Related papers: Concept Learning with Energy-Based Models
Traditional event detection classifies a word or a phrase in a given sentence for a set of predefined event types. The limitation of such predefined set is that it prevents the adaptation of the event detection models to new event types. We…
In previous works, we proposed a one-category (entitled thimac) conceptual model called a thinging machine (TM), which integrates staticity (e.g., objects) and dynamism (e.g., events) without losing valuable aspects of diagrammatic…
Human activity recognition is typically addressed by detecting key concepts like global and local motion, features related to object classes present in the scene, as well as features related to the global context. The next open challenges…
Generalization is a key challenge in machine learning, specifically in reasoning tasks, where models are expected to solve problems more complex than those encountered during training. Existing approaches typically train reasoning models in…
Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation…
As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…
We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced…
Current video understanding models excel at recognizing "what" is happening but fall short in high-level cognitive tasks like causal reasoning and future prediction, a limitation rooted in their lack of commonsense world knowledge. To…
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,…
Despite significant achievements and current interest in machine learning and artificial intelligence, the quest for a theory of intelligence, allowing general and efficient problem solving, has done little progress. This work tries to…
It is asserted that consciousness functionally is a vision. Biologically it is a sensation of work of a brain that converts external and internal signals into visual output. However, as we well know, human consciousness includes meaning…
We consider a living organism as an observer of the evolution of its environment recording sensory information about the state space X of the environment in real time. Sensory information is sampled and then processed on two levels. On the…
Demonstration is an appealing way for humans to provide assistance to reinforcement-learning agents. Most approaches in this area view demonstrations primarily as sources of behavioral bias. But in sparse-reward tasks, humans seem to treat…
The term behavior engineering (BE) encompasses a broad integration of behavioral and compositional requirements needed to model large-scale systems. BE forms a connection between systems-engineering processes and software-engineering…
The emergence of large language models (LLMs) has demonstrated that systems trained solely on text can acquire extensive world knowledge, develop reasoning capabilities, and internalize abstract semantic concepts--showcasing properties that…
Training a model to detect patterns of interrelated events that form situations of interest can be a complex problem: such situations tend to be uncommon, and only sparse data is available. We propose a hybrid neuro-symbolic architecture…
Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…
We propose a new class of waveform foundation models that departs from conventional sequence based representations by modeling physiological time series as realizations of latent event processes. Rather than treating signals as collections…
Motivation: Biomedical event detection is fundamental for information extraction in molecular biology and biomedical research. The detected events form the central basis for comprehensive biomedical knowledge fusion, facilitating the…
The infrastructure upon which the functioning of society depends is composed of complex ecosystems of systems. Consequently, we must reason about the properties of such ecosystems, which requires that we construct models of them. There are…