arXiv subjects

Yahui Wang

Publications and source records attributed to Yahui Wang.

16 recordsLinked to original sources

arXiv2026

The Second LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

This paper presents a review of the second LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aims to advance unified image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provides a common benchmark for evaluating the restoration accuracy, robustness, and generalization capability of models across multiple degradation categories within a unified framework. The competition attracted 158 registered participants, and 20 teams were included in the final ranking after their submitted results were successfully reproduced and verified. This report provides a comprehensive analysis of the submitted solutions and corresponding results, highlighting recent advances in real-world all-in-one image restoration. The summarized methods and empirical findings reveal effective design strategies and establish an updated benchmark for future research in real-world low-level vision.

cs.CV↗

arXiv2026

LoViF 2026 Challenge on Real-World All-in-One Image Restoration: Methods and Results

This paper presents a review for the LoViF Challenge on Real-World All-in-One Image Restoration. The challenge aimed to advance research on real-world all-in-one image restoration under diverse real-world degradation conditions, including blur, low-light, haze, rain, and snow. It provided a unified benchmark to evaluate the robustness and generalization ability of restoration models across multiple degradation categories within a common framework. The competition attracted 124 registered participants and received 9 valid final submissions with corresponding fact sheets, significantly contributing to the progress of real-world all-in-one image restoration. This report provides a detailed analysis of the submitted methods and corresponding results, emphasizing recent progress in unified real-world image restoration. The analysis highlights effective approaches and establishes a benchmark for future research in real-world low-level vision.

cs.CV↗

arXiv2026

NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results

This paper reports on the NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration (BSCVR). The challenge aims to advance research on recovering visually coherent videos from corrupted bitstreams, whose decoding often produces severe spatial-temporal artifacts and content distortion. Built upon recent progress in bitstream-corrupted video recovery, the challenge provides a common benchmark for evaluating restoration methods under realistic corruption settings. We describe the dataset, evaluation protocol, and participating methods, and summarize the final results and main technical trends. The challenge highlights the difficulty of this emerging task and provides useful insights for future research on robust video restoration under practical bitstream corruption.

cs.CV↗

arXiv2026

LoViF 2026 The First Challenge on Weather Removal in Videos

This paper presents a review of the LoViF 2026 Challenge on Weather Removal in Videos. The challenge encourages the development of methods for restoring clean videos from inputs degraded by adverse weather conditions such as rain and snow, with an emphasis on achieving visually plausible and temporally consistent results while preserving scene structure and motion dynamics. To support this task, we introduce a new short-form WRV dataset tailored for video weather removal. It consists of 18 videos 1,216 synthesized frames paired with 1,216 real-world ground-truth frames at a resolution of 832 x 480, and is split into training, validation, and test sets with a ratio of 1:1:1. The goal of this challenge is to advance robust and realistic video restoration under real-world weather conditions, with evaluation protocols that jointly consider fidelity and perceptual quality. The challenge attracted 37 participants and received 5 valid final submissions with corresponding fact sheets, contributing to progress in weather removal for videos. The project is publicly available at https://www.codabench.org/competitions/13462/.

cs.CV↗

arXiv2026

NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

cs.CV↗

arXiv2025

Spectral Analysis of Hard-Constraint PINNs: The Spatial Modulation Mechanism of Boundary Functions

Physics-Informed Neural Networks with hard constraints (HC-PINNs) are increasingly favored for their ability to strictly enforce boundary conditions via a trial function ansatz $\tilde{u} = A + B \cdot N$, yet the theoretical mechanisms governing their training dynamics have remained unexplored. Unlike soft-constrained formulations where boundary terms act as additive penalties, this work reveals that the boundary function $B$ introduces a multiplicative spatial modulation that fundamentally alters the learning landscape. A rigorous Neural Tangent Kernel (NTK) framework for HC-PINNs is established, deriving the explicit kernel composition law. This relationship demonstrates that the boundary function $B(\vec{x})$ functions as a spectral filter, reshaping the eigenspectrum of the neural network's native kernel. Through spectral analysis, the effective rank of the residual kernel is identified as a deterministic predictor of training convergence, superior to classical condition numbers. It is shown that widely used boundary functions can inadvertently induce spectral collapse, leading to optimization stagnation despite exact boundary satisfaction. Validated across multi-dimensional benchmarks, this framework transforms the design of boundary functions from a heuristic choice into a principled spectral optimization problem, providing a solid theoretical foundation for geometric hard constraints in scientific machine learning.

cs.LG↗

arXiv2025

Properly discontinuous actions, growth indicators, and conformal measures for transverse subgroups

