Related papers: [Draft] High-order estimation-based properties and…
We present SLOT-V, a novel supervised learning framework that learns observer models (human preferences) from robot motion trajectories in a legibility context. Legibility measures how easily a (human) observer can infer the robot's goal…
We present a general framework for classifying partially observed dynamical systems based on the idea of learning in the model space. In contrast to the existing approaches using model point estimates to represent individual data items, we…
System identification based on Koopman operator theory has grown in popularity recently. Spectral properties of the Koopman operator of a system were proven to relate to properties like invariant sets, stability, periodicity, etc. of the…
Explainability is emerging as a key requirement for autonomous systems. While many works have focused on what constitutes a valid explanation, few have considered formalizing explainability as a system property. In this work, we approach…
Large Language Models (LLMs) are increasingly deployed within agentic systems - collections of interacting, LLM-powered agents that execute complex, adaptive workflows using memory, tools, and dynamic planning. While enabling powerful new…
Existing imitation learning approaches often require that the complete demonstration data, including sequences of actions and states, are available. In this paper, we consider a more realistic and difficult scenario where a reinforcement…
In this note, we propose a novel approach for a class of autonomous dynamical systems that allows, given some observations of the solutions, to identify its parameters and reconstruct the state vector. This approach relies on proving the…
We survey work on the paradigm called "computing by observing." Its central feature is that one considers the behavior of an evolving system as the result of a computation. To this end an observer records this behavior. It has turned out…
This is a preliminary version of visual interpretation integrating multiple sensors in SUCCESSOR, an intelligent, model-based vision system. We pursue a thorough integration of hierarchical Bayesian inference with comprehensive physical…
Estimating hidden states in dynamical systems, also known as optimal filtering, is a long-standing problem in various fields of science and engineering. In this paper, we introduce a general filtering framework, \textbf{LLM-Filter}, which…
In this contribution we revisit regular model checking, a powerful framework that has been successfully applied for the verification of infinite-state systems, especially parameterized systems (concurrent systems with an arbitrary number of…
Functional programs typically interact with stateful libraries that hide state behind typed abstractions. One particularly important class of applications are data structure implementations that rely on such libraries to provide a level of…
This article addresses the problem of state observer design for continuous-time linear positive networked systems. Considering the bandwidth constraint in the communication network, an event-measurement-based positive observer design is…
In this paper, we consider partially observable timed automata endowed with a single clock. A time interval is associated with each transition specifying at which clock values it may occur. In addition, a resetting condition associated to a…
We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning. Given an image, we first predict a probabilistic…
We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…
We propose an automaton model which is a combination of symbolic and register automata, i.e., we enrich symbolic automata with memory. We call such automata Register Match Automata (RMA). RMA extend the expressive power of symbolic…
Prior work has shown that coupling sequential latent variable models with semantic ontological knowledge can improve the representational capabilities of event modeling approaches. In this work, we present a novel, doubly hierarchical,…
Humans can infer accurate mechanical outcomes from only a few observations, a capability known as mechanics intuition. The mechanisms behind such data-efficient learning remain unclear. Here, we propose a reinforcement learning framework in…
Emerging generative world models and vision-language-action (VLA) systems are rapidly reshaping automated driving by enabling scalable simulation, long-horizon forecasting, and capability-rich decision making. Across these directions,…