arXiv subjects

Yutao Chen

Publications and source records attributed to Yutao Chen.

At least 19 recordsLinked to original sources

arXiv2026

Sub-Infinite Horizon Stochastic Linear-Quadratic Optimal Control Problems and Delayed Backward Riccati Equations

In this paper, we investigate a class of so-called sub-infinite horizon stochastic linear-quadratic optimal control problems, in which the initial time $t$ is arbitrarily taken from $[0,\infty)$ and the running cost is defined over $[t,t+T]$ for a given $T>0$. The optimal control of this type of problem can be obtained by standard methods; however, it is shown that the resulting optimal control is generally time-inconsistent. Thus, instead of seeking an optimal control, which is time-inconsistent, we aim to find a time-consistent, locally optimal, and time-invariant equilibrium strategy, by introducing a new and very interesting type of Riccati equation. Its main feature is that the generator depends on a delay term of the unknown. In other words, this Riccati equation is a backward ordinary differential equation (ODE) with delay, which is equivalent to a forward ODE with advanced terms. Such an equation is essentially a Fredholm integral equation, whose solvability is challenging. We overcome the difficulty by deriving a sharp a priori estimate and applying the Leray--Schauder fixed point theorem. To this end, we establish a comparison theorem between two matrix-valued nonlinear algebraic equations. The convergence behavior of the solution to the Riccati equation as $T\to\infty$ is also provided.

math.OC↗

arXiv2026

Avatar V: Scaling Video-Reference Avatar Video Generation

Generating avatar videos that are not merely visually similar to a target individual but behaviorally recognizable, faithfully reproducing their talking rhythm, gestural tendencies, and expression dynamics, remains an open challenge. Existing methods predominantly condition on single static images, which provide insufficient identity information and cannot capture dynamic motion traits, while standard pixel-level objectives underserve the perceptually critical facial regions that determine avatar fidelity. We present Avatar V, a production-scale framework that addresses these limitations through video-reference-conditioned identity modeling. Rather than compressing identity into fixed-size embeddings, the model conditions directly on the full token sequence of a reference video, learning to reproduce both static identity attributes (facial geometry, skin texture) and dynamic behavioral patterns (talking rhythm, micro-expressions) through attention over the reference context. We introduce Sparse Reference Attention, an asymmetric mechanism achieving linear-complexity conditioning on arbitrarily long references; a motion representation stream enabling closed-loop talking style transfer; and an identity-aware super-resolution refiner inheriting the full reference conditioning. These are supported by a data engine curating 100M+ training clips from 50M raw videos, and a five-stage training pipeline with flow matching pre-training, personality fine-tuning, two-phase distillation (>10x acceleration), and RLHF alignment, deployed across thousands of GPUs. Avatar V generates 1080p videos of unlimited duration, achieving state-of-the-art identity preservation, lip synchronization, and generation quality on our cross-scene benchmark, consistently outperforming leading systems including Seedance 2.0, Kling O3 Pro, Veo 3.1, and OmniHuman 1.5 in both automated metrics and human evaluation.

cs.CV↗

arXiv2026

Programmable spectral symmetries in an anisotropic quantum Rabi simulator

The quantum Rabi model captures fundamental aspects of light--matter interaction, where symmetry dictates both spectra and dynamics. Over the past years, experiments have explored many of its nonperturbative properties, but have mostly focused on the isotropic limit, where rotating and counterrotating processes are locked together, leaving the broader symmetry landscape largely unexplored. Here we realize a programmable anisotropic quantum Rabi model in a superconducting processor, with independent control of the rotating and counterrotating couplings $(g_1,g_2)$ and of a transverse bias $\varepsilon$. Continuous anisotropy tuning, combined with a duality mapping, gives access to the full parameter space from the Jaynes-Cummings to the anti-Jaynes-Cummings limits. In the deep-strong-coupling regime, we show that anisotropy reconstructs the spectrum and turns complete collapse-revival dynamics into incomplete revivals even near degeneracy. With adiabatic state preparation and joint tomography, we resolve an anisotropy-induced ground-state parity switch, a crossing that has no analogue in the isotropic model. We further observe selective tunnelling associated with hidden symmetry in biased Rabi models and track its anisotropic displacement within the same device. These results establish a controllable route to engineering nonperturbative light--matter Hamiltonians, where symmetry, spectrum, and dynamics can be programmed independently.

