Remote Sensing Image Dehazing (RSID) poses significant challenges in real-world scenarios due to the complex atmospheric conditions and severe color distortions that degrade image quality. The scarcity of real-world remote sensing hazy image pairs has compelled existing methods to rely primarily on synthetic datasets. However, these methods struggle with real-world applications due to the inherent domain gap between synthetic and real data. To address this, we introduce Real-World Remote Sensing Hazy Image Dataset (RRSHID), the first large-scale dataset featuring real-world hazy and dehazed image pairs across diverse atmospheric conditions. Based on this, we propose MCAF-Net, a novel framework tailored for real-world RSID. Its effectiveness arises from three innovative components: Multi-branch Feature Integration Block Aggregator (MFIBA), which enables robust feature extraction through cascaded integration blocks and parallel multi-branch processing; Color-Calibrated Self-Supervised Attention Module (CSAM), which mitigates complex color distortions via self-supervised learning and attention-guided refinement; and Multi-Scale Feature Adaptive Fusion Module (MFAFM), which integrates
Text-to-image diffusion model since its propose has significantly influenced the content creation due to its impressive generation capability. However, this capability depends on large-scale text-image datasets gathered from web platforms like social media, posing substantial challenges in copyright compliance and personal privacy leakage. Though there are some efforts devoted to explore approaches for auditing data provenance in text-to-image diffusion models, existing work has unrealistic assumptions that can obtain model internal knowledge, e.g., intermediate results, or the evaluation is not reliable. To fill this gap, we propose a completely black-box auditing framework called Feature Semantic Consistency-based Auditing (FSCA). It utilizes two types of semantic connections within the text-to-image diffusion model for auditing, eliminating the need for access to internal knowledge. To demonstrate the effectiveness of our FSCA framework, we perform extensive experiments on LAION-mi dataset and COCO dataset, and compare with eight state-of-the-art baseline approaches. The results show that FSCA surpasses previous baseline approaches across various metrics and different data distr
Bridging the sim-to-real gap is a core challenge in deploying learned manipulation policies. Sim-to-real learning is attractive because it can replace expensive real robot demonstrations with scalable synthetic data, yet world-action models have not previously been shown to transfer from simulation to real robotic manipulation. We study whether a world-action model can be trained from synthetic priors and deployed zero-shot in the real world. To this end, we build upon Cosmos Policy, a video diffusion model adapted for visuomotor control. We construct simulation environments with extensive domain randomization and generate demonstrations using the AnyTask motion planning pipeline. We evaluate our approach across object lifting, drawer opening, and pick-and-place tasks using ${\sim}800$ synthetic demonstrations per task and no real demonstrations. When deployed zero-shot on a Franka Robot, our policy attains a 35\% average success rate. To our knowledge, this represents the first successful sim-to-real transfer of a world-action model for robotic manipulation.
Background: Advances in the theory and methods of computational oncology have enabled accurate characterization and prediction of tumor growth and treatment response on a patient-specific basis. This capability can be integrated into a digital twin framework in which bi-directional data-flow between the physical tumor and the digital tumor facilitate dynamic model re-calibration, uncertainty quantification, and clinical decision-support via recommendation of optimal therapeutic interventions. However, many digital twin frameworks rely on bespoke implementations tailored to each disease site, modeling choice, and algorithmic implementation. Findings: We present TumorTwin, a modular software framework for initializing, updating, and leveraging patient-specific cancer tumor digital twins. TumorTwin is publicly available as a Python package, with associated documentation, datasets, and tutorials. Novel contributions include the development of a patient-data structure adaptable to different disease sites, a modular architecture to enable the composition of different data, model, solver, and optimization objects, and CPU- or GPU-parallelized implementations of forward model solves and gr
Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience. However, current ORL benchmarks are almost entirely in simulation and utilize contrived datasets like replay buffers of online RL agents or sub-optimal trajectories, and thus hold limited relevance for real-world robotics. In this work (Real-ORL), we posit that data collected from safe operations of closely related tasks are more practical data sources for real-world robot learning. Under these settings, we perform an extensive (6500+ trajectories collected over 800+ robot hours and 270+ human labor hour) empirical study evaluating generalization and transfer capabilities of representative ORL methods on four real-world tabletop manipulation tasks. Our study finds that ORL and imitation learning prefer different action spaces, and that ORL algorithms can generalize from leveraging offline heterogeneous data sources and outperform imitation learning. We release our dataset and implementations at URL: https://sites.google.com/view/real-orl
