Related papers: Neurosymbolic Framework for Concept-Driven Logical…
Visual reasoning, particularly spatial reasoning, is a challenging cognitive task that requires understanding object relationships and their interactions within complex environments, especially in robotics domain. Existing vision_language…
Despite significant progress in natural language understanding, Large Language Models (LLMs) remain error-prone when performing logical reasoning, often lacking the robust mental representations that enable human-like comprehension. We…
In this paper we present a neurosymbolic architecture for coupling language-guided visual reasoning with robot manipulation. A non-expert human user can prompt the robot using unconstrained natural language, providing a referring expression…
Reasoning on the context of human beings is crucial for many real-world applications especially for those deploying autonomous systems (e.g. robots). In this paper, we present a new approach for context reasoning to further advance the…
Neural-symbolic approaches to machine learning incorporate the advantages from both connectionist and symbolic methods. Typically, these models employ a first module based on a neural architecture to extract features from complex data.…
While concept-based explanations improve interpretability over local attributions, they often rely on correlational signals and lack causal validation. We introduce VisionLogic, a novel neural-symbolic framework that produces faithful,…
This paper presents a neurosymbolic framework to solve motion planning problems for mobile robots involving temporal goals. The temporal goals are described using temporal logic formulas such as Linear Temporal Logic (LTL) to capture…
Spatial reasoning based on natural language expressions is essential for everyday human tasks. This reasoning ability is also crucial for machines to interact with their environment in a human-like manner. However, recent research shows…
Humans interact with the environment using a combination of perception - transforming sensory inputs from their environment into symbols, and cognition - mapping symbols to knowledge about the environment for supporting abstraction,…
Skeleton-based human action recognition has received widespread attention in recent years due to its diverse range of application scenarios. Due to the different sources of human skeletons, skeleton data naturally exhibit heterogeneity. The…
Patients with mental disorders often exhibit risky abnormal actions, such as climbing walls or hitting windows, necessitating intelligent video behavior monitoring for smart healthcare with the rising Internet of Things (IoT) technology.…
Robotic systems operating in human environments must reason about how object interactions evolve over time, which actions are currently being performed, and what manipulation step is likely to follow. Classical enriched Semantic Event…
We propose NEURONA, a neuro-symbolic framework for fMRI decoding and concept grounding in neural activity. Leveraging image- and video-based fMRI question-answering datasets, NEURONA learns to decode interacting concepts from visual stimuli…
Deep Learning models are a standard solution for sensor-based Human Activity Recognition (HAR), but their deployment is often limited by labeled data scarcity and models' opacity. Neuro-Symbolic AI (NeSy) provides an interesting research…
Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…
Zero-shot skeleton action recognition is a non-trivial task that requires robust unseen generalization with prior knowledge from only seen classes and shared semantics. Existing methods typically build the skeleton-semantics interactions by…
Skeleton-based action recognition has made great progress recently, but many problems still remain unsolved. For example, most of the previous methods model the representations of skeleton sequences without abundant spatial structure…
Situationally-aware artificial agents operating with competence in natural environments face several challenges: spatial awareness, object affordance detection, dynamic changes and unpredictability. A critical challenge is the agent's…
Computational context understanding refers to an agent's ability to fuse disparate sources of information for decision-making and is, therefore, generally regarded as a prerequisite for sophisticated machine reasoning capabilities, such as…
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior…