arXiv subjects

Rui Yao

Publications and source records attributed to Rui Yao.

At least 37 records · Page 2Linked to original sources

arXiv2025

KnowMT-Bench: Benchmarking Knowledge-Intensive Long-Form Question Answering in Multi-Turn Dialogues

Multi-Turn Long-Form Question Answering (MT-LFQA) is a key application paradigm of Large Language Models (LLMs) in knowledge-intensive domains. However, existing benchmarks are limited to single-turn dialogue, while multi-turn dialogue benchmarks typically assess other orthogonal capabilities rather than knowledge-intensive factuality. To bridge this critical gap, we introduce \textbf{KnowMT-Bench}, the \textit{first-ever} benchmark designed to systematically evaluate MT-LFQA for LLMs across knowledge-intensive fields, including medicine, finance, and law. To faithfully assess the model's real-world performance, KnowMT-Bench employs a dynamic evaluation setting where models generate their own multi-turn dialogue histories given logically progressive question sequences. The factual capability and information delivery efficiency of the \textit{final-turn} answer are then evaluated using a human-validated automated pipeline. Our experiments reveal that multi-turn contexts degrade performance: factual capability declines due to the contextual noise from self-generated histories, while information efficiency drops as models become more verbose with increasing dialogue length. We then investigate mitigation strategies, demonstrating that retrieval-augmented generation (RAG) can effectively alleviate and even reverse this factual degradation. These findings underscore the importance of our benchmark in evaluating and enhancing the conversational factual capabilities of LLMs in real-world knowledge-intensive applications. Code is available at \href{https://github.com/hardenyu21/KnowMT-Bench}{\textcolor{cyan}{\texttt{KnowMT-Bench}}}.

cs.CL↗

arXiv2025

Semi-supervised Image Dehazing via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models

Existing dehazing methods deal with real-world haze images with difficulty, especially scenes with thick haze. One of the main reasons is the lack of real-world paired data and robust priors. To avoid the costly collection of paired hazy and clear images, we propose an efficient semi-supervised image dehazing method via Expectation-Maximization and Bidirectional Brownian Bridge Diffusion Models (EM-B3DM) with a two-stage learning scheme. In the first stage, we employ the EM algorithm to decouple the joint distribution of paired hazy and clear images into two conditional distributions, which are then modeled using a unified Brownian Bridge diffusion model to directly capture the structural and content-related correlations between hazy and clear images. In the second stage, we leverage the pre-trained model and large-scale unpaired hazy and clear images to further improve the performance of image dehazing. Additionally, we introduce a detail-enhanced Residual Difference Convolution block (RDC) to capture gradient-level information, significantly enhancing the model's representation capability. Extensive experiments demonstrate that our EM-B3DM achieves superior or at least comparable performance to state-of-the-art methods on both synthetic and real-world datasets.

cs.CV↗

arXiv2025

Quantifying Grid Resilience Against Extreme Weather Using Large-Scale Customer Power Outage Data

In recent decades, the weather around the world has become more irregular and extreme, often causing large-scale extended power outages. Resilience -- the capability of withstanding, adapting to, and recovering from a large-scale disruption -- has become a top priority for the power sector. However, the understanding of power grid resilience still stays on the conceptual level mostly or focuses on particular components, yielding no actionable results or revealing few insights on the system level. This study provides a quantitatively measurable definition of power grid resilience, using a statistical model inspired by patterns observed from data and domain knowledge. We analyze a large-scale quarter-hourly historical electricity customer outage data and the corresponding weather records, and draw connections between the model and industry resilience practice. We showcase the resilience analysis using three major service territories on the east coast of the United States. Our analysis suggests that cumulative weather effects play a key role in causing immediate, sustained outages, and these outages can propagate and cause secondary outages in neighboring areas. The proposed model also provides some interesting insights into grid resilience enhancement planning. For example, our simulation results indicate that enhancing the power infrastructure in a small number of critical locations can reduce nearly half of the number of customer power outages in Massachusetts. In addition, we have shown that our model achieves promising accuracy in predicting the progress of customer power outages throughout extreme weather events, which can be very valuable for system operators and federal agencies to prepare disaster response.

stat.AP↗

arXiv2025

Integrated equilibrium model for electrified logistics and power systems

This paper proposes an integrated equilibrium model to characterize the complex interactions between electrified logistics systems and electric power delivery systems. The model consists of two major players: an electrified logistics operator (ELO) and a power system operator (PSO). The ELO aims to maximize its profit by strategically scheduling and routing its electric delivery vehicles (e-trucks) for deliveries and charging, in response to the locational marginal price (LMP) set by the PSO. The routing, delivery, and charging behaviors of e-trucks are modeled by a perturbed utility Markov decision process (PU-MDP) while their collective operations are optimized to achieve the ELO's objective by designing rewards in the PU-MDP. On the other hand, PSO optimizes the energy price by considering both the spatiotemporal e-truck charging demand and the base electricity load. The equilibrium of the integrated system is formulated as a fixed point, proved to exist under mild assumptions, and solved for a case study on the Hawaii network via Anderson's fixed-point acceleration algorithm. Along with these numerical results, this paper provides both theoretical insights and practical guidelines to achieve sustainable and efficient operations in modern electrified logistics and power systems.

eess.SY↗

arXiv2025

Modality-Guided Dynamic Graph Fusion and Temporal Diffusion for Self-Supervised RGB-T Tracking

To reduce the reliance on large-scale annotations, self-supervised RGB-T tracking approaches have garnered significant attention. However, the omission of the object region by erroneous pseudo-label or the introduction of background noise affects the efficiency of modality fusion, while pseudo-label noise triggered by similar object noise can further affect the tracking performance. In this paper, we propose GDSTrack, a novel approach that introduces dynamic graph fusion and temporal diffusion to address the above challenges in self-supervised RGB-T tracking. GDSTrack dynamically fuses the modalities of neighboring frames, treats them as distractor noise, and leverages the denoising capability of a generative model. Specifically, by constructing an adjacency matrix via an Adjacency Matrix Generator (AMG), the proposed Modality-guided Dynamic Graph Fusion (MDGF) module uses a dynamic adjacency matrix to guide graph attention, focusing on and fusing the object's coherent regions. Temporal Graph-Informed Diffusion (TGID) models MDGF features from neighboring frames as interference, and thus improving robustness against similar-object noise. Extensive experiments conducted on four public RGB-T tracking datasets demonstrate that GDSTrack outperforms the existing state-of-the-art methods. The source code is available at https://github.com/LiShenglana/GDSTrack.

cs.CV↗

arXiv2025

Fixed Point Computation: Beating Brute Force with Smoothed Analysis

We propose a new algorithm that finds an $\varepsilon$-approximate fixed point of a smooth function from the $n$-dimensional $\ell_2$ unit ball to itself. We use the general framework of finding approximate solutions to a variational inequality, a problem that subsumes fixed point computation and the computation of a Nash Equilibrium. The algorithm's runtime is bounded by $e^{O(n)}/\varepsilon$, under the smoothed-analysis framework. This is the first known algorithm in such a generality whose runtime is faster than $(1/\varepsilon)^{O(n)}$, which is a time that suffices for an exhaustive search. We complement this result with a lower bound of $e^{Ω(n)}$ on the query complexity for finding an $O(1)$-approximate fixed point on the unit ball, which holds even in the smoothed-analysis model, yet without the assumption that the function is smooth. Existing lower bounds are only known for the hypercube, and adapting them to the ball does not give non-trivial results even for finding $O(1/\sqrt{n})$-approximate fixed points.

cs.GT↗

arXiv2024

RQFormer: Rotated Query Transformer for End-to-End Oriented Object Detection

Oriented object detection presents a challenging task due to the presence of object instances with multiple orientations, varying scales, and dense distributions. Recently, end-to-end detectors have made significant strides by employing attention mechanisms and refining a fixed number of queries through consecutive decoder layers. However, existing end-to-end oriented object detectors still face two primary challenges: 1) misalignment between positional queries and keys, leading to inconsistency between classification and localization; and 2) the presence of a large number of similar queries, which complicates one-to-one label assignments and optimization. To address these limitations, we propose an end-to-end oriented detector called the Rotated Query Transformer, which integrates two key technologies: Rotated RoI Attention (RRoI Attention) and Selective Distinct Queries (SDQ). First, RRoI Attention aligns positional queries and keys from oriented regions of interest through cross-attention. Second, SDQ collects queries from intermediate decoder layers and filters out similar ones to generate distinct queries, thereby facilitating the optimization of one-to-one label assignments. Finally, extensive experiments conducted on four remote sensing datasets and one scene text dataset demonstrate the effectiveness of our method. To further validate its generalization capability, we also extend our approach to horizontal object detection The code is available at \url{https://github.com/wokaikaixinxin/RQFormer}.

cs.CV↗

arXiv2024

Facial Action Unit Detection by Adaptively Constraining Self-Attention and Causally Deconfounding Sample