quant-ph↗

arXiv2026

Learning Mixture Density via Natural Gradient Expectation Maximization

Mixture density networks are neural networks that produce Gaussian mixtures to represent continuous multimodal conditional densities. Standard training procedures involve maximum likelihood estimation using the negative log-likelihood (NLL) objective, which suffers from slow convergence and mode collapse. In this work, we improve the optimization of mixture density networks by integrating their information geometry. Specifically, we interpret mixture density networks as deep latent-variable models and analyze them through an expectation maximization framework, which reveals surprising theoretical connections to natural gradient descent. We then exploit such connections to derive the natural gradient expectation maximization (nGEM) objective. We show that empirically nGEM achieves up to 10$\times$ faster convergence while adding almost zerocomputational overhead, and scales well to high-dimensional data where NLL otherwise fails.

cs.LG↗

arXiv2025

Tight-binding photonics

Photonics, dealing with the generation, manipulation, and detection of photons in various systems, lays the foundation of many advanced technologies. A key task of photonics is to know how photons propagate in complex media such as periodic and aperiodic photonic crystals. The conventional wisdom is to numerically solve the Maxwell equations either by dedicated numerical techniques or brute-force finite-element calculations. Recently, the strict analogy between photonic crystals and theoretical tight-binding models provides an unprecedentedly convenient wayof understanding the spectra and wavefunctions of photonic systems by mapping the complicated differential equationsinto matrixed Hamiltonians that can be easily solved through the band theory and exact diagonalization. in this paper, we present a timely review of tight-binding-like photonics in various platforms, covering fundamental theories, experimental realizations, unique physical efiects, and their potential applications. We also provide a brief outlook on the future trends of this active area. Our review offers an in-depth and comprehensive picture on this rapidly developing field and may shed light on the future design on advanced tight-binding-like photonic devices.

physics.optics↗

arXiv2025

Kalman Filter Aided Federated Koopman Learning

Real-time control and estimation are pivotal for applications such as industrial automation and future healthcare. The realization of this vision relies heavily on efficient interactions with nonlinear systems. Therefore, Koopman learning, which leverages the power of deep learning to linearize nonlinear systems, has been one of the most successful examples of mitigating the complexity inherent in nonlinearity. However, the existing literature assumes access to accurate system states and abundant high-quality data for Koopman analysis, which is usually impractical in real-world scenarios. To fill this void, this paper considers the case where only observations of the system are available and where the observation data is insufficient to accomplish an independent Koopman analysis. To this end, we propose Kalman Filter aided Federated Koopman Learning (KF-FedKL), which pioneers the combination of Kalman filtering and federated learning with Koopman analysis. By doing so, we can achieve collaborative linearization with privacy guarantees. Specifically, we employ a straightforward yet efficient loss function to drive the training of a deep Koopman network for linearization. To obtain system information devoid of individual information from observation data, we leverage the unscented Kalman filter and the unscented Rauch-Tung-Striebel smoother. To achieve collaboration between clients, we adopt the federated learning framework and develop a modified FedAvg algorithm to orchestrate the collaboration. A convergence analysis of the proposed framework is also presented. Finally, through extensive numerical simulations, we showcase the performance of KF-FedKL under various situations.

cs.IT↗

arXiv2025

An Efficient Reservation Protocol for Medium Access: When Tree Splitting Meets Reinforcement Learning

