arXiv subjects

Yuchen Wang

Publications and source records attributed to Yuchen Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Earth Embeddings Reveal Diverse Urban Signals from Space

Conventional urban indicators derived from censuses, surveys, and administrative records are often costly, spatially inconsistent, and slow to update. Recent geospatial foundation models enable Earth embeddings, compact satellite image representations transferable across downstream tasks, but their utility for neighborhood-scale urban monitoring remains unclear. Here, we benchmark three Earth embedding families, AlphaEarth, Prithvi, and Clay, for urban signal prediction across six U.S. metropolitan areas from 2020 to 2023. Using a unified supervised-learning framework, we predict 14 neighborhood-level indicators spanning crime, income, health, and travel behavior, and evaluate performance under four settings: global, city-wise, year-wise, and city-year. Results show that Earth embeddings capture substantial urban variation, with the highest predictive skill for outcomes more directly tied to built-environment structure, including chronic health burdens and dominant commuting modes. By contrast, indicators shaped more strongly by fine-scale behavior and local policy, such as cycling, remain difficult to infer. Predictive performance varies markedly across cities but remains comparatively stable across years, indicating strong spatial heterogeneity alongside temporal robustness. Exploratory analysis suggests that cross-city variation in predictive performance is associated with urban form in task-specific ways. Controlled dimensionality experiments show that representation efficiency is critical: compact 64-dimensional AlphaEarth embeddings remain more informative than 64-dimensional reductions of Prithvi and Clay. This study establishes a benchmark for evaluating Earth embeddings in urban remote sensing and demonstrates their potential as scalable, low-cost features for SDG-aligned neighborhood-scale urban monitoring.

cs.LG↗

arXiv2026

Understanding the Theoretical Foundations of Deep Neural Networks through Differential Equations

Deep neural networks (DNNs) have achieved remarkable empirical success, yet the absence of a principled theoretical foundation continues to hinder their systematic development. In this survey, we present differential equations as a theoretical foundation for understanding, analyzing, and improving DNNs. We organize the discussion around three guiding questions: i) how differential equations offer a principled understanding of DNN architectures, ii) how tools from differential equations can be used to improve DNN performance in a principled way, and iii) what real-world applications benefit from grounding DNNs in differential equations. We adopt a two-fold perspective spanning the model level, which interprets the whole DNN as a differential equation, and the layer level, which models individual DNN components as differential equations. From these two perspectives, we review how this framework connects model design, theoretical analysis, and performance improvement. We further discuss real-world applications, as well as key challenges and opportunities for future research.

cs.AI↗

arXiv2026

Modeling Trend Dynamics with Variational Neural ODEs for Information Popularity Prediction

Predicting the future popularity of information in online social networks is a crucial yet challenging task, due to the complex spatiotemporal dynamics underlying information diffusion. Existing methods typically use structural or sequential patterns within the observation window as direct inputs for subsequent popularity prediction. However, most approaches lack the ability to explicitly model the overall trend of popularity up to the prediction time, which leads to limited predictive capability. To address these limitations, we propose VNOIP, a novel method based on variational neural Ordinary Differential Equations (ODEs) for information popularity prediction. Specifically, VNOIP introduces bidirectional jump ODEs with attention mechanisms to capture long-range dependencies and bidirectional context within cascade sequences. Furthermore, by jointly considering both cascade patterns and overall trend temporal patterns, VNOIP explicitly models the continuous-time dynamics of popularity trend trajectories with variational neural ODEs. Additionally, a knowledge distillation loss is employed to align the evolution of prior and posterior latent variables. Extensive experiments on real-world datasets demonstrate that VNOIP is highly competitive in both prediction accuracy and efficiency compared to state-of-the-art baselines.

cs.SI↗

arXiv2026

D-instanton Effects on a D3-brane

It has been proposed by Sen that the D-instanton effects in string theory can be systematically determined through the framework of open-closed string field theory. We apply the latter formalism to analyze the D-instanton corrections to the quantum effective action of a D3-brane in type IIB superstring theory, and determine the leading single and multi-instanton contributions to the $D^4 F^4$ effective coupling which is unprotected by supersymmetry. Notably, while we find that the one-instanton contribution agrees with a conjecture of Green and Gutperle, the multi-instanton contribution disagrees with the conjecture.

