Searcharxiv⌕ Search

arXiv subjects

Xi Chen

Publications and source records attributed to Xi Chen.

At least 181 records · Page 10Linked to original sources
arXiv2026

Maximum Likelihood Reconstruction for Multi-Look Digital Holography with Markov-Modeled Speckle Correlation

Multi-look acquisition is a widely used strategy for reducing speckle noise in coherent imaging systems such as digital holography. By acquiring multiple measurements, speckle can be suppressed through averaging or joint reconstruction, typically under the assumption that speckle realizations across looks are statistically independent. In practice, however, hardware constraints limit measurement diversity, leading to inter-look correlation that degrades the performance of conventional methods. In this work, we study the reconstruction of speckle-free reflectivity from complex-valued multi-look measurements in the presence of correlated speckle. We model the inter-look dependence using a first-order Markov process and derive the corresponding likelihood under a first-order Markov approximation, resulting in a constrained maximum likelihood estimation problem. To solve this problem, we develop an efficient projected gradient descent framework that combines gradient-based updates with implicit regularization via deep image priors, and leverages Monte Carlo approximation and matrix-free operators for scalable computation. Simulation results demonstrate that the proposed approach remains robust under strong inter-look correlation, achieving performance close to the ideal independent-look scenario and consistently outperforming methods that ignore such dependencies. These results highlight the importance of explicitly modeling inter-look correlation and provide a practical framework for multi-look holographic reconstruction under realistic acquisition conditions. Our code is available at: https://github.com/Computational-Imaging-RU/MLE-Holography-Markov.

eess.IV↗
arXiv2026

Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing

Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on complex cross-modal interactions that lead to low retrieval efficiency, or depend on large-scale vision-language model pre-training, which requires massive data and computational resources. To address these issues, we propose a fast-then-fine (FTF) two-stage retrieval framework that decomposes retrieval into a text-agnostic recall stage for efficient candidate selection and a text-guided rerank stage for fine-grained alignment. Specifically, in the recall stage, text-agnostic coarse-grained representations are employed for efficient candidate selection; in the rerank stage, a parameter-free balanced text-guided interaction block enhances fine-grained alignment without introducing additional learnable parameters. Furthermore, an inter- and intra-modal loss is designed to jointly optimize cross-modal alignment across multi-granular representations. Extensive experiments on public benchmarks demonstrate that the FTF achieves competitive retrieval accuracy while significantly improving retrieval efficiency compared with existing methods.

cs.CV↗
arXiv2026

Subharmonic instability of large-scale wavy structures in two-dimensional channels

A particular interest on two-dimensional turbulence is the inverse energy cascade from small to large sales, which leads to an energy condensation accompanied by the formation of large-scale vortical structures. Indeed, such a phenomenon is observed in the two-dimensional channel (2DCH) with large Reynolds numbers, where prominent large-scale wavy structures play a central role in the momentum and energy transfer across the inhomogeneous wall-normal direction \citep{Falkovich2018}. Yet, the instability of these wavy structures remains poorly understood, and it is unknown whether they have the capacity to generate turbulence. To address this, we first conduct the direct numerical simulation (DNS) of Navier-Stokes equations for 2DCH, then extract the large-scale wavy structures through the singular value decomposition, and finally perform a Floquet-based secondary instability analysis. Two bulk Reynolds numbers are examined in particular, i.e. $Re = 3000$ and $Re = 200000$, which lie on opposite sides of the transitional regime near $Re \approx 10000$ and cover the previously reported simulation domain. At $Re = 3000$, the large-scale wavy structure is found to be linearly stable, consistent with the laminar-like DNS flow field. However, at $Re = 200000$, a subharmonic torsional mode is identified, which leads to a definite growth rate ($λ_r = 0.18$) for the wavy structures with a half wave-length shift. Temporal reconstruction shows that this unstable mode deforms and splits into multiple wave trains and evolves in the opposite phase. Compared to the TS (Tollmien-Schlichting) wave of laminar flow, the subharmonic mode found here offers a novel understanding for the generation of turbulence in larger Reynolds number two-dimensional channels.