Facial action unit (AU) detection remains a challenging task, due to the subtlety, dynamics, and diversity of AUs. Recently, the prevailing techniques of self-attention and causal inference have been introduced to AU detection. However, most existing methods directly learn self-attention guided by AU detection, or employ common patterns for all AUs during causal intervention. The former often captures irrelevant information in a global range, and the latter ignores the specific causal characteristic of each AU. In this paper, we propose a novel AU detection framework called AC2D by adaptively constraining self-attention weight distribution and causally deconfounding the sample confounder. Specifically, we explore the mechanism of self-attention weight distribution, in which the self-attention weight distribution of each AU is regarded as spatial distribution and is adaptively learned under the constraint of location-predefined attention and the guidance of AU detection. Moreover, we propose a causal intervention module for each AU, in which the bias caused by training samples and the interference from irrelevant AUs are both suppressed. Extensive experiments show that our method achieves competitive performance compared to state-of-the-art AU detection approaches on challenging benchmarks, including BP4D, DISFA, GFT, and BP4D+ in constrained scenarios and Aff-Wild2 in unconstrained scenarios. The code is available at https://github.com/ZhiwenShao/AC2D.

cs.CV↗

arXiv2024

Spatial-Frequency Dual Progressive Attention Network For Medical Image Segmentation

In medical images, various types of lesions often manifest significant differences in their shape and texture. Accurate medical image segmentation demands deep learning models with robust capabilities in multi-scale and boundary feature learning. However, previous networks still have limitations in addressing the above issues. Firstly, previous networks simultaneously fuse multi-level features or employ deep supervision to enhance multi-scale learning. However, this may lead to feature redundancy and excessive computational overhead, which is not conducive to network training and clinical deployment. Secondly, the majority of medical image segmentation networks exclusively learn features in the spatial domain, disregarding the abundant global information in the frequency domain. This results in a bias towards low-frequency components, neglecting crucial high-frequency information. To address these problems, we introduce SF-UNet, a spatial-frequency dual-domain attention network. It comprises two main components: the Multi-scale Progressive Channel Attention (MPCA) block, which progressively extract multi-scale features across adjacent encoder layers, and the lightweight Frequency-Spatial Attention (FSA) block, with only 0.05M parameters, enabling concurrent learning of texture and boundary features from both spatial and frequency domains. We validate the effectiveness of the proposed SF-UNet on three public datasets. Experimental results show that compared to previous state-of-the-art (SOTA) medical image segmentation networks, SF-UNet achieves the best performance, and achieves up to 9.4\% and 10.78\% improvement in DSC and IOU. Codes will be released at https://github.com/nkicsl/SF-UNet.

eess.IV↗

arXiv2024

Deep neural networks for choice analysis: Enhancing behavioral regularity with gradient regularization

Deep neural networks (DNNs) frequently present behaviorally irregular patterns, significantly limiting their practical potentials and theoretical validity in travel behavior modeling. This study proposes strong and weak behavioral regularities as novel metrics to evaluate the monotonicity of individual demand functions (known as the "law of demand"), and further designs a constrained optimization framework with six gradient regularizers to enhance DNNs' behavioral regularity. The proposed framework is applied to travel survey data from Chicago and London to examine the trade-off between predictive power and behavioral regularity for large vs. small sample scenarios and in-domain vs. out-of-domain generalizations. The results demonstrate that, unlike models with strong behavioral foundations such as the multinomial logit, the benchmark DNNs cannot guarantee behavioral regularity. However, gradient regularization (GR) increases DNNs' behavioral regularity by around 6 percentage points (pp) while retaining their relatively high predictive power. In the small sample scenario, GR is more effective than in the large sample scenario, simultaneously improving behavioral regularity by about 20 pp and log-likelihood by around 1.7%. Comparing with the in-domain generalization of DNNs, GR works more effectively in out-of-domain generalization: it drastically improves the behavioral regularity of poorly performing benchmark DNNs by around 65 pp, indicating the criticality of behavioral regularization for enhancing model transferability and application in forecasting. Moreover, the proposed framework is applicable to other NN-based choice models such as TasteNets. Future studies could use behavioral regularity as a metric along with log-likelihood in evaluating travel demand models, and investigate other methods to further enhance behavioral regularity when adopting complex machine learning models.

cs.LG↗

arXiv2023

A Semi-Analytical Approach for State-Space Electromagnetic Transient Simulation Using the Differential Transformation

