activity
20222024
most citedGrounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations

2 citations · 4 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CL2024

Exploring Failure Cases in Multimodal Reasoning About Physical Dynamics

Sadaf Ghaffari, Nikhil Krishnaswamy

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 demon…

cs.HC2023

Combining Automatic Coding and Instructor Input to Generate ENA Visualizations for Asynchronous Online Discussion

Marcia Moraes, Sadaf Ghaffari, Yanye Luther +1

Asynchronous online discussions are a common fundamental tool to facilitate social interaction in hybrid and online courses. However, instructors lack the tools to accomplish the o…

cs.CL2023★ 2 cited

Grounding and Distinguishing Conceptual Vocabulary Through Similarity Learning in Embodied Simulations

Sadaf Ghaffari, Nikhil Krishnaswamy

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 lea…

cs.LG2022★ 1 cited

Detecting and Accommodating Novel Types and Concepts in an Embodied Simulation Environment

Sadaf Ghaffari, Nikhil Krishnaswamy

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, and…

cs.LG2022

Automated Code Extraction from Discussion Board Text Dataset

Sina Mahdipour Saravani, Sadaf Ghaffari, Yanye Luther +2

This study introduces and investigates the capabilities of three different text mining approaches, namely Latent Semantic Analysis, Latent Dirichlet Analysis, and Clustering Word V…

cs.AI2022★ 1 cited

Exploiting Embodied Simulation to Detect Novel Object Classes Through Interaction

Nikhil Krishnaswamy, Sadaf Ghaffari

In this paper we present a novel method for a naive agent to detect novel objects it encounters in an interaction. We train a reinforcement learning policy on a stacking task given…