification as a pair of dual optimization problems subject to error constraints: Compression-Driven Simplification (CDS), which minimizes data volume for a given length-error tolerance, and Precision-Driven Simplification (PDS), which minimizes length approximation error for a given compression target. Both problems are solved within a unified dynamic programming framework, and we provide mathematical proofs establishing that our formulation yields globally optimal solutions. This guarantees flexible, direct control over both compression ratio and length-approximation fidelity. { We benchmark CDS and PDS on real-world AIS datasets spanning diverse navigation scenarios and representative water area, comparing against state-of-the-art baselines. Experimental results on public benchmark datasets demonstrate that even under a small length error tolerance ($ε=0.1$ nmi), our methods achieve about 91\% data compression rate, approximately 14\% higher than the best-performing baseline, which implies that our methods are capable of maximally preserving the trajectory length while reducing data redundancy significant.

stat.AP↗

Aubry-André transition in photonic time quasicrystals

In one dimension, Anderson localization by a disordered potential sets in at any strength, whereas localization by a quasiperiodic potential in the Aubry-André model occurs through a transition at a critical strength. Disordered photonic time crystals exhibit a temporal counterpart of this Anderson localization, in which light, instead of decaying in space, stops propagating and grows in time. Whether a counterpart of the Aubry-André transition exists in photonic time quasicrystals remains an open question. Here we show that it does, and that the transition occurs at mobility edges in momentum rather than in energy. These edges arise even under impulsive modulation, where the field obeys the self-dual almost-Mathieu equation exactly, and for general analytic modulations Avila's global theory reveals the condition under which they form. The Aubry-André transition thus extends from spatial lattices to the time domain, where it sorts light by wave number into components that propagate and components that stop and grow.

physics.optics↗

Non-Hermitian photonic time quasicrystal

Photonic time crystals amplify waves through temporal modulation. We study a temporal analogue of the non-Hermitian Aubry-André-Harper model. By continuing an incommensurate temporal modulation into the complex phase plane, we find that the bulk amplification rate as a function of the complexification coordinate is organized into distinct integer phases, with its slope locked to an integer within each phase. This integer is Avila's acceleration, connecting a global structure of quasiperiodic operator theory with a directly observable optical propagation response. The quantized response persists in the presence of defects in the time-dependent permittivity modulation that preserve the underlying analytic phase structure. As a wave-level consequence, two input frequencies belonging to different integer phases acquire exponentially separated amplification, producing spectral selection and reshaping the temporal beat pattern. Our results establish that a global integer of quasiperiodic operator theory can govern a tunable, quantized growth response in a non-Hermitian photonic time quasicrystal.

physics.optics↗

Construction-Constrained Bernstein Synthesis of Joint Pitch-Width RDL Spiral Inductors for High-Q mmWave FoWLP Applications

We present a construction-constrained Bernstein framework for joint pitch-width synthesis of planar spiral inductors. A positive cubic Bernstein profile is integrated to prescribe a monotonic radial trajectory, while an independent Bernstein profile controls the conductor width. The nonnegativity, partition-of-unity, and convex-hull properties of the Bernstein basis convert endpoint, winding-direction, and width requirements into algebraic constraints. Embedded in differential evolution (DE), these constraints reject inadmissible candidates before full-wave evaluation, focusing expensive solver calls on geometries that satisfy the construction rules. The method is demonstrated on a two-turn mmWave inductor implemented in the redistribution layer (RDL) of fan-out wafer-level packaging (FoWLP), with the quality factor selected as the optimization objective. Searching the constrained Bernstein design space with DE yields a simulated Q of 34.85 at 30 GHz, compared with 29.66 for a uniform Archimedean baseline under the same stack, footprint, and ports. This corresponds to a 17.5% improvement while reducing planar copper area by 1.53%. The optimized response maintains Q >= 30 from 16 to 49 GHz.

physics.optics↗

SKETCH: Semantic Key-Point Conditioning for Long-Horizon Vessel Trajectory Prediction

Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and environmental factors. Existing methods often struggle to maintain global directional consistency, leading to drifting or implausible trajectories when extrapolated over long time horizons. To address this issue, we propose a semantic-key-point-conditioned trajectory modeling framework, in which future trajectories are predicted by conditioning on a high-level Next Key Point (NKP) that captures navigational intent. This formulation decomposes long-horizon prediction into global semantic decision-making and local motion modeling, effectively restricting the support of future trajectories to semantically feasible subsets. To efficiently estimate the NKP prior from historical observations, we adopt a pretrain-finetune strategy. Extensive experiments on real-world AIS data demonstrate that the proposed method consistently outperforms state-of-the-art approaches, particularly for long travel durations, directional accuracy, and fine-grained trajectory prediction.

cs.RO↗

Möbius-like Real-Space Topology Reshapes Spectral Winding Topology in Hatano-Nelson Rings

