Abstract
This survey provides a comprehensive overview of Video Anomaly Detection (VAD), focusing on identifying robust and interpretable methods for detecting anomalous events. It emphasizes the limitations of traditional supervised and unsupervised approaches and highlights the advantages of weakly supervised learning, in which models operate with minimal or no explicit anomaly annotations. A key contribution of this survey is its analysis of multi-modal data - integrating visual, audio, and textual modalities - for enhanced anomaly detection. It underscores how audio cues enrich visual features and how textual information during training fosters semantically richer representations. This multi-modal approach demonstrates improved generalization, better detection of subtle anomalies, and interpretable explanations of detected events, marking a paradigm shift in the field, Video Anomaly Understanding (VAU). Synthesizing advancements from benchmarks to methodologies, this work advocates for a centralized platform to enable systematic comparisons across diverse datasets, standardized evaluation metrics, and reproducible ablation studies of novel components. Such a framework would streamline the integration of innovations, address version control and foster transparency, bridging the gap between isolated methodological advances and system-level robustness. By prioritizing contextual understanding, causal reasoning, and real-world interpretability, this initiative aims to elevate weakly supervised VAD beyond detection, ensuring models contextualize and explain anomalies in practical deployments.

Abstract
In addition to evaluating tumor morphology using H&E staining, immunohistochemistry is used to assess the presence of specific proteins within the tissue. However, this is a costly and labor-intensive technique, for which virtual staining, as an image-to-image translation task, offers a promising alternative. Although recent, this is an emerging field of research with 64% of published studies just in 2024. Most studies use publicly available datasets of H&E-IHC pairs from consecutive tissue sections. Recognizing the training challenges, many authors develop complex virtual staining models based on conditional Generative Adversarial Networks but ignore the impact of adversarial loss on the quality of virtual staining. Furthermore, overlooking the issues of model evaluation, they claim improved performance based on metrics such as SSIM and PSNR, which are not sufficiently robust to evaluate the quality of virtually stained images. In this paper, we developed CSSP2P GAN, which we demonstrate to achieve heightened pathological fidelity through a blind pathological expert evaluation. Furthermore, while iteratively developing our model, we study the impact of the adversarial loss and demonstrate its crucial role in the quality of virtually stained images. Finally, while comparing our model with reference works in the field, we underscore the limitations of the currently used evaluation metrics and demonstrate the superior performance of CSSP2P GAN.

Abstract
This work reflects upon what Immersion can mean from the perspective of an Artificial Intelligence (AI). Applying the lens of immersive learning theory, it seeks to understand whether this new perspective supports ways for AI participation in cognitive ecologies. By treating AI as a participant rather than a tool, it explores what other participants (humans and other AIs) need to consider in environments where AI can meaningfully engage and contribute to the cognitive ecology, and what the implications are for designing such learning environments. Drawing from the three conceptual dimensions of immersion-System, Narrative, and Agency-this work reinterprets AIs in immersive learning contexts. It outlines practical implications for designing learning environments where AIs are surrounded by external digital services, can interpret a narrative of origins, changes, and structural developments in data, and dynamically respond, making operational and tactical decisions that shape human-AI collaboration. Finally, this work suggests how these insights might influence the future of AI training, proposing that immersive learning theory can inform the development of AIs capable of evolving beyond static models. This paper paves the way for understanding AI as an immersive learner and participant in evolving human-AI cognitive ecosystems.

Abstract

Abstract

Abstract
To achieve further performance and efficiency, System-onChip (SoC) designs increasingly rely on core customization or integration of application-specific hardware blocks. This requires extensive efforts during Design Space Exploration (DSE) of new hardware to achieve integration, correctness, and target performance. This is time-consuming and error-prone, hindering fast iterative hardware/software co-design. This paper presents a co-simulation framework which integrates arbitrary high-level simulators into Verilog-based SoC platforms, demonstrated on the RISC-V–based open-source X-HEEP SoC. Using inter-process communication we enable cycle-accurate lock-step co-simulation where high-level simulators of accelerators are exposed as memory-mapped peripherals to the RISC-V core. For experimental validation we re-implemented an existing peripheral of the X-HEEP SoC written in Register-Transfer Level (RTL) as an external simulator process, and observed that the co-simulated version maintains identical cycle-level behavior with a maximum wall-clock overhead of 11%. This work enables fast DSEs of heterogeneous RISC-V–based SoCs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.