As an enhanced version of massive machine-type communication in 5G, massive communication has emerged as one of the six usage scenarios anticipated for 6G, owing to its potential in industrial internet-of-things and smart metering. Driven by the need for random multiple-access (RMA) in massive communication, as well as, next-generation Wi-Fi, medium access control has attracted considerable recent attention. Holding the promise of attaining bandwidth-efficient collision resolution, multiaccess reservation no doubt plays a central role in RMA, e.g., the distributed coordination function (DCF) in IEEE 802.11. In this paper, we are interested in maximizing the bandwidth efficiency of reservation protocols for RMA under quality-of-service constraints. Particularly, we present a tree splitting based reservation scheme, in which the attempting probability is dynamically optimized by partially observable Markov decision process or reinforcement learning (RL). The RL-empowered tree-splitting algorithm guarantees that all these terminals with backlogged packets at the beginning of a contention cycle can be scheduled, thereby providing a first-in-first-out service. More importantly, it substantially reduces the reservation bandwidth determined by the communication complexity of DCF, through judiciously conceived coding and interaction for exchanging information required by distributed ordering. Simulations demonstrate that the proposed algorithm outperforms the CSMA/CA based DCF in IEEE 802.11.

cs.IT↗

arXiv2023

EVE: Efficient zero-shot text-based Video Editing with Depth Map Guidance and Temporal Consistency Constraints

Motivated by the superior performance of image diffusion models, more and more researchers strive to extend these models to the text-based video editing task. Nevertheless, current video editing tasks mainly suffer from the dilemma between the high fine-tuning cost and the limited generation capacity. Compared with images, we conjecture that videos necessitate more constraints to preserve the temporal consistency during editing. Towards this end, we propose EVE, a robust and efficient zero-shot video editing method. Under the guidance of depth maps and temporal consistency constraints, EVE derives satisfactory video editing results with an affordable computational and time cost. Moreover, recognizing the absence of a publicly available video editing dataset for fair comparisons, we construct a new benchmark ZVE-50 dataset. Through comprehensive experimentation, we validate that EVE could achieve a satisfactory trade-off between performance and efficiency. We will release our dataset and codebase to facilitate future researchers.

cs.CV↗

arXiv2023

Analysis of Age of Incorrect Information under Generic Transmission Delay

This paper investigates the Age of Incorrect Information (AoII) in a communication system whose channel suffers a random delay. We consider a slotted-time system where a transmitter observes a dynamic source and decides when to send updates to a remote receiver through the communication channel. The threshold policy, under which the transmitter initiates transmission only when the AoII exceeds the threshold, governs the transmitter's decision. In this paper, we analyze and calculate the performance of the threshold policy in terms of the achieved AoII. Using the Markov chain to characterize the system evolution, the expected AoII can be obtained precisely by solving a system of linear equations whose size is finite and depends on the threshold. We also give closed-form expressions of the expected AoII under two particular thresholds. Finally, calculation results show that there are better strategies than the transmitter constantly transmitting new updates.

cs.IT↗

arXiv2023

Preempting to Minimize Age of Incorrect Information under Transmission Delay

We study the problem of optimizing the decisions of a preemptively capable transmitter to minimize the Age of Incorrect Information (AoII) when the communication channel has a random delay. We consider a slotted-time system where a transmitter observes a Markovian source and makes decisions based on the system status. In each time slot, the transmitter decides whether to preempt or skip when the channel is busy. When the channel is idle, the transmitter decides whether to send a new update. A remote receiver estimates the state of the Markovian source based on the update it receives. We consider a generic transmission delay and assume that the transmission delay is independent and identically distributed for each update. This paper aims to optimize the transmitter's decision in each time slot to minimize the AoII with generic time penalty functions. To this end, we first use the Markov decision process to formulate the optimization problem and derive the analytical expressions of the expected AoIIs achieved by two canonical preemptive policies. Then, we prove the existence of the optimal policy and provide a feasible value iteration algorithm to approximate the optimal policy. However, the value iteration algorithm will be computationally expensive if we want considerable confidence in the approximation. Therefore, we analyze the system characteristics under two canonical delay distributions and theoretically obtain the corresponding optimal policies using the policy improvement theorem. Finally, numerical results are presented to illustrate the performance improvements brought about by the preemption capability.