hep-th↗

arXiv2026

A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving

Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consistent nature of kinematics across diverse domains, we aim to incorporate domain-invariant knowledge to enhance zero-shot trajectory prediction capabilities. The key challenges include: 1) effectively extracting domain-invariant scene representations, and 2) integrating invariant features with kinematic models to enable generalized predictions. To address these challenges, we propose a novel generalizable Physics-guided Causal Model (PCM), which comprises two core components: a Disentangled Scene Encoder, which adopts intervention-based disentanglement to extract domain-invariant features from scenes, and a CausalODE Decoder, which employs a causal attention mechanism to effectively integrate kinematic models with meaningful contextual information. Extensive experiments on real-world autonomous driving datasets demonstrate our method's superior zero-shot generalization performance in unseen cities, significantly outperforming competitive baselines. The source code is released at https://github.com/ZY-Zong/Physics-guided-Causal-Model.

cs.AI↗

arXiv2026

HA2F: Dual-module Collaboration-Guided Hierarchical Adaptive Aggregation Framework for Remote Sensing Change Detection

Remote sensing change detection (RSCD) aims to identify the spatio-temporal changes of land cover, providing critical support for multi-disciplinary applications (e.g., environmental monitoring, disaster assessment, and climate change studies). Existing methods focus either on extracting features from localized patches, or pursue processing entire images holistically, which leads to the cross temporal feature matching deviation and exhibiting sensitivity to radiometric and geometric noise. Following the above issues, we propose a dual-module collaboration guided hierarchical adaptive aggregation framework, namely HA2F, which consists of dynamic hierarchical feature calibration module (DHFCM) and noise-adaptive feature refinement module (NAFRM). The former dynamically fuses adjacent-level features through perceptual feature selection, suppressing irrelevant discrepancies to address multi-temporal feature alignment deviations. The NAFRM utilizes the dual feature selection mechanism to highlight the change sensitive regions and generate spatial masks, suppressing the interference of irrelevant regions or shadows. Extensive experiments verify the effectiveness of the proposed HA2F, which achieves state-of-the-art performance on LEVIR-CD, WHU-CD, and SYSU-CD datasets, surpassing existing comparative methods in terms of both precision metrics and computational efficiency. In addition, ablation experiments show that DHFCM and NAFRM are effective. \href{https://huggingface.co/InPeerReview/RemoteSensingChangeDetection-RSCD.HA2F}{HA2F Official Code is Available Here!}

cs.CV↗

arXiv2026

Lens: A Knowledge-Guided Foundation Model for Network Traffic

Network traffic refers to the amount of data being sent and received over the Internet or any system that connects computers. Analyzing network traffic is vital for security and management, yet remains challenging due to the heterogeneity of plain-text packet headers and encrypted payloads. To capture the latent semantics of traffic, recent studies have adopted Transformer-based pretraining techniques to learn network representations from massive traffic data. However, these methods pre-train on data-driven tasks but overlook network knowledge, such as masking partial digits of the indivisible network port numbers for prediction, thereby limiting semantic understanding. In addition, they struggle to extend classification to new classes during fine-tuning due to the distribution shift. Motivated by these limitations, we propose \Lens, a unified knowledge-guided foundation model for both network traffic classification and generation. In pretraining, we propose a Knowledge-Guided Mask Span Prediction method with textual context for learning knowledge-enriched representations. For extending to new classes in finetuning, we reframe the traffic classification as a closed-ended generation task and introduce context-aware finetuning to adapt to the distribution shift. Evaluation results across various benchmark datasets demonstrate that the proposed Lens~achieves superior performance on both classification and generation tasks. For traffic classification, Lens~outperforms competitive baselines substantially on 8 out of 12 tasks with an average accuracy of \textbf{96.33\%} and extends to novel classes with significantly better performance. For traffic generation, Lens~generates better high-fidelity network traffic for network simulation, gaining up to \textbf{30.46\%} and \textbf{33.3\%} better accuracy and F1 in fuzzing tests. We will open-source the code upon publication.