physics.flu-dyn↗
arXiv2026

What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search

Recent work has demonstrated the promise of orchestrating large language models (LLMs) within evolutionary and agentic optimization systems. However, the mechanisms driving these optimization gains remain poorly understood. In this work, we present a large-scale study of LLM-guided evolutionary search, collecting optimization trajectories for 15 LLMs across 8 tasks. Although zero-shot problem-solving ability correlates with final optimization outcomes, it explains only part of the variance: models with similar initial capability often induce dramatically different search trajectories and outcomes. By analyzing these trajectories, we find that strong LLM optimizers behave as local refiners, producing frequent incremental improvements while progressively localizing the search in semantic space. Conversely, weaker optimizers exhibit large semantic drift, with sporadic breakthroughs followed by stagnation. Notably, various measures of solution novelty do not predict final performance; novelty is beneficial only when the search remains sufficiently localized around high-performing regions of the solution space. Our results highlight the importance of trajectory analysis for understanding and improving LLM-based optimization systems and provide actionable insights for their design and training.

cs.CL↗
arXiv2026

OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection

Open-Vocabulary Object Detection (OVOD) aims to enable detectors to generalize across categories by leveraging semantic information. Although existing methods are pretrained on large vision-language datasets, their inference is still limited to fixed category names, creating a gap between multimodal training and unimodal inference. Previous work has shown that improving textual representation can significantly enhance OVOD performance, indicating that the textual space is still underexplored. To this end, we propose OVOD-Agent, which transforms passive category matching into proactive visual reasoning and self-evolving detection. Inspired by the Chain-of-Thought (CoT) paradigm, OVOD-Agent extends the textual optimization process into an interpretable Visual-CoT with explicit actions. OVOD's lightweight nature makes LLM-based management unsuitable; instead, we model visual context transitions as a Weakly Markovian Decision Process (w-MDP) over eight state spaces, which naturally represents the agent's state, memory, and interaction dynamics. A Bandit module generates exploration signals under limited supervision, helping the agent focus on uncertain regions and adapt its detection policy. We further integrate Markov transition matrices with Bandit trajectories for self-supervised Reward Model (RM) optimization, forming a closed loop from Bandit exploration to RM learning. Experiments on COCO and LVIS show that OVOD-Agent provides consistent improvements across OVOD backbones, particularly on rare categories, confirming the effectiveness of the proposed framework.

cs.AI↗
arXiv2026

Physics-Informed Neural Networks for Maximizing Quantum Fisher Information in Time-Dependent Many-Body Systems

Quantum Fisher Information (QFI) sets the ultimate precision limit for parameter estimation and is therefore a central quantity in quantum metrology. In time-dependent many-body systems, however, maximizing QFI is a highly non-trivial task due to the combined effects of non-commutativity, control complexity, and the exponential growth of the Hilbert space. In this work, we present a physics-informed neural network (PINN) framework to address this problem through the learning of counter-diabatic quantum dynamics. Our approach combines a variational PINN formulation with a Magnus-expansion treatment of time-ordered evolution, enabling the adiabatic gauge potential and the scheduling function to be inferred directly from the underlying physics while enforcing the Euler-Lagrange structure of the protocol. The method is applied to several families of driven spin Hamiltonians, including nearest-neighbor, dipolar, and trapped-ion-inspired interactions, for systems of up to six qubits. The numerical results show that the proposed framework systematically improves over reference solutions based only on the Euler-Lagrange condition, yielding high normalized QFI together with favorable fidelity and extremal-balance metrics while preserving small phsical residuals. The analysis further shows that learning the scheduling function provides a clear performance advantage in most cases, and reveals non-trivial finite-size effects, with $q=3$ emerging as a particularly challenging regime. Although scalability remains limited by the exponential growth of the operator space and by automatic-differentiation costs, the results demonstrate that PINNs constitute a viable and physically grounded route for learning metrologically optimal control strategies in interacting quantum systems.

quant-ph↗
arXiv2026

Classical counterparts of shortcuts to adiabaticity in nonlinear dissipative Lagrangian systems

Shortcuts to adiabaticity (STA) were first developed in quantum dynamics to realize rapid transformations with suppressed residual excitations. Here we show how the same idea can be implemented in classical nonlinear dissipative Lagrangian systems. Using a coupled $r$-$θ$ manipulator as an illustrative model, we perform inverse engineering on the Euler-Lagrange equations with Rayleigh dissipation by prescribing endpoint-stationary trajectories, obtaining the corresponding force and torque profiles and quantifying how geometric coupling amplifies errors and residual energy. We further compare smooth STA protocols with actuator-bounded time-optimal solutions and with proportional-integral-derivative tracking, which highlights a trade-off among smoothness, speed, and robustness. Finally, we introduce a single-shot correction based on one mid-course measurement to reduce the effect of early deviations while keeping the inputs nearly smooth. These results provide a practical bridge between quantum STA concepts and their classical counterparts.