Electromagnetic transient (EMT) simulation is a crucial tool for power system dynamic analysis because of its detailed component modeling and high simulation accuracy. However, it suffers from computational burdens for large power grids since a tiny time step is typically required for accuracy. This paper proposes an efficient and accurate semi-analytical approach for state-space EMT simulations of power grids. It employs high-order semi-analytical solutions derived using the differential transformation from the state-space EMT grid model. The approach incorporates a proposed variable time step strategy based on equation imbalance, leveraging structural information of the grid model, to enlarge the time step and accelerate simulations, while high resolution is maintained by reconstructing detailed fast EMT dynamics through an efficient dense output mechanism. It also addresses limit-induced switches during large time steps by using a binary search-enhanced quadratic interpolation algorithm. Case studies are conducted on EMT models of the IEEE 39-bus system and a synthetic 390-bus system to demonstrate the merits of the new simulation approach against traditional methods.

eess.SY↗

arXiv2023

A general equilibrium model for multi-passenger ridesharing systems with stable matching

This paper proposes a general equilibrium model for multi-passenger ridesharing systems, in which interactions between ridesharing drivers, passengers, platforms, and transportation networks are endogenously captured. Stable matching is modeled as an equilibrium problem in which no ridesharing driver or passenger can reduce ridesharing disutility by unilaterally switching to another matching sequence. This paper is one of the first studies that explicitly integrates the ridesharing platform multi-passenger matching problem into the model. By integrating matching sequence with hyper-network, ridesharing-passenger transfers are avoided in a multi-passenger ridesharing system. Moreover, the matching stability between the ridesharing drivers and passengers is extended to address the multi-OD multi-passenger case in terms of matching sequence. The paper provides a proof for the existence of the proposed general equilibrium. A sequence-bush algorithm is developed for solving the multi-passenger ridesharing equilibrium problem. This algorithm is capable to handle complex ridesharing constraints implicitly. Results illustrate that the proposed sequence-bush algorithm outperforms general-purpose solver, and provides insights into the equilibrium of the joint stable matching and route choice problem. Numerical experiments indicate that ridesharing trips are typically longer than average trip lengths. Sensitivity analysis suggests that a properly designed ridesharing unit price is necessary to achieve network benefits, and travelers with relatively lower values of time are more likely to participate in ridesharing.

econ.GN↗

arXiv2023

Perturbed utility stochastic traffic assignment

This paper develops a fast algorithm for computing the equilibrium assignment with the perturbed utility route choice (PURC) model. Without compromise, this allows the significant advantages of the PURC model to be used in large-scale applications. We formulate the PURC equilibrium assignment problem as a convex minimization problem and find a closed-form stochastic network loading expression that allows us to formulate the Lagrangian dual of the assignment problem as an unconstrained optimization problem. To solve this dual problem, we formulate a quasi-Newton accelerated gradient descent algorithm (qN-AGD*). Our numerical evidence shows that qN-AGD* clearly outperforms a conventional primal algorithm as well as a plain accelerated gradient descent algorithm. qN-AGD* is fast with a runtime that scales about linearly with the problem size, indicating that solving the perturbed utility assignment problem is feasible also with very large networks.

math.OC↗

arXiv2023

Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision

Vehicle-to-everything (V2X) perception is an innovative technology that enhances vehicle perception accuracy, thereby elevating the security and reliability of autonomous systems. However, existing V2X perception methods focus on static scenes from mainly vehicle-based vision, which is constrained by sensor capabilities and communication loads. To adapt V2X perception models to dynamic scenes, we propose to build V2X perception from road-to-vehicle vision and present Adaptive Road-to-Vehicle Perception (AR2VP) method. In AR2VP,we leverage roadside units to offer stable, wide-range sensing capabilities and serve as communication hubs. AR2VP is devised to tackle both intra-scene and inter-scene changes. For the former, we construct a dynamic perception representing module, which efficiently integrates vehicle perceptions, enabling vehicles to capture a more comprehensive range of dynamic factors within the scene.Moreover, we introduce a road-to-vehicle perception compensating module, aimed at preserving the maximized roadside unit perception information in the presence of intra-scene changes.For inter-scene changes, we implement an experience replay mechanism leveraging the roadside unit's storage capacity to retain a subset of historical scene data, maintaining model robustness in response to inter-scene shifts. We conduct perception experiment on 3D object detection and segmentation, and the results show that AR2VP excels in both performance-bandwidth trade-offs and adaptability within dynamic environments.

cs.CV↗

arXiv2023

How would mobility-as-a-service (MaaS) platform survive as an intermediary? From the viewpoint of stability in many-to-many matching