Let $G$ be a connected semisimple real algebraic group. The class of transverse subgroups of $G$ includes all discrete subgroups of rank one Lie groups and any subgroups of Anosov or relative Anosov subgroups. Given a transverse subgroup $Γ$, we show that the $Γ$-action on the Weyl chamber flow space determined by its limit set is properly discontinuous. This allows us to consider the quotient space and define Bowen-Margulis-Sullivan measures. We then establish the ergodic dichotomy for the Weyl chamber flow, in the original spirit of Hopf-Tsuji-Sullivan. We also introduce the notion of growth indicators and discuss their properties and roles in the study of conformal measures, extending the work of Quint. We discuss several applications as well.

math.DS↗

arXiv2025

MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation

Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding, but structured understanding of medical reports remains insufficiently benchmarked. Therefore, we introduce MedRepBench, a benchmark with 1,925 de-identified Chinese medical report images spanning diverse departments, patient demographics, and acquisition formats. In MedRepBench, we mainly focus on report-grounded interpretation rather than evaluating diagnostic reasoning, treatment recommendation, or the integration of patient history. The interpretation is defined as structured extraction of report fields (e.g., item, value, unit, reference range, abnormal flag) plus a patient-facing explanation grounded strictly in the report content. The benchmark primarily evaluates end-to-end VLMs, and also includes a controlled text-only setting (high-quality OCR + LLM) to approximate an upper bound when character recognition errors are minimized. Our evaluation framework provides two complementary protocols: (1) an objective protocol measuring field-level recall of structured items, and (2) an automated subjective protocol that uses an LLM-based judge to score factuality, interpretability, and reasoning quality under a fixed prompt. Using the objective metric as a reward signal, we also provide a lightweight GRPO-based alignment baseline for a mid-sized VLM, which improves field-level recall by up to 6%. Finally, we analyze practical limitations of OCR+LLM pipelines, including layout-related errors and additional system latency, showing the need for robust end-to-end vision-based medical report understanding. The dataset and evaluation resources are publicly available on https://huggingface.co/datasets/MedRepBench/MedRepBench.

cs.CV↗

arXiv2025

Ergodic dichotomy for subspace flows in higher rank

In this paper, we study the ergodicity of a one-parameter diagonalizable subgroup of a connected semisimple real algebraic group $G$ acting on a homogeneous space or, more generally, a homogeneous-like space, equipped with a Bowen-Margulis-Sullivan type measure. These flow spaces are associated with Anosov subgroups of $G$, or more generally, with transverse subgroups of $G$. We obtain an ergodicity criterion similar to the Hopf-Tsuji-Sullivan dichotomy for the ergodicity of the geodesic flow on hyperbolic manifolds. In addition, we extend this criterion to the action of any connected diagonal subgroup of arbitrary dimension. Our criterion provides a codimension dichotomy on the ergodicity of a connected diagonalizable subgroup for general Anosov subgroups. This generalizes an earlier work by Burger-Landesberg-Lee-Oh for Borel Anosov subgroups.

math.DS↗

arXiv2023

GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection

Along with the rapid evolution of mobile communication technologies, such as 5G, there has been a drastically increase in telecom fraud, which significantly dissipates individual fortune and social wealth. In recent years, graph mining techniques are gradually becoming a mainstream solution for detecting telecom fraud. However, the graph imbalance problem, caused by the Pareto principle, brings severe challenges to graph data mining. This is a new and challenging problem, but little previous work has been noticed. In this paper, we propose a Graph ATtention network with COst-sensitive BOosting (GAT-COBO) for the graph imbalance problem. First, we design a GAT-based base classifier to learn the embeddings of all nodes in the graph. Then, we feed the embeddings into a well-designed cost-sensitive learner for imbalanced learning. Next, we update the weights according to the misclassification cost to make the model focus more on the minority class. Finally, we sum the node embeddings obtained by multiple cost-sensitive learners to obtain a comprehensive node representation, which is used for the downstream anomaly detection task. Extensive experiments on two real-world telecom fraud detection datasets demonstrate that our proposed method is effective for the graph imbalance problem, outperforming the state-of-the-art GNNs and GNN-based fraud detectors. In addition, our model is also helpful for solving the widespread over-smoothing problem in GNNs. The GAT-COBO code and datasets are available at https://github.com/xxhu94/GAT-COBO.

cs.LG↗

arXiv2023

Cost Sensitive GNN-based Imbalanced Learning for Mobile Social Network Fraud Detection

With the rapid development of mobile networks, the people's social contacts have been considerably facilitated. However, the rise of mobile social network fraud upon those networks, has caused a great deal of distress, in case of depleting personal and social wealth, then potentially doing significant economic harm. To detect fraudulent users, call detail record (CDR) data, which portrays the social behavior of users in mobile networks, has been widely utilized. But the imbalance problem in the aforementioned data, which could severely hinder the effectiveness of fraud detectors based on graph neural networks(GNN), has hardly been addressed in previous work. In this paper, we are going to present a novel Cost-Sensitive Graph Neural Network (CSGNN) by creatively combining cost-sensitive learning and graph neural networks. We conduct extensive experiments on two open-source realworld mobile network fraud datasets. The results show that CSGNN can effectively solve the graph imbalance problem and then achieve better detection performance than the state-of-the-art algorithms. We believe that our research can be applied to solve the graph imbalance problems in other fields. The CSGNN code and datasets are publicly available at https://github.com/xxhu94/CSGNN.