The spectral winding number serves as a bulk topological invariant in non-Hermitian systems, governing the emergence of skin modes and encoding the non-Hermitian bulk-boundary correspondence. However, most existing studies are built on conventional lattice geometries such as linear chains, rings, or planar arrays, leaving the role of real-space topological connectivity as an independent degree of freedom largely unexplored. Here, we construct a Möbius ring system by cutting two parallel Hatano-Nelson (HN) rings and reconnecting them with a half-twist, without altering any local hopping parameter. This topological reconstruction transforms the periodic-boundary spectrum from two disjoint ellipses into a multi-petalled rose curve, and leads to distinct decay lengths for different eigenstates under open boundary conditions. Moreover, the spectral winding number can be driven through discrete winding-number jumps by tuning the coupling strength, with critical values obtained analytically. Our results demonstrate that real-space Möbius connectivity, mediated by the coupling strength, provides an independent and tunable foundation for the systematic control of non-Hermitian topology, with implications for the design of topological devices and sensing schemes.

physics.optics↗

MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems

Despite strong results on many tasks, multimodal large language models (MLLMs) still underperform on visual mathematical problem solving, especially in reliably perceiving and interpreting diagrams. Inspired by human problem-solving, we hypothesize that the ability to extract meaningful information from diagrams is pivotal, as it directly conditions subsequent inference. Hence, we introduce FlowVerse, a comprehensive benchmark that provides a fine-grained evaluation of MLLMs' perception and reasoning capabilities. Our preliminary results on FlowVerse reveal that existing MLLMs exhibit substantial limitations when extracting essential information and reasoned properties from diagrams and performing complex reasoning based on these visual inputs. In response, we introduce MathFlow, a modular problem-solving pipeline that decouples perception and inference into distinct stages, thereby optimizing each independently. Given the perceptual limitations observed in current MLLMs, we trained MathFlow-P-7B as a dedicated perception model. Experimental results indicate that MathFlow-P-7B yields substantial performance gains when integrated with various closed-source and open-source inference models. This demonstrates the effectiveness of the MathFlow pipeline and its compatibility with diverse inference frameworks. Project page: https://github.com/MathFlow-zju/MathFlow.

cs.CV↗

CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving

Despite significant progress, multimodal large language models continue to struggle with visual mathematical problem solving. Some recent works recognize that visual perception is a bottleneck in visual mathematical reasoning, but their solutions are limited to improving the extraction and interpretation of visual inputs. Notably, they all ignore the key issue of whether the extracted visual cues are faithfully integrated and properly utilized in subsequent reasoning. Motivated by this, we present CogFlow, a novel cognitive-inspired three-stage framework that incorporates a knowledge internalization stage, explicitly simulating the hierarchical flow of human reasoning: perception$\Rightarrow$internalization$\Rightarrow$reasoning. In line with this hierarchical flow, we holistically enhance all its stages. We devise Synergistic Visual Rewards to boost perception capabilities in parametric and semantic spaces, jointly improving visual information extraction from symbols and diagrams. To guarantee faithful integration of extracted visual cues into subsequent reasoning, we introduce a Knowledge Internalization Reward model in the internalization stage, bridging perception and reasoning. Moreover, we design a Visual-Gated Policy Optimization algorithm to further enforce the reasoning is grounded with the visual knowledge, preventing models seeking shortcuts that appear coherent but are visually ungrounded reasoning chains. Moreover, we contribute a new dataset MathCog for model training, which contains samples with over 120K high-quality perception-reasoning aligned annotations. Comprehensive experiments and analysis on commonly used visual mathematical reasoning benchmarks validate the superiority of the proposed CogFlow. Project page: https://shchen233.github.io/cogflow.

cs.CV↗

NeRF-MIR: Towards High-Quality Restoration of Masked Images with Neural Radiance Fields

Neural Radiance Fields (NeRF) have demonstrated remarkable performance in novel view synthesis. However, there is much improvement room on restoring 3D scenes based on NeRF from corrupted images, which are common in natural scene captures and can significantly impact the effectiveness of NeRF. This paper introduces NeRF-MIR, a novel neural rendering approach specifically proposed for the restoration of masked images, demonstrating the potential of NeRF in this domain. Recognizing that randomly emitting rays to pixels in NeRF may not effectively learn intricate image textures, we propose a \textbf{P}atch-based \textbf{E}ntropy for \textbf{R}ay \textbf{E}mitting (\textbf{PERE}) strategy to distribute emitted rays properly. This enables NeRF-MIR to fuse comprehensive information from images of different views. Additionally, we introduce a \textbf{P}rogressively \textbf{I}terative \textbf{RE}storation (\textbf{PIRE}) mechanism to restore the masked regions in a self-training process. Furthermore, we design a dynamically-weighted loss function that automatically recalibrates the loss weights for masked regions. As existing datasets do not support NeRF-based masked image restoration, we construct three masked datasets to simulate corrupted scenarios. Extensive experiments on real data and constructed datasets demonstrate the superiority of NeRF-MIR over its counterparts in masked image restoration.