cs.LG↗

arXiv2026

1-GHz VIS-to-MIR frequency combs enabled by CMOS-compatible nanophotonic waveguides

A fully stabilized frequency comb is essential for precision metrology and coherent optical synthesis. However, fully-stabilized frequency combs generally require separate stages for supercontinuum generation (SCG) and self-referencing, largely limiting their compactness. Here, enabled by the low-threshold multi-octave supercontinuum generation and concurrent third-harmonic generation in low-loss silicon nitride waveguides, we present a novel approach to a self-referenced frequency comb source at 1 GHz repetition rate spanning from the full visible (VIS) to the mid-infrared (MIR). Our coherent comb is seeded by an all-polarization-maintaining ultrafast fiber laser at 1556 nm, with a pulse duration of 73 fs at 1 GHz repetition rate. With an injected energy of merely 110 pJ, the pulses propagate through dispersion-engineered Si3N4 waveguides, generating supercontinuum spanning over three octaves from 350-3280 nm i.e. 0.76 PHz of coherent bandwidth. Moreover, the on-chip third harmonic generation provides a carrier envelope offset beat note via f-3f with a signal-to-noise ratio of 43 dB. Fueled by the evolving photonic integration providing possibilities of on-chip filtering and photo-detectors, this approach for single-chip self-referencing of high-repetition-rate frequency combs paves the way for ultrabroadband comb sources with unprecedented compactness and field-readiness.

physics.optics↗

arXiv2026

InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents

LLM agents can reason and use tools, but they often break down on long-horizon tasks due to unbounded context growth and accumulated errors. Common remedies such as context compression or retrieval-augmented prompting introduce trade-offs between information fidelity and reasoning stability. We present InfiAgent, a general-purpose framework that keeps the agent's reasoning context strictly bounded regardless of task duration by externalizing persistent state into a file-centric state abstraction. At each step, the agent reconstructs context from a workspace state snapshot plus a fixed window of recent actions. Experiments on DeepResearch and an 80-paper literature review task show that, without task-specific fine-tuning, InfiAgent with a 20B open-source model is competitive with larger proprietary systems and maintains substantially higher long-horizon coverage than context-centric baselines. These results support explicit state externalization as a practical foundation for stable long-horizon agents. Github Repo:https://github.com/ChenglinPoly/infiAgent

cs.AI↗

arXiv2025

GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection

Active Speaker Detection (ASD) aims to identify who is currently speaking in each frame of a video. Most state-of-the-art approaches rely on late fusion to combine visual and audio features, but late fusion often fails to capture fine-grained cross-modal interactions, which can be critical for robust performance in unconstrained scenarios. In this paper, we introduce GateFusion, a novel architecture that combines strong pretrained unimodal encoders with a Hierarchical Gated Fusion Decoder (HiGate). HiGate enables progressive, multi-depth fusion by adaptively injecting contextual features from one modality into the other at multiple layers of the Transformer backbone, guided by learnable, bimodally-conditioned gates. To further strengthen multimodal learning, we propose two auxiliary objectives: Masked Alignment Loss (MAL) to align unimodal outputs with multimodal predictions, and Over-Positive Penalty (OPP) to suppress spurious video-only activations. GateFusion establishes new state-of-the-art results on several challenging ASD benchmarks, achieving 77.8% mAP (+9.4%), 86.1% mAP (+2.9%), and 96.1% mAP (+0.5%) on Ego4D-ASD, UniTalk, and WASD benchmarks, respectively, and delivering competitive performance on AVA-ActiveSpeaker. Out-of-domain experiments demonstrate the generalization of our model, while comprehensive ablations show the complementary benefits of each component.

