Related papers: Can VLMs Unlock Semantic Anomaly Detection? A Fram…

The integration of open-source third-party library dependencies in Java development introduces significant security risks when these libraries contain known vulnerabilities. Existing Software Composition Analysis (SCA) tools struggle to…

As robots acquire increasingly sophisticated skills and see increasingly complex and varied environments, the threat of an edge case or anomalous failure is ever present. For example, Tesla cars have seen interesting failure modes ranging…

Pre-trained Vision-Language Models (VLMs) have recently shown promise in detecting anomalies. However, previous approaches are fundamentally limited by their reliance on human-designed prompts and the lack of accessible anomaly samples,…

Semantic anomalies-context-dependent hazards that pixel-level detectors cannot reason about-pose a critical safety risk in autonomous driving. We propose a \emph{semantic observer layer}: a quantized vision-language model (VLM) running at…

Recent advancements in open-source Visual Language Models (VLMs) such as LLaVA, Qwen-VL, and Llama have catalyzed extensive research on their integration with diverse systems. The internet-scale general knowledge encapsulated within these…

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This…

Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only normal samples have gained traction, they often suffer from high…

We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our…

Autonomous driving systems face significant challenges in handling unpredictable edge-case scenarios, such as adversarial pedestrian movements, dangerous vehicle maneuvers, and sudden environmental changes. Current end-to-end driving models…

We show that multi-agent systems guided by vision-language models (VLMs) improve end-to-end autonomous scientific discovery. By treating plots as verifiable checkpoints, a VLM-as-a-judge evaluates figures against dynamically generated…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Vision-language models (VLMs) show promise for autonomous driving but often lack transparent reasoning capabilities that are critical for safety. We investigate whether explicitly modeling reasoning during fine-tuning enhances VLM…

Logical image understanding involves interpreting and reasoning about the relationships and consistency within an image's visual content. This capability is essential in applications such as industrial inspection, where logical anomaly…

Vision Language Models (VLMs) have advanced perception in autonomous driving (AD), but they remain vulnerable to adversarial threats. These risks range from localized physical patches to imperceptible global perturbations. Existing defense…

While Vision-Language Models (VLMs) have shown promising progress in general multimodal tasks, they often struggle in industrial anomaly detection and reasoning, particularly in delivering interpretable explanations and generalizing to…

Large-scale Vision-Language Models (VLMs) have achieved notable progress in aligning visual inputs with text. However, their ability to deeply understand the unique physical properties of non-RGB vision sensor images remains limited. In…

Video Anomaly Detection (VAD) has traditionally been framed as binary classification or outlier detection, providing neither interpretable reasoning nor precise spatial localization of anomalous events. While Vision-Language Models (VLMs)…

Vision-Language Models (VLMs) offer the ability to generate high-level, interpretable descriptions of complex activities from images and videos, making them valuable for situational awareness (SA) applications. In such settings, the focus…

Vision-Language Models (VLMs) show promise for autonomous driving, yet their struggle with hallucinations, inefficient reasoning, and limited real-world validation hinders accurate perception and robust step-by-step reasoning. To overcome…

Ensuring safe decision-making in autonomous vehicles remains a fundamental challenge despite rapid advances in end-to-end learning approaches. Traditional reinforcement learning (RL) methods rely on manually engineered rewards or sparse…