arXiv subjects

Yonggang Wu

Publications and source records attributed to Yonggang Wu.

4 recordsLinked to original sources

arXiv2026

Orbia: Do Generated Videos Form a Consistent 3D World?

Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluation underexplored. We introduce Orbia, the first benchmark dedicated to a systematic and comprehensive evaluation of 3D consistency in interactive world models. Through controlled exploration and revisit, we organize the evaluation into three dimensions: input preservation, generated-content persistence, and 3D self-consistency. For input preservation, registered RGB-D references and annotated anchors support appearance, geometry, and spatial stability measurements. For generated-content persistence, we compare revisits to regions absent from the input image with their first generated observations to test whether models preserve what they create. For 3D self-consistency, cross-view depth and feature correspondence, regional scale agreement, and held-out Gaussian rendering test whether generated views describe the same 3D scene. Minute-long exploration and revisits further test long-term consistency. Our construction and annotation pipeline brings together public datasets, self-captured scenes, and simulation, yielding 720 instances across indoor and outdoor environments and six exploration-and-revisit protocols. Evaluation spans 27 text-, action-, and camera-conditioned models through native-interface adapters. Our Orbia benchmark provides a systematic basis for diagnosing 3D inconsistency and developing more persistent video world models.

cs.CV↗

arXiv2026

CausalCompass: Evaluating the Robustness of Time-Series Causal Discovery in Misspecified Scenarios

Causal discovery from time series is a fundamental task in machine learning. However, its widespread adoption is hindered by a reliance on untestable causal assumptions and by the lack of robustness-oriented evaluation in existing benchmarks. To address these challenges, we propose CausalCompass, a flexible and extensible benchmark framework designed to assess the robustness of time-series causal discovery (TSCD) methods under violations of modeling assumptions. To demonstrate the practical utility of CausalCompass, we conduct extensive benchmarking of representative TSCD algorithms across eight assumption-violation scenarios. Our experimental results indicate that no single method consistently attains optimal performance across all settings. Nevertheless, the methods exhibiting superior overall performance across diverse scenarios are almost invariably deep learning-based approaches. We further provide hyperparameter sensitivity analyses to deepen the understanding of these findings. We additionally conduct ablation experiments to explain the strong performance of deep learning-based methods under assumption violations. We also find, somewhat surprisingly, that NTS-NOTEARS relies heavily on standardized preprocessing in practice, performing poorly in the vanilla setting but exhibiting strong performance after standardization. Finally, our work aims to provide a comprehensive and systematic evaluation of TSCD methods under assumption violations, thereby facilitating their broader adoption in real-world applications. The user-friendly implementation, documentation and datasets are available at https://anonymous.4open.science/r/CausalCompass-anonymous-5B4F/.

cs.LG↗

arXiv2026

TFWaveFormer: Temporal-Frequency Collaborative Multi-level Wavelet Transformer for Dynamic Link Prediction

Dynamic link prediction plays a crucial role in diverse applications including social network analysis, communication forecasting, and financial modeling. While recent Transformer-based approaches have demonstrated promising results in temporal graph learning, their performance remains limited when capturing complex multi-scale temporal dynamics. In this paper, we propose TFWaveFormer, a novel Transformer architecture that integrates temporal-frequency analysis with multi-resolution wavelet decomposition to enhance dynamic link prediction. Our framework comprises three key components: (i) a temporal-frequency coordination mechanism that jointly models temporal and spectral representations, (ii) a learnable multi-resolution wavelet decomposition module that adaptively extracts multi-scale temporal patterns through parallel convolutions, replacing traditional iterative wavelet transforms, and (iii) a hybrid Transformer module that effectively fuses local wavelet features with global temporal dependencies. Extensive experiments on benchmark datasets demonstrate that TFWaveFormer achieves state-of-the-art performance, outperforming existing Transformer-based and hybrid models by significant margins across multiple metrics. The superior performance of TFWaveFormer validates the effectiveness of combining temporal-frequency analysis with wavelet decomposition in capturing complex temporal dynamics for dynamic link prediction tasks.

cs.LG↗

arXiv2015

Generalized Cramer-Rao Bound for Joint Estimation of Target Position and Velocity for Active and Passive Radar Networks

In this paper, we derive the Cramer-Rao bound (CRB) for joint target position and velocity estimation using an active or passive distributed radar network under more general, and practically occurring, conditions than assumed in previous work. In particular, the presented results allow nonorthogonal signals, spatially dependent Gaussian reflection coefficients, and spatially dependent Gaussian clutter-plus-noise. These bounds allow designers to compare the performance of their developed approaches, which are deemed to be of acceptable complexity, to the best achievable performance. If their developed approaches lead to performance close to the bounds, these developed approaches can be deemed "good enough". A particular recent study where algorithms have been developed for a practical radar application which must involve nonorthogonal signals, for which the best performance is unknown, is a great example. The presented results in our paper do not make any assumptions about the approximate location of the target being known from previous target detection signal processing. In addition, for situations in which we do not know some parameters accurately, we also derive the mismatched CRB. Numerical investigations of the mean squared error of the maximum likelihood estimation are employed to support the validity of the CRBs. In order to demonstrate the utility of the provided results to a topic of great current interest, the numerical results focus on a passive radar system using the Global System for Mobile communication (GSM) cellar system.

math.ST↗