cs.CV↗

arXiv2025

Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the robustness of the vision-language models. Different from the vanilla dropout, we apply dropout on the tokens of the textual and visual branches, where we evaluate the token significance considering both intra-modal context and inter-modal alignment, enabling flexible dropout probabilities for each token. Moreover, to maintain semantic alignment for general knowledge transfer while encouraging the diverse representations that dropout introduces, we further propose residual entropy regularization. Experiments on 15 benchmarks show our method's effectiveness in challenging scenarios like low-shot learning, long-tail classification, and out-of-distribution generalization. Notably, our method surpasses regularization-based methods including KgCoOp by 5.10% and PromptSRC by 2.13% in performance on base-to-novel generalization.

cs.CV↗

arXiv2025

Qumode-Based Variational Quantum Eigensolver for Molecular Excited States

We introduce the Qumode Subspace Variational Quantum Eigensolver (QSS-VQE), a hybrid quantum-classical algorithm for computing molecular excited states using the Fock basis of bosonic qumodes in circuit quantum electrodynamics (cQED) devices. This approach harnesses the native universal gate sets of qubit-qumode architectures to construct highly expressive variational ansatze, offering potential advantages over conventional qubit-based methods. In QSS-VQE, the electronic structure Hamiltonian is first mapped to a qubit representation and subsequently embedded into the Fock space of bosonic qumodes, enabling efficient state preparation and reduced quantum resource requirements. We demonstrate the performance of QSS-VQE through simulations of molecular excited states, including dihydrogen and a conical intersection in cytosine. Additionally, we explore a bosonic model Hamiltonian to assess the expressivity of qumode gates, identifying regimes where qumode-based implementations outperform purely qubit-based approaches. These results highlight the promise of leveraging bosonic degrees of freedom for enhanced quantum simulation of complex molecular systems.

quant-ph↗

arXiv2025

Robust Decentralized Multi-armed Bandits: From Corruption-Resilience to Byzantine-Resilience

Decentralized cooperative multi-agent multi-armed bandits (DeCMA2B) considers how multiple agents collaborate in a decentralized multi-armed bandit setting. Though this problem has been extensively studied in previous work, most existing methods remain susceptible to various adversarial attacks. In this paper, we first study DeCMA2B with adversarial corruption, where an adversary can corrupt reward observations of all agents with a limited corruption budget. We propose a robust algorithm, called DeMABAR, which ensures that each agent's individual regret suffers only an additive term proportional to the corruption budget. Then we consider a more realistic scenario where the adversary can only attack a small number of agents. Our theoretical analysis shows that the DeMABAR algorithm can also almost completely eliminate the influence of adversarial attacks and is inherently robust in the Byzantine setting, where an unknown fraction of the agents can be Byzantine, i.e., may arbitrarily select arms and communicate wrong information. We also conduct numerical experiments to illustrate the robustness and effectiveness of the proposed method.

cs.LG↗

arXiv2025

Correlated Purification for Restoring $N$-Representability in Quantum Simulation

Classical shadow tomography offers a scalable route to estimating properties of quantum states, but the resulting reduced density matrices (RDMs) often violate constraints that ensure they represent $N$-electron states -- known as $N$-representability conditions -- because of statistical and hardware noise. We present a correlated purification framework based on semidefinite programming to restore accuracy to these noisy, unphysical two-electron RDMs. The method performs a bi-objective optimization that minimizes both the many-electron energy and the nuclear norm of the change in the measured 2-RDM. The nuclear norm, often employed in matrix completion, promotes low-rank, physically meaningful corrections to the 2-RDM, while the energy term acts as a regularization term that can improve the purity of the ground state. While the method is particularly effective for the ground state, it can also be applied to excited and non-stationary states by decreasing the weight of the energy relative to the error norm. In an application to fermionic shadow tomography of large hydrogen chains, correlated purification yields substantial reductions in both energy and 2-RDM error, achieving chemical accuracy across dissociation curves. This framework provides a robust strategy for tomography in many-body quantum simulations.