cs.CV↗

IDDR-NGP: Incorporating Detectors for Distractor Removal with Instant Neural Radiance Field

This paper presents the first unified distractor removal method, named IDDR-NGP, which directly operates on Instant-NPG. The method is able to remove a wide range of distractors in 3D scenes, such as snowflakes, confetti, defoliation and petals, whereas existing methods usually focus on a specific type of distractors. By incorporating implicit 3D representations with 2D detectors, we demonstrate that it is possible to efficiently restore 3D scenes from multiple corrupted images. We design the learned perceptual image patch similarity~( LPIPS) loss and the multi-view compensation loss (MVCL) to jointly optimize the rendering results of IDDR-NGP, which could aggregate information from multi-view corrupted images. All of them can be trained in an end-to-end manner to synthesize high-quality 3D scenes. To support the research on distractors removal in implicit 3D representations, we build a new benchmark dataset that consists of both synthetic and real-world distractors. To validate the effectiveness and robustness of IDDR-NGP, we provide a wide range of distractors with corresponding annotated labels added to both realistic and synthetic scenes. Extensive experimental results demonstrate the effectiveness and robustness of IDDR-NGP in removing multiple types of distractors. In addition, our approach achieves results comparable with the existing SOTA desnow methods and is capable of accurately removing both realistic and synthetic distractors.

cs.CV↗

Align$^3$GR: Unified Multi-Level Alignment for LLM-based Generative Recommendation

Large Language Models (LLMs) demonstrate significant advantages in leveraging structured world knowledge and multi-step reasoning capabilities. However, fundamental challenges arise when transforming LLMs into real-world recommender systems due to semantic and behavioral misalignment. To bridge this gap, we propose Align$^3$GR, a novel framework that unifies token-level, behavior modeling-level, and preference-level alignment. Our approach introduces: Dual tokenization fusing user-item semantic and collaborative signals. Enhanced behavior modeling with bidirectional semantic alignment. Progressive DPO strategy combining self-play (SP-DPO) and real-world feedback (RF-DPO) for dynamic preference adaptation. Experiments show Align$^3$GR outperforms the SOTA baseline by +17.8% in Recall@10 and +20.2% in NDCG@10 on the public dataset, with significant gains in online A/B tests and full-scale deployment on an industrial large-scale recommendation platform.

cs.IR↗

SAMora: Enhancing SAM through Hierarchical Self-Supervised Pre-Training for Medical Images

The Segment Anything Model (SAM) has demonstrated significant potential in medical image segmentation. Yet, its performance is limited when only a small amount of labeled data is available, while there is abundant valuable yet often overlooked hierarchical information in medical data. To address this limitation, we draw inspiration from self-supervised learning and propose SAMora, an innovative framework that captures hierarchical medical knowledge by applying complementary self-supervised learning objectives at the image, patch, and pixel levels. To fully exploit the complementarity of hierarchical knowledge within LoRAs, we introduce HL-Attn, a hierarchical fusion module that integrates multi-scale features while maintaining their distinct characteristics. SAMora is compatible with various SAM variants, including SAM2, SAMed, and H-SAM. Experimental results on the Synapse, LA, and PROMISE12 datasets demonstrate that SAMora outperforms existing SAM variants. It achieves state-of-the-art performance in both few-shot and fully supervised settings while reducing fine-tuning epochs by 90%. The code is available at https://github.com/ShChen233/SAMora.

eess.IV↗

The ODE Method for Stochastic Approximation and Reinforcement Learning with Markovian Noise

Stochastic approximation is a class of algorithms that update a vector iteratively, incrementally, and stochastically, including, e.g., stochastic gradient descent and temporal difference learning. One fundamental challenge in analyzing a stochastic approximation algorithm is to establish its stability, i.e., to show that the stochastic vector iterates are bounded almost surely. In this paper, we extend the celebrated Borkar-Meyn theorem for stability from the Martingale difference noise setting to the Markovian noise setting, which greatly improves its applicability in reinforcement learning, especially in those off-policy reinforcement learning algorithms with linear function approximation and eligibility traces. Central to our analysis is the diminishing asymptotic rate of change of a few functions, which is implied by both a form of the strong law of large numbers and a form of the law of the iterated logarithm.