In the dynamic landscape of digital forensics, the integration of Artificial Intelligence (AI) and Machine Learning (ML) stands as a transformative technology, poised to amplify the efficiency and precision of digital forensics investigations. However, the use of ML and AI in digital forensics is still in its nascent stages. As a result, this paper gives a thorough and in-depth analysis that goes beyond a simple survey and review. The goal is to look closely at how AI and ML techniques are used in digital forensics and incident response. This research explores cutting-edge research initiatives that cross domains such as data collection and recovery, the intricate reconstruction of cybercrime timelines, robust big data analysis, pattern recognition, safeguarding the chain of custody, and orchestrating responsive strategies to hacking incidents. This endeavour digs far beneath the surface to unearth the intricate ways AI-driven methodologies are shaping these crucial facets of digital forensics practice. While the promise of AI in digital forensics is evident, the challenges arising from increasing database sizes and evolving criminal tactics necessitate ongoing collaborative researc
This paper proposes a system for the ingestion and analysis of real-time sensor and actor data of bulk materials handling plants and machinery. It references issues that concern mining sensor data in cyber physical systems (CPS). The advance of cyber physical systems has created a significant change in the architecture of sensor and actor data. It affects the complexity of the observed systems in general, the number of signals being processed, the spatial distribution of the signal sources on a machine or plant and the global availability of the data. There are different definitions for what constitutes cyber physical systems: the most succinct and pertinent to the work shown in this paper is the definition given by the IEEE: A CPS is a system with a coupling of the cyber aspects of computing and communications with the physical aspects of dynamics and engineering that must abide by the laws of physics. This includes sensor networks, real-time and hybrid systems. Results computed from sensor and actor data must obey the equations used for modelling the physics of the observed system - this fundamentally poses an inverse problem. Such problems are not covered sufficiently by literat
This article presents a vision where \textit{real-time} digital twins of the physical wireless environments are continuously updated using multi-modal sensing data from the distributed infrastructure and user devices, and are used to make communication and sensing decisions. This vision is mainly enabled by the advances in precise 3D maps, multi-modal sensing, ray-tracing computations, and machine/deep learning. This article details this vision, explains the different approaches for constructing and utilizing these real-time digital twins, discusses the applications and open problems, and presents a research platform that can be used to investigate various digital twin research directions.
What if a world simulation model could render not an imagined environment but a city that actually exists? Prior generative world models synthesize visually plausible yet artificial environments by imagining all content. We present Seoul World Model (SWM), a city-scale world model grounded in the real city of Seoul. SWM anchors autoregressive video generation through retrieval-augmented conditioning on nearby street-view images. However, this design introduces several challenges, including temporal misalignment between retrieved references and the dynamic target scene, limited trajectory diversity and data sparsity from vehicle-mounted captures at sparse intervals. We address these challenges through cross-temporal pairing, a large-scale synthetic dataset enabling diverse camera trajectories, and a view interpolation pipeline that synthesizes coherent training videos from sparse street-view images. We further introduce a Virtual Lookahead Sink to stabilize long-horizon generation by continuously re-grounding each chunk to a retrieved image at a future location. We evaluate SWM against recent video world models across three cities: Seoul, Busan, and Ann Arbor. SWM outperforms existi
The capability of video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. However, applying the VSR model to real-world video with unknown and complex degradation remains a challenging task. First, existing degradation metrics in most VSR methods are not able to effectively simulate real-world noise and blur. On the contrary, simple combinations of classical degradation are used for real-world noise modeling, which led to the VSR model often being violated by out-of-distribution noise. Second, many SR models focus on noise simulation and transfer. Nevertheless, the sampled noise is monotonous and limited. To address the aforementioned problems, we propose a Negatives augmentation strategy for generalized noise modeling in Video Super-Resolution (NegVSR) task. Specifically, we first propose sequential noise generation toward real-world data to extract practical noise sequences. Then, the degeneration domain is widely expanded by negative augmentation to build up various yet challenging real-world noise sets. We further propose the augmented negative guidance loss to learn robust features among augmented negatives
