Grounding and distinguishing conceptual vocabulary through similarity learning in embodied simulations
S Ghaffari, N Krishnaswamy - arXiv preprint arXiv:2305.13668, 2023 - arxiv.org
We present a novel method for using agent experiences gathered through an embodied
simulation to ground contextualized word vectors to object representations. We use similarity …
simulation to ground contextualized word vectors to object representations. We use similarity …
Detecting and accommodating novel types and concepts in an embodied simulation environment
S Ghaffari, N Krishnaswamy - arXiv preprint arXiv:2211.04555, 2022 - arxiv.org
In this paper, we present methods for two types of metacognitive tasks in an AI system:
rapidly expanding a neural classification model to accommodate a new category of object …
rapidly expanding a neural classification model to accommodate a new category of object …
An Abstract Specification of VoxML as an Annotation Language
VoxML is a modeling language used to map natural language expressions into real-time
visualizations using commonsense semantic knowledge of objects and events. Its utility has …
visualizations using commonsense semantic knowledge of objects and events. Its utility has …
A Methodology for Evaluating Multimodal Referring Expression Generation for Embodied Virtual Agents
N Alalyani, N Krishnaswamy - … of the 25th International Conference on …, 2023 - dl.acm.org
Robust use of definite descriptions in a situated space often involves recourse to both verbal
and non-verbal modalities. For IVAs, virtual agents designed to interact with humans, the …
and non-verbal modalities. For IVAs, virtual agents designed to interact with humans, the …
Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics
S Ghaffari, N Krishnaswamy - arXiv preprint arXiv:2402.15654, 2024 - arxiv.org
In this paper, we present an exploration of LLMs' abilities to problem solve with physical
reasoning in situated environments. We construct a simple simulated environment and …
reasoning in situated environments. We construct a simple simulated environment and …
[PDF][PDF] Hybrid Machine Learning/Knowledge Base Systems Learning through Natural Language Dialogue with Deep Learning Models
Neurosymbolic approaches to AI typically involve attempts to reincorporate the structure and
speed of symbolic reasoning into the flexible representations of deep learning.“Knowledge,” …
speed of symbolic reasoning into the flexible representations of deep learning.“Knowledge,” …
[PDF][PDF] Hybrid ML/KB Systems Learning through NL Dialog with DL Models
S Nirenburg, N Krishnaswamy… - AAAI-Make Workshop …, 2023 - homepages.hass.rpi.edu
Neurosymbolic approaches to artificial intelligence have so far been understood primarily as
“a method of reincorporating some of the structure and speed of symbolic reasoning into the …
“a method of reincorporating some of the structure and speed of symbolic reasoning into the …