Related papers: Improving the Visualization of Alloy Instances

In-context learning (ICL) enables multimodal large language models (MLLMs) to classify images from a few labelled examples. Yet, how these models use the provided context remains opaque. While Chain-of-Thought prompting is widely used,…

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…

Visual entailment (VE) is to recognize whether the semantics of a hypothesis text can be inferred from the given premise image, which is one special task among recent emerged vision and language understanding tasks. Currently, most of the…

Explainable Artificial Intelligence (XAI) has gained importance in interpreting model predictions. Among leading techniques for XAI, Local Interpretable Model-agnostic Explanations (LIME) is most frequently utilized as it notably helps…

Alignment of large language models remains a central challenge in natural language processing. Preference optimization has emerged as a popular and effective method for improving alignment, typically through training-time or prompt-based…

The advancement of vision language models (VLMs) has empowered embodied agents to accomplish simple multimodal planning tasks, but not long-horizon ones requiring long sequences of actions. In text-only simulations, long-horizon planning…

Accelerated discovery in materials science demands autonomous systems capable of dynamically formulating and solving design problems. In this work, we introduce a novel framework that leverages Bayesian optimization over a problem…

Recent advancements in autonomous driving (AD) have explored the use of vision-language models (VLMs) within visual question answering (VQA) frameworks for direct driving decision-making. However, these approaches often depend on…

The quality of software products tends to correlate with the quality of the abstractions adopted early in the design process. Acknowledging this tendency has led to the development of various tools and methodologies for modeling systems…

Explainability is one of the key ethical concepts in the design of AI systems. However, attempts to operationalize this concept thus far have tended to focus on approaches such as new software for model interpretability or guidelines with…

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…

Uncertainty quantification is essential for assessing the reliability and trustworthiness of modern AI systems. Among existing approaches, verbalized uncertainty, where models express their confidence through natural language, has emerged…

End-to-end robot policies achieve high performance through neural networks trained via reinforcement learning (RL). Yet, their black box nature and abstract reasoning pose challenges for human-robot interaction (HRI), because humans may…

Recent work has demonstrated the promise of combining local explanations with active learning for understanding and supervising black-box models. Here we show that, under specific conditions, these algorithms may misrepresent the quality of…

Machine Learning (ML) is becoming more prevalent in the systems we use daily. Yet designers of these systems are under-equipped to design with these technologies. Recently, interactive visualizations have been used to present ML concepts to…

Computer programming is among the fundamental aspects of computer science curriculum. Many students first introduced to introductory computer programming courses experience difficulties in learning and comprehending. Vast amount of…

Appropriate evaluation is a key component in visualization research. It is typically based on empirical studies that assess visualization components or complete systems. While such studies often include the user of the visualization,…

This paper introduces a novel method of analysis for SoC development building upon commonly used tools and techniques to approximate and automate the human process of investigation. Knowledge of the interactions between components within a…

This study empirically validates automated logical specification methods for behavioural models, focusing on their robustness, scalability, and reproducibility. By the systematic reproduction and extension of prior results, we confirm key…

Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse view guides "where to look", while selectively acquired…