cs.SI↗

arXiv2021

Nonlinear coupling of reversed shear Alfven eigenmode and toroidal Alfven eigenmode during current ramp

Two novel nonlinear mode coupling processes for reversed shear Alfven eigenmode (RSAE) nonlinear saturation are proposed and investigated. In the first process, RSAE nonlinearly couples to a co-propagating toroidal Alfven eigenmode (TAE) with the same toroidal and poloidal mode numbers, and generates a geodesic acoustic mode (GAM). In the second process, RSAE couples to a counter-propagating TAE and generates an ion acoustic wave quasi-mode (IAW). The condition for the two processes to occur is favored during current ramp. Both processes contribute to effectively saturate the Alfvenic instabilities, as well as nonlinearly transfer of energy from energetic fusion alpha particles to fuel ions in burning plasmas.

physics.plasm-ph↗

arXiv2020

StreamNet: A DAG System with Streaming Graph Computing

To achieve high throughput in the POW based blockchain systems, researchers proposed a series of methods, and DAG is one of the most active and promising fields. We designed and implemented the StreamNet, aiming to engineer a scalable and endurable DAG system. When attaching a new block in the DAG, only two tips are selected. One is the parent tip whose definition is the same as in Conflux[1]; another is using Markov Chain Monte Carlo (MCMC) technique by which the definition is the same as IOTA [2]. We infer a pivotal chain along the path of each epoch in the graph, and a total order of the graph could be calculated without a centralized authority. To scale up, we leveraged the graph streaming property; high transaction validation speed will be achieved even if the DAG is growing. To scale out, we designed the direct signal gossip protocol to help disseminate block updates in the network, such that messages can be passed in the network more efficiently. We implemented our system based on IOTA's reference code (IRI) and ran comprehensive experiments over the different sizes of clusters of multiple network topologies.

cs.DC↗

arXiv2019

CubemapSLAM: A Piecewise-Pinhole Monocular Fisheye SLAM System

We present a real-time feature-based SLAM (Simultaneous Localization and Mapping) system for fisheye cameras featured by a large field-of-view (FoV). Large FoV cameras are beneficial for large-scale outdoor SLAM applications, because they increase visual overlap between consecutive frames and capture more pixels belonging to the static parts of the environment. However, current feature-based SLAM systems such as PTAM and ORB-SLAM limit their camera model to pinhole only. To compensate for the vacancy, we propose a novel SLAM system with the cubemap model that utilizes the full FoV without introducing distortion from the fisheye lens, which greatly benefits the feature matching pipeline. In the initialization and point triangulation stages, we adopt a unified vector-based representation to efficiently handle matches across multiple faces, and based on this representation we propose and analyze a novel inlier checking metric. In the optimization stage, we design and test a novel multi-pinhole reprojection error metric that outperforms other metrics by a large margin. We evaluate our system comprehensively on a public dataset as well as a self-collected dataset that contains real-world challenging sequences. The results suggest that our system is more robust and accurate than other feature-based fisheye SLAM approaches. The CubemapSLAM system has been released into the public domain.

cs.RO↗

arXiv2018

A High-Order Modified Finite Volume WENO Method on 3D Cartesian Grids

The modified dimension-by-dimension finite volume (FV) WENO method on Cartesian grids proposed by Buchm\"{u}ller and Helzel can retain the full order of accuracy of the one-dimensional WENO reconstruction and requires only one flux computation per interface. The high-order accurate conversion between face-averaged values and face-center point values is the main ingredient of this method. In this paper, we derive sixth-order accurate conversion formulas on three-dimensional Cartesian grids. It is shown that the resulting modified FV WENO method is efficient and high-order accurate when applied to smooth nonlinear multidimensional problems, and is robust for calculating non-smooth nonlinear problems with strong shocks..

math.NA↗

arXiv2017

Chaotic Brillouin Optical Correlation Domain Analysis

We propose and experimentally demonstrate a chaotic Brillouin optical correlation-domain analysis (BOCDA) system for distributed fiber sensing. The utilization of the chaotic laser with low coherent state ensures high spatial resolution. The experimental results demonstrate a 3.92-cm spatial resolution over a 906-m measurement range. The uncertainty in the measurement of the local Brillouin frequency shift is 1.2MHz. The measurement signal-to-noise ratio is given, which is agreement with the theoretical value.

physics.ins-det↗