Digital agents require diverse, large-scale UI trajectories to generalize across real-world tasks, yet collecting such data is prohibitively expensive in both human annotation, infra and engineering perspectives. To this end, we introduce $\textbf{UI-Simulator}$, a scalable paradigm that generates structured UI states and transitions to synthesize training trajectories at scale. Our paradigm integrates a digital world simulator for diverse UI states, a guided rollout process for coherent exploration, and a trajectory wrapper that produces high-quality and diverse trajectories for agent training. We further propose $\textbf{UI-Simulator-Grow}$, a targeted scaling strategy that enables more rapid and data-efficient scaling by prioritizing high-impact tasks and synthesizes informative trajectory variants. Experiments on WebArena and AndroidWorld show that UI-Simulator rivals or surpasses open-source agents trained on real UIs with significantly better robustness, despite using weaker teacher models. Moreover, UI-Simulator-Grow matches the performance of Llama-3-70B-Instruct using only Llama-3-8B-Instruct as the base model, highlighting the potential of targeted synthesis scaling parad
Cybercrime and the market for cyber-related compromises are becoming attractive revenue sources for state-sponsored actors, cybercriminals and technical individuals affected by financial hardships. Due to burgeoning cybercrime on new technological frontiers, efforts have been made to assist digital forensic investigators (DFI) and law enforcement agencies (LEA) in their investigative efforts. Forensic tool innovations and ontology developments, such as the Unified Cyber Ontology (UCO) and Cyber-investigation Analysis Standard Expression (CASE), have been proposed to assist DFI and LEA. Although these tools and ontologies are useful, they lack extensive information sharing and tool interoperability features, and the ontologies lack the latest Smart City Infrastructure (SCI) context that was proposed. To mitigate the weaknesses in both solutions and to ensure a safer cyber-physical environment for all, we propose the Smart City Ontological Paradigm Expression (SCOPE), an expansion profile of the UCO and CASE ontology that implements SCI threat models, SCI digital forensic evidence, attack techniques, patterns and classifications from MITRE. We showcase how SCOPE could present complex
Artificial Intelligence (AI) and Large Language Models (LLMs) hold significant promise in revolutionizing healthcare, especially in clinical applications. Simultaneously, Digital Twin technology, which models and simulates complex systems, has gained traction in enhancing patient care. However, despite the advances in experimental clinical settings, the potential of AI and digital twins to streamline clinical operations remains largely untapped. This paper introduces a novel digital twin framework specifically designed to enhance oncology clinical operations. We propose the integration of multiple specialized digital twins, such as the Medical Necessity Twin, Care Navigator Twin, and Clinical History Twin, to enhance workflow efficiency and personalize care for each patient based on their unique data. Furthermore, by synthesizing multiple data sources and aligning them with the National Comprehensive Cancer Network (NCCN) guidelines, we create a dynamic Cancer Care Path, a continuously evolving knowledge base that enables these digital twins to provide precise, tailored clinical recommendations.
Multiple studies in the past have analyzed the role and dynamics of the Twitter social network during real world events. However, little work has explored the content of other social media services, or compared content across two networks during real world events. We believe that social media platforms like Facebook also play a vital role in disseminating information on the Internet during real world events. In this work, we study and characterize the content posted on the world's biggest social network, Facebook, and present a comparative analysis of Facebook and Twitter content posted during 16 real world events. Contrary to existing notion that Facebook is used mostly as a private network, our findings reveal that more than 30% of public content that was present on Facebook during these events, was also present on Twitter. We then performed qualitative analysis on the content spread by the most active users during these events, and found that over 10% of the most active users on both networks post spam content. We used stylometric features from Facebook posts and tweet text to classify this spam content, and were able to achieve an accuracy of over 99% for Facebook, and over 98%
In the social sciences, researchers search for information on the Web, but this is most often distributed on different websites, search portals, digital libraries, data archives, and databases. In this work, we present an integrated search system for social science information that allows finding information around research data in a single digital library. Users can search for research data sets, publications, survey variables, questions from questionnaires, survey instruments, and tools. Information items are linked to each other so that users can see, for example, which publications contain data citations to research data. The integration and linking of different kinds of information increase their visibility so that it is easier for researchers to find information for re-use. In a log-based usage study, we found that users search across different information types, that search sessions contain a high rate of positive signals and that link information is often explored.