cs.IT↗

arXiv2023

Minimizing Age of Incorrect Information over a Channel with Random Delay

We consider a transmitter-receiver pair in a slotted-time system. The transmitter observes a dynamic source and sends updates to a remote receiver through an error-free communication channel that suffers a random delay. We consider two cases. In the first case, the update is guaranteed to be delivered within a certain number of time slots. In the second case, the update is immediately discarded once the transmission time exceeds a predetermined value. The receiver estimates the state of the dynamic source using the received updates. In this paper, we adopt the Age of Incorrect Information (AoII) as the performance metric and investigate the problem of optimizing the transmitter's action in each time slot to minimize AoII. We first characterize the optimization problem using the Markov decision process and investigate the performance of the threshold policy, under which the transmitter transmits updates only when the transmission is allowed and the AoII exceeds the threshold $τ$. By delving into the characteristics of the system evolution, we precisely compute the expected AoII achieved by the threshold policy using the Markov chain. Then, we prove that the optimal policy exists and provide a computable relative value iteration algorithm to estimate the optimal policy. Furthermore, by leveraging the policy improvement theorem, we theoretically prove that, under an easily verifiable condition, the optimal policy is the threshold policy with $τ=1$. Finally, numerical results are presented to highlight the performance of the optimal policy.

cs.IT↗

arXiv2023

Age of Incorrect Information under Delay

This paper investigates the problem of minimizing the Age of Incorrect Information (AoII) when the communication channel has a random delay. We consider a slotted-time system where a transmitter observes a dynamic source and decides when to send updates to a remote receiver through a channel with random delay. The receiver maintains estimates of the state of the dynamic source based on the received updates. In this paper, we adopt AoII as the performance metric and investigate the problem of optimizing the transmitter's action in each time slot to minimize AoII. We first characterize the considered problem using Markov Decision Process (MDP). Then, leveraging the policy improvement theorem and under an easy-to-verify condition, we prove that the optimal decision for the transmitter is to initiate a transmission whenever the channel is idle and AoII is not zero. The results apply to generic delay distribution. Lastly, we verify the condition numerically and provide the numerical results that highlight the performance of the optimal policy.

cs.IT↗

arXiv2023

Minimizing Age of Incorrect Information in the Presence of Timeout

We consider a slotted-time system with a transmitter-receiver pair. In the system, a transmitter observes a dynamic source and sends updates to a remote receiver through a communication channel. We assume that the channel is error-free but suffers a random delay. Moreover, when an update has been transmitted for too long, the transmission will be terminated immediately, and the update will be discarded. We assume the maximum transmission time is predetermined and is not controlled by the transmitter. The receiver will maintain estimates of the current state of the dynamic source using the received updates. In this paper, we adopt the Age of Incorrect Information (AoII) as the performance metric and investigate the problem of optimizing the transmitter's action in each time slot to minimize AoII. We first characterize the optimization problem using Markov Decision Process and evaluate the performance of some canonical transmission policies. Then, by leveraging the policy improvement theorem, we prove that, under a simple and easy-to-verify condition, the optimal policy for the transmitter is the one that initiates a transmission whenever the channel is idle and AoII is not zero. Lastly, we take the case where the transmission time is geometrically distributed as an example. For this example, we verify the condition numerically and provide numerical results that highlight the performance of the optimal policy.

cs.IT↗

arXiv2022

Two-dimensional characterization of three-dimensional magnetic bubbles in Fe$_3$Sn$_2$ nanostructures

We report differential phase contrast scanning transmission electron microscopy (TEM) of nanoscale magnetic objects in Kagome ferromagnet Fe$_3$Sn$_2$ nanostructures. This technique can directly detect the deflection angle of a focused electron beam, thus allowing clear identification of the real magnetic structures of two magnetic objects including three-ring and complex arch-shaped vortices in Fe$_3$Sn$_2$ by Lorentz transmission electron microscopy imaging. Numerical calculations based on real material-specific parameters well reproduced the experimental results, showing that the magnetic objects can be attributed to integral magnetizations of two types of complex three-dimensional (3D) magnetic skyrmion bubbles with depth-modulated spin twisting. Magnetic configurations obtained using the high-resolution TEM are generally considered as two-dimensional (2D) magnetic objects previously. Our results imply the importance of the integral magnetizations of underestimated 3D magnetic structures in 2D TEM magnetic characterizations.