cs.LG↗

Nonreciprocal Coupling Induced by Nonlocal Loss Engineering

Nonreciprocal coupling between photonic modes enables a range of advanced functionalities, though the available approaches for its practical implementation remain limited. Here, we introduce a novel strategy for achieving nonreciprocal coupling via nonlocal, nonlinear loss. We prove that robust, broadband, and continuously tunable nonreciprocal coupling can be realized by engineering the loss rate as a function of the state of a nonlocal mode, as validated through effective Hamiltonian modeling and numerical simulations. Our results suggest a promising route toward scalable, power-independent, and potentially integrable nonreciprocal photonic systems, with promising applications in non-Hermitian devices and topological photonics.

physics.optics↗

The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning

The paper concerns the $d$-dimensional stochastic approximation recursion, $$ θ_{n+1}= θ_n + α_{n + 1} f(θ_n, Φ_{n+1}) $$ where $ \{ Φ_n \}$ is a stochastic process on a general state space, satisfying a conditional Markov property that allows for parameter-dependent noise. The main results are established under additional conditions on the mean flow and a version of the Donsker-Varadhan Lyapunov drift condition known as (DV3): (i) An appropriate Lyapunov function is constructed that implies convergence of the estimates in $L_4$. (ii) A functional central limit theorem (CLT) is established, as well as the usual one-dimensional CLT for the normalized error. Moment bounds combined with the CLT imply convergence of the normalized covariance $\textsf{E}[ z_n z_n^T ]$ to the asymptotic covariance in the CLT, where $z_n =: (θ_n-θ^*)/\sqrt{α_n}$. (iii) The CLT holds for the normalized version $z^{\text{PR}}_n =: \sqrt{n} [θ^{\text{PR}}_n -θ^*]$, of the averaged parameters $θ^{\text{PR}}_n =:n^{-1} \sum_{k=1}^nθ_k$, subject to standard assumptions on the step-size. Moreover, the covariance in the CLT coincides with the minimal covariance of Polyak and Ruppert. (iv) An example is given where $f$ and $\bar{f}$ are linear in $θ$, and $Φ$ is a geometrically ergodic Markov chain but does not satisfy (DV3). While the algorithm is convergent, the second moment of $θ_n$ is unbounded and in fact diverges. This arXiv version represents a major extension of the results in prior versions.The main results now allow for parameter-dependent noise, as is often the case in applications to reinforcement learning.

math.ST↗

Exploration of the two-dimensional Ising magnetic materials in the triangular prismatic crystal field

Magnetic anisotropy is essential for stabilizing two-dimensional (2D) magnetism, which has significant applications in spintronics and the advancement of fundamental physics. In this work, we examine the electronic structure and magnetic properties of triangular prismatic MSi$_2$N$_4$ (M = V, Cr) monolayers, using crystal field theory, spin-orbital state analyses, and density functional calculations. Our results reveal that the pristine VSi$_2$N$_4$ monolayer exhibits magnetism with a V$^{4+}$ 3$d^1$ $S$ = 1/2 charge-spin state within the triangular prismatic crystal field. However, the strong $d$ orbital hybridization between adjacent V$^{4+}$ ions disrupts the $d$ orbital splitting in this crystal field, resulting in a relatively small in-plane magnetic anisotropy of approximately 2 $μ$eV per V atom.In contrast, the pristine CrSi$_2$N$_4$ monolayer is nonmagnetic, characterized by the Cr$^{4+}$ 3$d^2$ $S$ = 0 state. Upon substituting nonmagnetic Cr$^{4+}$ with Si$^{4+}$, Cr$_\frac{1}{3}$Si$_\frac{8}{3}$N$_4$ transforms into an antiferromagnetic insulator with Cr$^{4+}$ 3$d^2$ $S$ = 1 state, featuring a large orbital moment of -1.06 $μ_{\rm B}$ oriented along the $z$-axis and huge perpendicular magnetic anisotropy of 18.63 meV per Cr atom. These findings highlight the potential for further exploration of 2D Ising magnetic materials within a unique triangular prismatic crystal field.

cond-mat.mtrl-sci↗

Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training

We introduce DualMind, a generalist agent designed to tackle various decision-making tasks that addresses challenges posed by current methods, such as overfitting behaviors and dependence on task-specific fine-tuning. DualMind uses a novel "Dual-phase" training strategy that emulates how humans learn to act in the world. The model first learns fundamental common knowledge through a self-supervised objective tailored for control tasks and then learns how to make decisions based on different contexts through imitating behaviors conditioned on given prompts. DualMind can handle tasks across domains, scenes, and embodiments using just a single set of model weights and can execute zero-shot prompting without requiring task-specific fine-tuning. We evaluate DualMind on MetaWorld and Habitat through extensive experiments and demonstrate its superior generalizability compared to previous techniques, outperforming other generalist agents by over 50$\%$ and 70$\%$ on Habitat and MetaWorld, respectively. On the 45 tasks in MetaWorld, DualMind achieves over 30 tasks at a 90$\%$ success rate.

cs.AI↗