quant-ph↗
arXiv2026

A New Cloud-Cloud Collision Source N68 toward the G35 Molecular Cloud Complex

Bubble N68 in the G35 complex shows clear cloud-cloud collision (CCC) signatures. Its semi-ring-like morphology harbors many significant massive star formation tracers: 6 HII regions, 4 6.7 GHz masers, 5 Midcourse Space Experiment sources, 9 radio peaks, and nearly 10 O/B-type stars. We also identified 163 young stellar objects (45 Class I, 5 Flat, 113 Class II), indicating active star formation toward N68. Our molecular study with CO reveals two distinct molecular clouds (N68a: 47-56 km s$^{-1}$; N68b: 56-64 km s$^{-1}$), with broad bridge features and complementary distributions at their borders, indicating an ongoing CCC. Star formation in N68 is collectively driven by collect-and-collapse (CC), radiation-driven implosion (RDI), and CCC mechanisms. However, compared with the CC and RDI mechanisms, the CCC mechanism does not enhance the star formation efficiency; instead, it tends to trigger the formation of massive stars. N68, along with bubbles N65 and N61, constructs a $\sim100$ pc scale CCC system in the G35 complex.

astro-ph.GA↗
arXiv2026

Spectro-temporal unitary transformations for coherent modulation: design trade-offs and practical considerations

This paper analyzes the performance of spectro-temporal unitary transforms for coherent optical modulation. Unlike conventional IQ modulation, such transforms are based on a cascade of phase modulators and dispersive elements, so are theoretically lossless and not limited by the bandwidth of the constituent modulators. We analyse the performance limits and design trade-offs of this scheme: estimating how the number of stages, amount of dispersion, modulator bandwidth, symbol block length and electrical signal power impacts the achievable signal-to-distortion ratio (SDR). Importantly, we show that high (>30 dB) SDRs suitable for modern >200 GBd class coherent optical communications are achievable with a low (<6) number of stages and reasonable parameters for driver power, modulator bandwidth and on-chip dispersion. Finally we address the SDR penalties associated with potential phase, amplitude, or dispersion errors, and limited DAC resolution.

physics.optics↗
arXiv2026

Optimizing thermal convection by phase-locking circulation to wall oscillations

This study numerically investigates two-dimensional Rayleigh-Benard convection subjected to horizontal oscillation of the bottom plate, with Prandtl number Pr=4.3, Rayleigh numbers Ra ranging from 5e6 to 1e8, and oscillation frequencies f between 0.0001 and 0.5. The imposed oscillation breaks the up-down symmetry of the classical system, inducing a strong frequency-dependent response in global heat transport, with the maximum Nusselt number enhancement exceeding 60% compared to the uncontrolled case. Central to this control efficiency is a phase-locking mechanism: at the optimal frequency, the intrinsic response time of the large-scale circulation (LSC), quantified by the sign-recovery of volume-averaged angular momentum, locks precisely to the wall oscillation period, enabling perfectly synchronized LSC reversals. Deviations from this optimal condition lead to a marked mismatch; the LSC response time becomes substantially longer when frequency exceeds the optimum and significantly shorter when frequency falls below it. In contrast, boundary layer velocities simply follow the wall oscillations and fail to distinguish control efficiency. Fourier mode analysis reveals that at the optimal frequency, a single-roll mode remains dominant throughout the cycle, facilitating efficient plume transport, whereas higher frequencies yield incomplete reversals and lower frequencies produce a double-roll structure that diminishes heat-transfer efficiency. This frequency-locking mechanism is shown to persist for optimal controls across the entire investigated Rayleigh number range, thus offering robust insight for active control strategies in thermally driven turbulent flows.

