BridgeEQA: Virtual Embodied Agents for Real Bridge Inspections

Deploying embodied agents that can answer questions about their surroundings in realistic real-world settings remains difficult, partly due to the scarcity of benchmarks that faithfully capture practical operating conditions. We propose infrastructure inspection as a compelling domain for open-vocabulary Embodied Question Answering (EQA): it naturally demands multi-scale reasoning, long-range spatial understanding, and complex semantic relationships, while offering unique evaluation advantages via standardized National Bridge Inventory (NBI) condition ratings (0-9), professional inspection reports, and egocentric imagery. We introduce BridgeEQA, a benchmark of 2,200 open-vocabulary question-answer pairs (in the style of OpenEQA) grounded in professional inspection reports across 200 real-world bridge scenes with 47.93 images on average per scene. Questions require synthesizing visual evidence across multiple images and aligning responses with NBI condition ratings. We further propose a new EQA metric Image Citation Relevance to evaluate the ability of a model to cite relevant images. Evaluations of state-of-the-art vision-language models reveal substantial performance gaps under episodic memory EQA settings. To address this, we propose Embodied Memory Visual Reasoning (EMVR), which formulates inspection as sequential navigation over an image-based scene graph: images are nodes, and an agent takes actions to traverse views, compare evidence, and reason within a Markov decision process. EMVR shows strong performance over the baselines. We publicly release both the dataset and code.

RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG

Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence, yet evaluating RAG systems in specialized, safety-critical domains remains a significant challenge. Existing evaluation frameworks often rely on heuristic-based metrics that fail to capture domain-specific nuances and other works utilize LLM-as-a-Judge approaches that lack validated alignment with human judgment. This paper introduces RAGalyst, an automated, human-aligned agentic framework designed for the rigorous evaluation of domain-specific RAG systems. RAGalyst features an agentic pipeline that generates high-quality, synthetic question-answering (QA) datasets from source documents, incorporating an agentic filtering step to ensure data fidelity. The framework refines two key LLM-as-a-Judge metrics-Answer Correctness and Answerability-using prompt optimization to achieve a strong correlation with human annotations. Applying this framework to evaluate various RAG components across three distinct domains (military operations, cybersecurity, and bridge engineering), we find that performance is highly context-dependent. No single embedding model, LLM, or hyperparameter configuration proves universally optimal. Additionally, we provide an analysis on the most common low Answer Correctness reasons in RAG. These findings highlight the necessity of a systematic evaluation framework like RAGalyst, which empowers practitioners to uncover domain-specific trade-offs and make informed design choices for building reliable and effective RAG systems. RAGalyst is available on our Github.

ViewDelta: Text-Prompted Change Detection in Unaligned Images

Detecting changes between images is a fundamental problem in computer vision with broad applications in situational awareness, infrastructure assessment, environment monitoring, and industrial automation. Existing supervised models are typically limited to detecting specific types of changes, necessitating retraining for new tasks. To address these limitations with a single approach, we propose a novel change detection method that is the first to utilize unaligned images and textual prompts to output a binary segmentation of changes relevant to user-provided text. Our architecture not only enables flexible detection across diverse change detection use cases, but also yields state-of-the art performance on established benchmarks. Additionally, we release an accompanying dataset comprising of 100,311 pairs of images with text prompts and the corresponding change detection labels. We demonstrate the effectiveness of our method both quantitatively and qualitatively on datasets with a wide variety of viewpoints in indoor, outdoor, street level, synthetic, and satellite images.

View-Invariant Pixelwise Anomaly Detection in Multi-object Scenes with Adaptive View Synthesis

The inspection and monitoring of infrastructure assets typically requires identifying visual anomalies in scenes periodically photographed over time. Images collected manually or with robots such as unmanned aerial vehicles from the same scene at different instances in time are typically not perfectly aligned. Supervised segmentation methods can be applied to identify known problems, but unsupervised anomaly detection approaches are required when unknown anomalies occur. Current unsupervised pixel-level anomaly detection methods have mainly been developed for industrial settings where the camera position is known and constant. However, we find that these methods fail to generalize to the case when images are not perfectly aligned. We term the problem of unsupervised anomaly detection between two such imperfectly aligned sets of images as Scene Anomaly Detection (Scene AD). We present a novel network termed OmniAD to address the Scene AD problem posed. Specifically, we refine the anomaly detection method reverse distillation to achieve a 40% increase in pixel-level anomaly detection performance. The network's performance is further demonstrated to improve with two new data augmentation strategies proposed that leverage novel view synthesis and camera localization to improve generalization. We validate our approach with qualitative and quantitative results on a new dataset, ToyCity, the first Scene AD dataset with multiple objects, as well as on the established single object-centric dataset, MAD. https://drags99.github.io/OmniAD/