Related papers: ModelWizard: Toward Interactive Model Construction
A plausible definition of "reasoning" could be "algebraically manipulating previously acquired knowledge in order to answer a new question". This definition covers first-order logical inference or probabilistic inference. It also includes…
We describe a guided proceduralization framework that optimizes geometry processing on architectural input models to extract target grammars. We aim to provide efficient artistic workflows by creating procedural representations from…
We regard explanations as a blending of the input sample and the model's output and offer a few definitions that capture various desired properties of the function that generates these explanations. We study the links between these…
Data warehouses are overwhelmingly built through a bottom-up process, which starts with the identification of sources, continues with the extraction and transformation of data from these sources, and then loads the data into a set of data…
Mechanistic interpretability aims to explain neural model behaviour by reverse-engineering learned computational structure into human-understandable components. Without a formal framework, however, mechanistic explanations cannot be…
This experience report presents a model-driven approach to legacy system modernization that inserts an enriched, technology-agnostic intermediate model between the legacy codebase and the modern target platform, and reports on its…
There is growing interest in leveraging large language models (LLMs) for text-to-model translation and optimization tasks. This paper aims to advance this line of research by introducing \textsc{Text2Model} and \textsc{Text2Zinc}.…
Designing agents capable of explaining complex sequential decisions remain a significant open problem in automated decision-making. Recently, there has been a lot of interest in developing approaches for generating such explanations for…
Among the many software vulnerability discovery techniques available today, fuzzing has remained highly popular due to its conceptual simplicity, its low barrier to deployment, and its vast amount of empirical evidence in discovering…
With increasing linkage within value chains, the IT systems of different companies are also being connected with each other. This enables the integration of services within the movement of Industry 4.0 in order to improve the quality and…
A structural time series model additively decomposes into generative, semantically-meaningful components, each of which depends on a vector of parameters. We demonstrate that considering each generative component together with its vector of…
Large language models (LLMs) have transformed AI across diverse domains, with prompting being central to their success in guiding model outputs. However, manual prompt engineering is both labor-intensive and domain-specific, necessitating…
While multimodal large language models can describe visual content, their ability to generate executable procedures remains underexplored. CrochetBench presented in this paper evaluates this shift from describing to doing through…
Autonomous agents are increasingly expected to operate in complex, dynamic, and uncertain environments, performing tasks such as manipulation, navigation, and decision-making. Achieving these capabilities requires agents to understand the…
In spite of machine learning's rapid growth, its engineering support is scattered in many forms, and tends to favor certain engineering stages, stakeholders, and evaluation preferences. We envision a capability-based framework, which uses…
Data-driven storytelling has gained prominence in journalism and other data reporting fields. However, the process of creating these stories remains challenging, often requiring the integration of effective visualizations with compelling…
While machine learning can accurately model process systems, models for decision making should also be structurally simple and physically interpretable. In process control, for example, (nearly) linear models are favored than nonlinear…
Evaluation of robotic manipulation systems has largely relied on fixed benchmarks authored by a small number of experts, where task instances, constraints, and success criteria are predefined and difficult to extend. This paradigm limits…
What can be learned about causality and experimentation from passive data? This question is salient given recent successes of passively-trained language models in interactive domains such as tool use. Passive learning is inherently limited.…
Despite the tremendous efforts to democratize machine learning, especially in applied-science, the application is still often hampered by the lack of coding skills. As we consider programmatic understanding key to building effective and…