arXiv subjects

Yi Zuo

Publications and source records attributed to Yi Zuo.

15 recordsLinked to original sources

arXiv2026

DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis

Trajectory-controlled video generation has become essential for controllable video generation. While current methods perform well under small-view camera motions, they degrade significantly with large-view motions. Existing solutions for extreme-view synthesis typically require dedicated video pairs, demanding substantial annotation effort. To address these limitations, we propose Dynamic Extreme VIew Synthesis-GRPO (DEVIS-GRPO), a GRPO-based framework for trajectory-controlled video generation, the first online policy gradient method for extreme view video generation. Central to our approach is a novel sampling strategy: Accumulative Dynamic Extreme VIew Synthesis (ADEVIS), which achieves large-view camera motions by progressively accumulating small-view increments. This method delivers two key advantages: 1) enhanced training efficiency, as it eliminates the need to warm-start the policy model by collecting expensive paired large-view videos, and 2) increased sampling diversity, achieved by flexibly varying trajectory configurations. Finally, we designed a multi-level consistency-quality reward function to select high-quality samples for model optimization. Experiments on the Kubric-4D, iPhone, and DL3DV datasets demonstrate our method's superiority. On Kubric-4D, we achieve relative improvements of 21.57% in PSNR and 7.31% in SSIM over the second-best method in non-occlusion areas. On iPhone, LPIPS is reduced by 18.56%.

cs.CV↗

arXiv2025

Optical multistability in a compact microcavity enabled by near-exceptional coupling

Multistability -- the emergence of multiple stable states under identical conditions -- is a hallmark of nonlinear complexity and an enabling mechanism for multilevel optical memory and photonic computing. Its realization in a compact footprint, however, is limited by intrinsically weak optical nonlinearities and the enlarged free spectral range that raises the multistability threshold. Here, we overcome this constraint by engineering a pair of spectrally close, ultra-high-Q resonances in a photonic crystal microcavity. Leveraging structural perturbations that deliberately introduce non-Hermitian coupling through a shared radiation channel, we drive the resonances toward an exceptional point with nearly degenerate wavelengths and balanced quality factors approaching $10^6$. This configuration substantially enhances thermo-optical nonlinearity and produces pronounced tristability and hysteresis loops within a footprint of 20 {\mu}m at input powers below 240 {\mu}W. We further demonstrate proof-of-concept optical random-access memory through controlled switching among multistable states. These results establish a general strategy for nonlinear microcavities to achieve energy-efficient multistability for reconfigurable all-optical memories, logic, and neuromorphic processors.

physics.optics↗

arXiv2025

Edit-Your-Interest: Efficient Video Editing via Feature Most-Similar Propagation

Text-to-image (T2I) diffusion models have recently demonstrated significant progress in video editing. However, existing video editing methods are severely limited by their high computational overhead and memory consumption. Furthermore, these approaches often sacrifice visual fidelity, leading to undesirable temporal inconsistencies and artifacts such as blurring and pronounced mosaic-like patterns. We propose Edit-Your-Interest, a lightweight, text-driven, zero-shot video editing method. Edit-Your-Interest introduces a spatio-temporal feature memory to cache features from previous frames, significantly reducing computational overhead compared to full-sequence spatio-temporal modeling approaches. Specifically, we first introduce a Spatio-Temporal Feature Memory bank (SFM), which is designed to efficiently cache and retain the crucial image tokens processed by spatial attention. Second, we propose the Feature Most-Similar Propagation (FMP) method. FMP propagates the most relevant tokens from previous frames to subsequent ones, preserving temporal consistency. Finally, we introduce an SFM update algorithm that continuously refreshes the cached features, ensuring their long-term relevance and effectiveness throughout the video sequence. Furthermore, we leverage cross-attention maps to automatically extract masks for the instances of interest. These masks are seamlessly integrated into the diffusion denoising process, enabling fine-grained control over target objects and allowing Edit-Your-Interest to perform highly accurate edits while robustly preserving the background integrity. Extensive experiments decisively demonstrate that the proposed Edit-Your-Interest outperforms state-of-the-art methods in both efficiency and visual fidelity, validating its superior effectiveness and practicality.

cs.CV↗

arXiv2024

Miniaturized spectrometer enabled by end-to-end deep learning on large-scale radiative cavity array

Miniaturized (mini-) spectrometers are highly desirable tools for chemical, biological, and medical diagnostics because of their potential for portable and in situ spectral detection. In this work, we propose and demonstrate a mini-spectrometer that combines a large-scale radiative cavity array with end-to-end deep learning networks. Specifically, we utilize high-Q bound states in continuum cavities with distinct radiation characteristics as the fundamental units to achieve parallel spectral detection. We realize a 36 $\times$ 30 cavity array that spans a wide spectral range from 1525 to 1605 nm with quality factors above 10^4. We further train a deep network with 8000 outputs to directly map arbitrary spectra to array responses excited by the out-of-plane incident. Experimental results demonstrate that the proposed mini-spectrometer can resolve unknown spectra with a resolution of 0.048 nm in a bandwidth of 80 nm and fidelity exceeding 95%, thus offering a promising method for compact, high resolution, and broadband spectroscopy.

physics.optics↗

arXiv2024

Edit-Your-Motion: Space-Time Diffusion Decoupling Learning for Video Motion Editing

Existing diffusion-based methods have achieved impressive results in human motion editing. However, these methods often exhibit significant ghosting and body distortion in unseen in-the-wild cases. In this paper, we introduce Edit-Your-Motion, a video motion editing method that tackles these challenges through one-shot fine-tuning on unseen cases. Specifically, firstly, we utilized DDIM inversion to initialize the noise, preserving the appearance of the source video and designed a lightweight motion attention adapter module to enhance motion fidelity. DDIM inversion aims to obtain the implicit representations by estimating the prediction noise from the source video, which serves as a starting point for the sampling process, ensuring the appearance consistency between the source and edited videos. The Motion Attention Module (MA) enhances the model's motion editing ability by resolving the conflict between the skeleton features and the appearance features. Secondly, to effectively decouple motion and appearance of source video, we design a spatio-temporal two-stage learning strategy (STL). In the first stage, we focus on learning temporal features of human motion and propose recurrent causal attention (RCA) to ensure consistency between video frames. In the second stage, we shift focus on learning the appearance features of the source video. With Edit-Your-Motion, users can edit the motion of humans in the source video, creating more engaging and diverse content. Extensive qualitative and quantitative experiments, along with user preference studies, show that Edit-Your-Motion outperforms other methods.

cs.CV↗

arXiv2023

The Robust Semantic Segmentation UNCV2023 Challenge Results

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.

cs.CV↗

arXiv2023

Work Statistics and Adiabatic Assumption in Nonequilibrium Many-Body Theory

Keldysh field theory, based on adiabatic assumptions, serves as an widely used framework for addressing nonequilibrium many-body systems. Nonetheless, the validity of such adiabatic assumptions when addressing interacting Gibbs states remains a topic of contention. We use the knowledge of work statistics developed in nonequilibrium thermodynamics to study this problem. Consequently, we deduce a universal theorem delineating the characteristics of evolutions that transition an initial Gibbs state to another. Based on this theorem, we analytically ascertain that adiabatic evolutions fail to transition a non-interacting Gibbs state to its interacting counterpart. However, this adiabatic approach remains a superior approximation relative to its non-adiabatic counterpart. Numerics verifying our theory and predictions are also provided. Furthermore, our findings render insights into the preparation of Gibbs states within the domain of quantum computation.

quant-ph↗

arXiv2023

Ultra-low-loss optical interconnect enabled by topological unidirectional guided resonance

Grating couplers that interconnect photonic chips to off-chip components are of essential importance for various optoelectronics applications. Despite numerous efforts in past decades, existing grating couplers still suffer from poor energy efficiency and thus hinder photonic integration toward a larger scale. Here, we theoretically propose and experimentally demonstrate a method to achieve ultra-low-loss grating coupler by employing topological unidirectional guided resonances (UGRs). Leveraging the unidirectional emitting nature of UGRs, the useless downward radiation is greatly suppressed with no mirror placed on the bottom. By engineering the dispersion and apodizing the geometry of grating, we realize a grating coupler on 340 nm silicon-on-insulator platform with a record-low-loss of 0.34 dB and bandwidth exceeding 30 nm at the telecom wavelength of 1550 nm. We further show a pair of grating couplers works as optic via that interconnects two stacked photonic chips with a loss of only 0.94 dB. Our work sheds light on the feasibility of energy-efficient optical interconnect for silicon photonics, and paving the way to large-scale photonic integration for applications from optical communication to photonic computing.

physics.optics↗

arXiv2022

Distinguishing quantum dynamics via Markovianity and Non-Markovianity

To study various quantum dynamics, it is important to develop effective methods to detect and distinguish different quantum dynamics. A common non-demolition approach is to couple an auxiliary system (ancilla) to the target system, and to measure the ancilla only. By doing so, the target system becomes an environment for the ancilla. Thus, different quantum dynamics of target systems will correspond to different environment properties. Here, we analytically study XX spin chains presenting different kinds of quantum dynamics, namely localized, delocalized, and dephasing dynamics, and build connections between Markovianity and non-Markovianity-the two most common properties of an environment. For a qubit coupled to the XX chain, we derived the reduced density matrix of the qubit through the projection method. Furthermore, when dephasing noise was introduced to the XX chain, we generalized the projection method by introducing an open-system interaction picture - a modification of the Dirac interaction picture. By calculating the reduced density matrix for the qubit analytically and numerically, we found that the delocalized (localized) chain corresponds to the Markovian (non-Markovian) bath when boundary effects are not considered, and the feature of the chain with dephasing noise as a bath is dependent on the dephasing strength. The three kinds of quantum dynamics can be distinguished by measuring the qubit only.

quant-ph↗

arXiv2022

AIM 2022 Challenge on Instagram Filter Removal: Methods and Results

This paper introduces the methods and the results of AIM 2022 challenge on Instagram Filter Removal. Social media filters transform the images by consecutive non-linear operations, and the feature maps of the original content may be interpolated into a different domain. This reduces the overall performance of the recent deep learning strategies. The main goal of this challenge is to produce realistic and visually plausible images where the impact of the filters applied is mitigated while preserving the content. The proposed solutions are ranked in terms of the PSNR value with respect to the original images. There are two prior studies on this task as the baseline, and a total of 9 teams have competed in the final phase of the challenge. The comparison of qualitative results of the proposed solutions and the benchmark for the challenge are presented in this report.

cs.CV↗

arXiv2022

Keldysh Nonlinear Sigma Model for a Free-Fermion Gas under Continuous Measurements

Quantum entanglement phase transitions have provided new insights to quantum many-body dynamics. Both disorders and measurements are found to induce similar entanglement transitions. Here, we provide a theoretical framework that unifies these two seemingly disparate concepts and discloses their internal connections. Specifically, we analytically analyze a $d$-dimension free-fermion gas subject to continuous projective measurements. By mapping the Lindblad master equation to the functional Keldysh field theory, we develop an effective theory termed as the time-local Keldysh nonlinear sigma model, which enables us to analytically describe the physics of the monitored system. Our effective theory resembles to that used to describe the disordered fermionic systems. As an application of the effective theory, we study the transport property and obtain a Drude-form conductivity where the elastic scattering time is replaced by the inverse measurement strength. According to these similarities, two different concepts, measurements and disorders, are unified in the same theoretical framework. A numerical verification of our theory and predictions is also provided.

quant-ph↗

arXiv2021

Variable Selection in GLM and Cox Models with Second-Generation P-Values

Variable selection has become a pivotal choice in data analyses that impacts subsequent inference and prediction. In linear models, variable selection using Second-Generation P-Values (SGPV) has been shown to be as good as any other algorithm available to researchers. Here we extend the idea of Penalized Regression with Second-Generation P-Values (ProSGPV) to the generalized linear model (GLM) and Cox regression settings. The proposed ProSGPV extension is largely free of tuning parameters, adaptable to various regularization schemes and null bound specifications, and is computationally fast. Like in the linear case, it excels in support recovery and parameter estimation while maintaining strong prediction performance. The algorithm also preforms as well as its competitors in the high dimensional setting (n>p). Slight modifications of the algorithm improve its performance when data are highly correlated or when signals are dense. This work significantly strengthens the case for the ProSGPV approach to variable selection.

stat.ME↗

arXiv2021

LUAI Challenge 2021 on Learning to Understand Aerial Images

This report summarizes the results of Learning to Understand Aerial Images (LUAI) 2021 challenge held on ICCV 2021, which focuses on object detection and semantic segmentation in aerial images. Using DOTA-v2.0 and GID-15 datasets, this challenge proposes three tasks for oriented object detection, horizontal object detection, and semantic segmentation of common categories in aerial images. This challenge received a total of 146 registrations on the three tasks. Through the challenge, we hope to draw attention from a wide range of communities and call for more efforts on the problems of learning to understand aerial images.

cs.CV↗

arXiv2021

Variable Selection with Second-Generation P-Values

Many statistical methods have been proposed for variable selection in the past century, but few balance inference and prediction tasks well. Here we report on a novel variable selection approach called Penalized regression with Second-Generation P-Values (ProSGPV). It captures the true model at the best rate achieved by current standards, is easy to implement in practice, and often yields the smallest parameter estimation error. The idea is to use an l0 penalization scheme with second-generation p-values (SGPV), instead of traditional ones, to determine which variables remain in a model. The approach yields tangible advantages for balancing support recovery, parameter estimation, and prediction tasks. The ProSGPV algorithm can maintain its good performance even when there is strong collinearity among features or when a high dimensional feature space with p > n is considered. We present extensive simulations and a real-world application comparing the ProSGPV approach with smoothly clipped absolute deviation (SCAD), adaptive lasso (AL), and mini-max concave penalty with penalized linear unbiased selection (MC+). While the last three algorithms are among the current standards for variable selection, ProSGPV has superior inference performance and comparable prediction performance in certain scenarios. Supplementary materials are available online.

stat.ME↗

arXiv2017

Topological surface electronic states in candidate nodal-line semimetal CaAgAs

We investigate systematically the bulk and surface electronic structure of the candidate nodal-line semimetal CaAgAs by angle resolved photoemission spectroscopy and density functional calculations. We observed a metallic, linear, non-$k_z$-dispersive surface band that coincides with the high-binding-energy part of the theoretical topological surface state, proving the topological nontriviality of the system. An overall downshift of the experimental Fermi level points to a rigid-band-like $p$-doping of the samples, due possibly to Ag vacancies in the as-grown crystals.

cond-mat.mtrl-sci↗