Mobility-as-a-service (MaaS) provides seamless door-to-door trips by integrating different transport modes. Although many MaaS platforms have emerged in recent years, most of them remain at a limited integration level. This study investigates the assignment and pricing problem for a MaaS platform as an intermediary in a multi-modal transportation network, which purchases capacity from service operators and sells multi-modal trips to travelers. The analysis framework of many-to-many stable matching is adopted to decompose the joint design problem and to derive the stability condition such that both operators and travelers are willing to participate in the MaaS system. To maximize the flexibility in route choice and remove boundaries between modes, we design an origin-destination pricing scheme for MaaS trips. On the supply side, we propose a wholesale purchase price for service capacity. Accordingly, the assignment problem is reformulated and solved as a bi-level program, where MaaS travelers make multi-modal trips to minimize their travel costs meanwhile interacting with non-MaaS travelers in the multi-modal transport system. We prove that, under the proposed pricing scheme, there always exists a stable outcome to the overall many-to-many matching problem. Further, given an optimal assignment and under some mild conditions, a unique optimal pricing scheme is ensured. Numerical experiments conducted on the extended Sioux Falls network also demonstrate that the proposed MaaS system could create a win-win-win situation -- the MaaS platform is profitable and both traveler welfare and transit operator revenues increase from a baseline scenario without MaaS.

econ.GN↗

arXiv2023

Spatio-Temporal Wildfire Prediction using Multi-Modal Data

Due to severe societal and environmental impacts, wildfire prediction using multi-modal sensing data has become a highly sought-after data-analytical tool by various stakeholders (such as state governments and power utility companies) to achieve a more informed understanding of wildfire activities and plan preventive measures. A desirable algorithm should precisely predict fire risk and magnitude for a location in real time. In this paper, we develop a flexible spatio-temporal wildfire prediction framework using multi-modal time series data. We first predict the wildfire risk (the chance of a wildfire event) in real-time, considering the historical events using discrete mutually exciting point process models. Then we further develop a wildfire magnitude prediction set method based on the flexible distribution-free time-series conformal prediction (CP) approach. Theoretically, we prove a risk model parameter recovery guarantee, as well as coverage and set size guarantees for the CP sets. Through extensive real-data experiments with wildfire data in California, we demonstrate the effectiveness of our methods, as well as their flexibility and scalability in large regions.

stat.AP↗

arXiv2023

CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer

Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate frontend contour initialization, multi-stage error accumulation, or deficient local information aggregation. To tackle these limitations, we propose a novel arbitrary-shaped scene text detection framework named CT-Net by progressive contour regression with contour transformers. Specifically, we first employ a contour initialization module that generates coarse text contours without any post-processing. Then, we adopt contour refinement modules to adaptively refine text contours in an iterative manner, which are beneficial for context information capturing and progressive global contour deformation. Besides, we propose an adaptive training strategy to enable the contour transformers to learn more potential deformation paths, and introduce a re-score mechanism that can effectively suppress false positives. Extensive experiments are conducted on four challenging datasets, which demonstrate the accuracy and efficiency of our CT-Net over state-of-the-art methods. Particularly, CT-Net achieves F-measure of 86.1 at 11.2 frames per second (FPS) and F-measure of 87.8 at 10.1 FPS for CTW1500 and Total-Text datasets, respectively.

cs.CV↗

arXiv2023

Facial Action Unit Detection via Adaptive Attention and Relation

Facial action unit (AU) detection is challenging due to the difficulty in capturing correlated information from subtle and dynamic AUs. Existing methods often resort to the localization of correlated regions of AUs, in which predefining local AU attentions by correlated facial landmarks often discards essential parts, or learning global attention maps often contains irrelevant areas. Furthermore, existing relational reasoning methods often employ common patterns for all AUs while ignoring the specific way of each AU. To tackle these limitations, we propose a novel adaptive attention and relation (AAR) framework for facial AU detection. Specifically, we propose an adaptive attention regression network to regress the global attention map of each AU under the constraint of attention predefinition and the guidance of AU detection, which is beneficial for capturing both specified dependencies by landmarks in strongly correlated regions and facial globally distributed dependencies in weakly correlated regions. Moreover, considering the diversity and dynamics of AUs, we propose an adaptive spatio-temporal graph convolutional network to simultaneously reason the independent pattern of each AU, the inter-dependencies among AUs, as well as the temporal dependencies. Extensive experiments show that our approach (i) achieves competitive performance on challenging benchmarks including BP4D, DISFA, and GFT in constrained scenarios and Aff-Wild2 in unconstrained scenarios, and (ii) can precisely learn the regional correlation distribution of each AU.

cs.CV↗