cond-mat.mtrl-sci↗

arXiv2022

Hint for a minimal interaction length in $e^+e^-\toγγ$ annihilation in total cross section of centre-of-mass energies 55-207 GeV

The measurements of the total cross section of the $ e^+e^-\toγγ$ reaction from the VENUS, TOPAS, OPAL, DELPHI, ALEPH and L3 collaborations, collected between 1989 to 2003, are used to perform a $ χ^{2} $ test to search for a finite interaction length in direct contact term. The experimental data of the total cross section compared to the QED cross section of a $ χ^{2} $ test allows, to set limit on a finite interaction length $ r_{e}=(1.25\pm 0.16) \times 10 ^{-17} [cm] $. In the direct contact term annihilation is this interaction lengths a measure for the size of the electron.

hep-ex↗

arXiv2022

An Efficient MPC Algorithm For Switched Systems with Minimum Dwell Time Constraints

This paper presents an efficient suboptimal model predictive control (MPC) algorithm for nonlinear switched systems subject to minimum dwell time constraints (MTC). While MTC are required for most physical systems due to stability, power and mechanical restrictions, MPC optimization problems with MTC are challenging to solve. To efficiently solve such problems, the on-line MPC optimization problem is decomposed into a sequence of simpler problems, which include two nonlinear programs (NLP) and a rounding step, as typically done in mixed-integer optimal control (MIOC). Unlike the classical approach that embeds MTC in a mixed-integer linear program (MILP) with combinatorial constraints in the rounding step, our proposal is to embed the MTC in one of the NLPs using move blocking. Such a formulation can speedup on-line computations by employing recent move blocking algorithms for NLP problems and by using a simple sum-up-rounding (SUR) method for the rounding step. An explicit upper bound of the integer approximation error for the rounding step is given. In addition, a combined shrinking and receding horizon strategy is developed to satisfy closed-loop MTC. Recursive feasibility is proven using a $l$-step control invariant ($l$-CI) set, where $l$ is the minimum dwell time step length. An algorithm to compute $l$-CI sets for switched linear systems off-line is also presented. Numerical studies show significant speed-up and comparable control performance of the proposed MPC algorithm against the classical approach, though at the cost of sub-optimal solutions.

math.OC↗

arXiv2021

Minimizing Age of Incorrect Information for Unreliable Channel with Power Constraint

Age of Incorrect Information (AoII) is a newly introduced performance metric that considers communication goals. Therefore, comparing with traditional performance metrics and the recently introduced metric - Age of Information (AoI), AoII achieves better performance in many real-life applications. However, the fundamental nature of AoII has been elusive so far. In this paper, we consider the AoII in a system where a transmitter sends updates about a multi-state Markovian source to a remote receiver through an unreliable channel. The communication goal is to minimize AoII subject to a power constraint. We cast the problem into a Constrained Markov Decision Process (CMDP) and prove that the optimal policy is a mixture of two deterministic threshold policies. Afterward, by leveraging the notion of Relative Value Iteration (RVI) and the structural properties of threshold policy, we propose an efficient algorithm to find the threshold policies as well as the mixing coefficient. Lastly, numerical results are laid out to highlight the performance of AoII-optimal policy.

cs.IT↗

arXiv2021

Learn to Predict Vertical Track Irregularity with Extremely Imbalanced Data

Railway systems require regular manual maintenance, a large part of which is dedicated to inspecting track deformation. Such deformation might severely impact trains' runtime security, whereas such inspections remain costly for both finance and human resources. Therefore, a more precise and efficient approach to detect railway track deformation is in urgent need. In this paper, we showcase an application framework for predicting vertical track irregularity, based on a real-world, large-scale dataset produced by several operating railways in China. We have conducted extensive experiments on various machine learning & ensemble learning algorithms in an effort to maximize the model's capability in capturing any irregularity. We also proposed a novel approach for handling imbalanced data in multivariate time series prediction tasks with adaptive data sampling and penalized loss. Such an approach has proven to reduce models' sensitivity to the imbalanced target domain, thus improving its performance in predicting rare extreme values.

cs.LG↗