Related papers: CHAMELEON: OutSystems Live Bidirectional Transform…
Dynamic mode decomposition (DMD) has emerged as a popular data-driven modeling approach to identifying spatio-temporal coherent structures in dynamical systems, owing to its strong relation with the Koopman operator. For dynamical systems…
Most current neural networks for molecular dynamics (MD) include physical inductive biases, resulting in specialized and complex architectures. This is in contrast to most other machine learning domains, where specialist approaches are…
Building generalist embodied agents requires a unified system that can interpret multimodal goals, model environment dynamics, and execute reliable actions across diverse real-world tasks. Multimodal large language models (MLLMs) offer…
Context: The OutSystems Platform is a development environment composed of several DSLs, used to specify, quickly build, and validate web and mobile applications. The DSLs allow users to model different perspectives such as interfaces and…
As LLM-based agents increasingly rely on external tools, it is important to evaluate their ability to sustain tool-grounded reasoning beyond familiar workflows and short-range interactions. We introduce AgentEscapeBench, an…
Recent advances in text-to-image (T2I) diffusion models have significantly improved semantic image editing, yet most methods fall short in performing 3D-aware object manipulation. In this work, we present FFSE, a 3D-aware autoregressive…
The authors' "metatools" are a collection of tools for generic programming. This includes generating Java sources from mathematically well-founded specifications, as well as the creation of strictly typed document object models for XML…
Large language models (LLMs) have enabled web agents that follow natural language goals through multi-step browser interactions. However, agents fine-tuned on specific trajectories and domain often struggle to generalize out of domain, and…
The integration of large language models (LLMs) with external tools has significantly expanded the capabilities of AI agents. However, as the diversity of both LLMs and tools increases, selecting the optimal model-tool combination becomes a…
We introduce ChatGarment, a novel approach that leverages large vision-language models (VLMs) to automate the estimation, generation, and editing of 3D garments from images or text descriptions. Unlike previous methods that struggle in…
In this paper we apply a model-driven engineering approach to designing domain-specific solutions for robot control system development. We present a case study of the complete process, including identification of the domain meta-model,…
Researchers have been highly active to investigate the classical machine learning workflow and integrate best practices from the software engineering lifecycle. However, deep learning exhibits deviations that are not yet covered in this…
Professional creative software has steep learning curves for novices due to complex interfaces, limited guidance, and unfamiliar terminology. To support educators and tool creators in addressing learner challenges, we introduce TaskLens, an…
Model transformations are helpful to evolve, refactor, refine and maintain models. While domain-specific languages are normally intuitive for modelers, common model transformation approaches (regardless of whether they transform graphical…
Computer-Aided Design (CAD) delivers rapid, editable modeling for engineering and manufacturing. Recent AI progress now makes full automation feasible for various CAD tasks. However, progress is bottlenecked by data: public corpora mostly…
Multimodal Artificial Intelligence (AI) systems, particularly Vision-Language Models (VLMs), have become integral to critical applications ranging from autonomous decision-making to automated document processing. As these systems scale,…
There is a pressing need for better development methods and tools to keep up with the growing demand and increasing complexity of new software systems. New types of user interfaces, the need for intelligent components, sustainability…
Distributed software engineering is widely recognized as a complex task. Among the inherent complexities is the process of obtaining a system design from its global requirement specification. This paper deals with such transformation…
Flow diagrams are a common tool used to help build and interpret models of dynamical systems, often in biological contexts such as consumer-resource models and similar compartmental models. Typically, their usage is intuitive and informal.…
Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio, thanks to their temporally uni-directional attention mechanism, which models correlations between the current token and previous…