As the world becomes increasingly dependent on technology, researchers in both industry and academia endeavor to understand how technology is used, the impact it has on everyday life, the artifact life-cycle and overall integrations of digital information. In doing so, researchers are increasingly gathering 'real-world' or 'in-the-wild' residual data, obtained from a variety of sources, without the explicit consent of the original owners. This data gathering raises significant concerns regarding privacy, ethics and legislation, as well as practical considerations concerning investigator training, data storage, overall security and data disposal. This research surveys recent studies of residual data gathered in-the-wild and analyzes the challenges that were confronted. Amalgamating these insights, the research presents a compendium of practices for addressing the issues that can arise in-the-wild when conducting residual data research. The practices identified in this research can be used to critique current projects and assess the feasibility of proposed future research.
The emergence of breakthrough artificial intelligence (AI) techniques has led to a renewed focus on how small data settings, i.e., settings with limited information, can benefit from such developments. This includes societal issues such as how best to include under-represented groups in data-driven policy and decision making, or the health benefits of assistive technologies such as wearables. We provide a conceptual overview, in particular contrasting small data with big data, and identify common themes from exemplary case studies and application areas. Potential solutions are described in a more detailed technical overview of current data analysis and modelling techniques, highlighting contributions from different disciplines, such as knowledge-driven modelling from statistics and data-driven modelling from computer science. By linking application settings, conceptual contributions and specific techniques, we highlight what is already feasible and suggest what an agenda for fully leveraging small data might look like.
In the rapidly evolving field of digital libraries, the development of large language models (LLMs) has opened up new possibilities for simulating user behavior. This innovation addresses the longstanding challenge in digital library research: the scarcity of publicly available datasets on user search patterns due to privacy concerns. In this context, we introduce Agent4DL, a user search behavior simulator specifically designed for digital library environments. Agent4DL generates realistic user profiles and dynamic search sessions that closely mimic actual search strategies, including querying, clicking, and stopping behaviors tailored to specific user profiles. Our simulator's accuracy in replicating real user interactions has been validated through comparisons with real user data. Notably, Agent4DL demonstrates competitive performance compared to existing user search simulators such as SimIIR 2.0, particularly in its ability to generate more diverse and context-aware user behaviors.
Thanks to the rapidly evolving integration of LLMs into decision-support tools, a significant transformation is happening across large-scale systems. Like other medical fields, the use of LLMs such as GPT-4 is gaining increasing interest in radiation oncology as well. An attempt to assess GPT-4's performance in radiation oncology was made via a dedicated 100-question examination on the highly specialized topic of radiation oncology physics, revealing GPT-4's superiority over other LLMs. GPT-4's performance on a broader field of clinical radiation oncology is further benchmarked by the ACR Radiation Oncology In-Training (TXIT) exam where GPT-4 achieved a high accuracy of 74.57%. Its performance on re-labelling structure names in accordance with the AAPM TG-263 report has also been benchmarked, achieving above 96% accuracies. Such studies shed light on the potential of LLMs in radiation oncology. As interest in the potential and constraints of LLMs in general healthcare applications continues to rise5, the capabilities and limitations of LLMs in radiation oncology decision support have not yet been fully explored.
Most of the recent literature on image super-resolution (SR) assumes the availability of training data in the form of paired low resolution (LR) and high resolution (HR) images or the knowledge of the downgrading operator (usually bicubic downscaling). While the proposed methods perform well on standard benchmarks, they often fail to produce convincing results in real-world settings. This is because real-world images can be subject to corruptions such as sensor noise, which are severely altered by bicubic downscaling. Therefore, the models never see a real-world image during training, which limits their generalization capabilities. Moreover, it is cumbersome to collect paired LR and HR images in the same source domain. To address this problem, we propose DSGAN to introduce natural image characteristics in bicubically downscaled images. It can be trained in an unsupervised fashion on HR images, thereby generating LR images with the same characteristics as the original images. We then use the generated data to train a SR model, which greatly improves its performance on real-world images. Furthermore, we propose to separate the low and high image frequencies and treat them differently