physics.flu-dyn↗
arXiv2026

OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner

The Diffusion Probabilistic Model (DPM) achieves remarkable performance in image generation, while its increasing parameter size and computational overhead hinder its deployment in practical applications. To improve this, the existing literature focuses on obtaining a smaller model with a fixed architecture through model compression. However, in practice, DPMs usually need to be deployed on various devices with different resource constraints, which leads to multiple compression processes, incurring significant overhead for repeated training. To obviate this, we propose a once-for-all (OFA) compression framework for DPMs that yields different subnetworks with various computations in a one-shot training manner. The existing OFA framework typically involves massive subnetworks with different parameter sizes, while such a huge candidate space slows the optimization. Thus, we propose to restrict the candidate subnetworks with a certain set of parameter sizes, where each size corresponds to a specific subnetwork. Specifically, to construct each subnetwork with a given size, we gradually allocate the maintained channels by their importance. Furthermore, we propose a reweighting strategy to balance the optimization process of different subnetworks. Experimental results show that our approach can produce compressed DPMs for various sizes with significantly lower training overhead while achieving satisfactory performance.

cs.CV↗
arXiv2026

Fragile Reconstruction: Adversarial Vulnerability of Reconstruction-Based Detectors for Diffusion-Generated Images

Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, reconstruction-based methods have emerged as a prominent paradigm for this task. However, we find that such methods exhibit severe security vulnerabilities to adversarial perturbations; that is, by adding imperceptible adversarial perturbations to input images, the detection accuracy of classifiers collapses to near zero. To verify this threat, we present a systematic evaluation of the adversarial robustness of three representative detectors across four diverse generative backbone models. First, we construct adversarial attacks in white-box scenarios, which degrade the performance of all well-trained detectors. Moreover, we find that these attacks demonstrate transferability; specifically, attacks crafted against one detector can be transferred to others, indicating that adversarial attacks on detectors can also be constructed in a black-box setting. Finally, we assess common countermeasures and find that standard defense methods against adversarial attacks provide limited mitigation. We attribute these failures to the low signal-to-noise ratio (SNR) of attacked samples as perceived by the detectors. Overall, our results reveal fundamental security limitations of reconstruction-based detectors and highlight the need to rethink existing detection strategies.

cs.CV↗
arXiv2026

Beyond Message Passing: A Semantic View of Agent Communication Protocols

Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired perspective on this emerging landscape by organizing agent communication into three layers: communication, syntactic, and semantic. Under this framework, we systematically analyze 18 representative protocols and compare how they support reliable transport, structured interaction, and meaning-level coordination. Our analysis shows a clear imbalance in current protocol design. Most protocols provide increasingly mature support for transport, streaming, schema definition, and lifecycle management, but offer limited protocol-level mechanisms for clarification, context alignment, and verification. As a result, semantic responsibilities are often pushed into prompts, wrappers, or application-specific orchestration logic, creating hidden interoperability and maintenance costs. To make this gap actionable, we further identify major forms of technical debt in today's protocol ecosystem and distill practical guidance for selecting protocols under different deployment settings. We conclude by outlining a research agenda for interoperable, secure, and semantically robust agent ecosystems that move beyond message passing toward shared understanding.

cs.NI↗
arXiv2026

A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation

The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems. However, existing compilation methods are limited to predefined tasks, and the community lacks a comprehensive benchmark to evaluate the cinematic compilation. To address this, we introduce CineBench, the first benchmark for instruction-driven cinematic video compilation, featuring diverse user instructions and high-quality ground-truth compilations annotated by professional editors. To overcome contextual collapse and temporal fragmentation, we present CineAgents, a multi-agent system that reformulates cinematic video compilation into ``design-and-compose'' paradigm. CineAgents performs script reverse-engineering to construct a hierarchical narrative memory to provide multi-level context and employs an iterative narrative planning process that refines a creative blueprint into a final compiled script. Extensive experiments demonstrate that CineAgents significantly outperforms existing methods, generating compilations with superior narrative coherence and logical coherence.

cs.CV↗
arXiv2026

Hidden in Plain Sight: Visual-to-Symbolic Analytical Solution Inference from Field Visualizations

Recovering analytical solutions of physical fields from visual observations is a fundamental yet underexplored capability for AI-assisted scientific reasoning. We study visual-to-symbolic analytical solution inference (ViSA) for two-dimensional linear steady-state fields: given field visualizations (and first-order derivatives) plus minimal auxiliary metadata, the model must output a single executable SymPy expression with fully instantiated numeric constants. We introduce ViSA-R2 and align it with a self-verifying, solution-centric chain-of-thought pipeline that follows a physicist-like pathway: structural pattern recognition solution-family (ansatz) hypothesis parameter derivation consistency verification. We also release ViSA-Bench, a VLM-ready synthetic benchmark covering 30 linear steady-state scenarios with verifiable analytical/symbolic annotations, and evaluate predictions by numerical accuracy, expression-structure similarity, and character-level accuracy. Using an 8B open-weight Qwen3-VL backbone, ViSA-R2 outperforms strong open-source baselines and the evaluated closed-source frontier VLMs under a standardized protocol.