quant-ph↗

arXiv2025

Constrained Shadow Tomography for Molecular Simulation on Quantum Devices

Quantum state tomography is a fundamental task in quantum information science, enabling detailed characterization of correlations, entanglement, and electronic structure in quantum systems. However, its exponential measurement and computational demands limit scalability, motivating efficient alternatives such as classical shadows, which enable accurate prediction of many observables from randomized measurements. In this work, we introduce a bi-objective semidefinite programming approach for constrained shadow tomography, designed to reconstruct the two-particle reduced density matrix (2-RDM) from noisy or incomplete shadow data. By integrating $N$-representability constraints and nuclear-norm regularization into the optimization, the method builds an $N$-representable 2-RDM that balances fidelity to the shadow measurements with energy minimization. This unified framework mitigates noise and sampling errors while enforcing physical consistency in the reconstructed states. Numerical and hardware results demonstrate that the approach significantly improves accuracy, noise resilience, and scalability, providing a robust foundation for physically consistent fermionic state reconstruction in realistic quantum simulations.

quant-ph↗

arXiv2025

Future-Proofing Programmers: Optimal Knowledge Tracing for AI-Assisted Personalized Education

Learning to learn is becoming a science, driven by the convergence of knowledge tracing, signal processing, and generative AI to model student learning states and optimize education. We propose CoTutor, an AI-driven model that enhances Bayesian Knowledge Tracing with signal processing techniques to improve student progress modeling and deliver adaptive feedback and strategies. Deployed as an AI copilot, CoTutor combines generative AI with adaptive learning technology. In university trials, it has demonstrated measurable improvements in learning outcomes while outperforming conventional educational tools. Our results highlight its potential for AI-driven personalization, scalability, and future opportunities for advancing privacy and ethical considerations in educational technology. Inspired by Richard Hamming's vision of computer-aided 'learning to learn,' CoTutor applies convex optimization and signal processing to automate and scale up learning analytics, while reserving pedagogical judgment for humans, ensuring AI facilitates the process of knowledge tracing while enabling learners to uncover new insights.

cs.AI↗

arXiv2025

Deep Dubbing: End-to-End Auto-Audiobook System with Text-to-Timbre and Context-Aware Instruct-TTS

The pipeline for multi-participant audiobook production primarily consists of three stages: script analysis, character voice timbre selection, and speech synthesis. Among these, script analysis can be automated with high accuracy using NLP models, whereas character voice timbre selection still relies on manual effort. Speech synthesis uses either manual dubbing or text-to-speech (TTS). While TTS boosts efficiency, it struggles with emotional expression, intonation control, and contextual scene adaptation. To address these challenges, we propose DeepDubbing, an end-to-end automated system for multi-participant audiobook production. The system comprises two main components: a Text-to-Timbre (TTT) model and a Context-Aware Instruct-TTS (CA-Instruct-TTS) model. The TTT model generates role-specific timbre embeddings conditioned on text descriptions. The CA-Instruct-TTS model synthesizes expressive speech by analyzing contextual dialogue and incorporating fine-grained emotional instructions. This system enables the automated generation of multi-participant audiobooks with both timbre-matched character voices and emotionally expressive narration, offering a novel solution for audiobook production.

eess.AS↗

arXiv2025

10-W Sub-100-fs Ultrafast Cr:ZnS/ZnSe MOPA System enabled by doping gradient engineering

We report on a high-power mid-infrared femtosecond master oscillator power amplifier (MOPA) system, employing Cr:ZnS and Cr:ZnSe polycrystals with fine-tuned doping profiles. Based on the soft-aperture Kerr-lens mode-locking in the soliton regime, the seed oscillator generates ~40-fs pulses with a repetition rate ~173 MHz with an average power close to 400 mW. The amplification process of the seed pulse train is investigated in depth in a single-pass configuration for both Cr:ZnS and Cr:ZnSe crystal rods. For further power scaling, a dual-stage MOPA system has been implemented, generating pulse trains with an average power up to 10.4 W, limited only by the pump source, with a re-compressed pulse duration of 78 fs using a dispersion compensator comprising chirped mirrors and sapphire plates. This work paves the way for further power scaling of mid-infrared Cr:ZnS/ZnSe ultrafast laser systems without moving parts for applications in material processing, remote sensing and medicine.

physics.optics↗