cs.AI↗
arXiv2026

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models

Large Language Models (LLMs) achieve impressive performance across many tasks but remain prone to hallucination, especially in long-form generation where redundant retrieved contexts and lengthy reasoning chains amplify factual errors. Recent studies highlight a critical phenomenon: the closer key information appears to the model outputs, the higher the factual accuracy. However, existing retrieval-augmented language models (RALMs) lack effective mechanisms to ensure this proximity - external evidence is injected into reasoning via multi-turn retrieval, but this cannot ensure key information stays close to the outputs. We propose Micro-Macro Retrieval (M2R), a novel retrieve-while-generate framework to fill this gap. At the macro level, M2R retrieves coarse-grained evidence from external sources; at the micro level, it extracts essential results from a key information repository built during reasoning and reuses them while generating answers. This design directly addresses the key-information-to-output proximity bottleneck, effectively reducing hallucination in long-form tasks. M2R is trained with a curriculum learning-based reinforcement learning strategy using customized rule-based rewards, enabling stable acquisition of retrieval and grounding skills. Extensive experiments across different benchmarks demonstrate the effectiveness of M2R, especially in lengthy-context settings.

cs.CL↗
arXiv2026

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification

The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However, as one of the earliest and most fundamental tasks integrated into this paradigm, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to traditional deep learning models, despite their overwhelming advantages in pre-training data and model parameters. This paradox prompts a critical rethinking: where exactly does the performance degradation originate? In this paper, we conduct extensive experiments on 14 open-source medical MLLMs across three representative image classification datasets. Moving beyond superficial performance benchmarking, we employ feature probing to track the information flow of visual features module-by-module and layer-by-layer throughout the entire MLLM pipeline, enabling explicit visualization of where and how classification signals are distorted, diluted, or overridden. As the first attempt to dissect classification performance degradation in medical MLLMs, our findings reveal four failure modes: 1) quality limitation in visual representation, 2) fidelity loss in connector projection, 3) comprehension deficit in LLM reasoning, and 4) misalignment of semantic mapping. Meanwhile, we introduce quantitative scores that characterize the healthiness of feature evolution, enabling principled comparisons across diverse MLLMs and datasets. Furthermore, we provide insightful discussions centered on the critical barriers that prevent current medical MLLMs from fulfilling their promised clinical potential. We hope that our work provokes rethinking within the community-highlighting that the road from high expectations to clinically deployable MLLMs remains long and winding.

cs.CV↗
arXiv2026

Policy-Aware Design of Large-Scale Factorial Experiments

Digital firms routinely run many online experiments on shared user populations. When product decisions are compositional, such as combinations of interface elements, flows, messages, or incentives, the number of feasible interventions grows combinatorially, while available traffic remains limited. Overlapping experiments can therefore generate interaction effects that are poorly handled by decentralized A/B testing. We study how to design large-scale factorial experiments when the objective is not to estimate every treatment effect, but to identify a high-performing policy under a fixed experimentation budget. We propose a two-stage design that centralizes overlapping experiments into a single factorial problem and models expected outcomes as a low-rank tensor. In the first stage, the platform samples a subset of intervention combinations, uses tensor completion to infer performance on untested combinations, and eliminates weak factor levels using estimated marginal contributions. In the second stage, it applies sequential halving to the surviving combinations to select a final policy. We establish gap-independent simple-regret bounds and gap-dependent identification guarantees showing that the relevant complexity scales with the degrees of freedom of the low-rank tensor and the separation structure across factor levels, rather than the full factorial size. In an offline evaluation based on a product-bundling problem constructed from 100 million Taobao interactions, the proposed method substantially outperforms one-shot tensor completion and unstructured best-arm benchmarks, especially in low-budget and high-noise settings. These results show how centralized, policy-aware experimentation can make combinatorial product design operationally feasible at platform scale.

stat.ML↗