Gita Sukthankar

University of Central Florida | UCF · Department of Electrical Engineering & Computer Science

Background: This article introduces SC-Phi2, a fine-tuned StarCraft II small language model. Small language models, like Phi2, Gemma, and DistilBERT, are streamlined versions of large language models (LLMs) with fewer parameters that require less computational power and memory to run. Method: To teach Microsoft’s Phi2 model about StarCraft, we crea...

This paper introduces SC-Phi2, a fine-tuned StarCraft II small language model for macromanagement tasks. Small language models, like Phi2, Gemma, and DistilBERT, are streamlined versions of large language models (LLMs) with fewer parameters that require less power and memory to run. To teach Microsoft's Phi2 model about StarCraft, we create a new S...

In humans, intrinsic motivation is an important mechanism for open-ended cognitive development; in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is $\textit{episodic memory}$ which enables both the recollection of events from the past and the projection of subjective future. This paper...

Due to the rise in video content creation targeted towards children, there is a need for robust content moderation schemes for video hosting platforms. A video that is visually benign may include audio content that is inappropriate for young children while being impossible to detect with a unimodal content moderation system. Popular video hosting p...

We present a novel method aimed at enhancing the sample efficiency of ensemble Q learning. Our proposed approach integrates multi-head self-attention into the ensembled Q networks while bootstrapping the state-action pairs ingested by the ensemble. This not only results in performance improvements over the original REDQ and its variant DroQ, thereb...

Human-centric visual understanding is an important desideratum for effective human-robot interaction. In order to navigate crowded public places, social robots must be able to interpret the activity of the surrounding humans. This paper addresses one key aspect of human-centric visual understanding, multi-person pose estimation. Achieving good perf...

In humans, intrinsic motivation is an important mechanism for open-ended cognitive development; in robots, it has been shown to be valuable for exploration. An important aspect of human cognitive development is episodic memory which enables both the recollection of events from the past and the projection of subjective future. This paper explores th...

Conflict prediction in communication is integral to the design of virtual agents that support successful teamwork by providing timely assistance. The aim of our research is to analyze discourse to predict collaboration success. Unfortunately, resource scarcity is a problem that teamwork researchers commonly face since it is hard to gather a large n...

Software quality is an important problem for technology companies, since it substantially impacts the efficiency, usefulness, and maintainability of the final product; hence, code review is a must-do activity for software developers. During the code review process, senior engineers monitor other developers' work to spot possible problems and enforc...

This paper presents a new approach for predicting team performance from the behavioral traces of a set of agents. This spatiotemporal forecasting problem is very relevant to sports analytics challenges such as coaching and opponent modeling. We demonstrate that our proposed model, Spatial Temporal Graph Convolutional Networks (ST-GCN), outperforms...

This paper presents an analysis of how dialogue act sequences vary across different datasets in order to anticipate the potential degradation in the performance of learned models during domain adaptation. We hypothesize the following: 1) dialogue sequences from related domains will exhibit similar n-gram frequency distributions 2) this similarity c...

In this study, we explore the future of work by examining differences in productivity when teams are composed of only humans or both humans and machine agents. Our objective was to characterize the similarities and differences between human and human–machine teams as they work to coordinate across their specialized roles. This form of research is i...

Good communication is indubitably the foundation of effective teamwork. Over time teams develop their own communication styles and often exhibit entrainment, a conversational phenomena in which humans synchronize their linguistic choices. Conversely, teams may experience conflict due to either personal incompatibility or differing viewpoints. We ta...

This paper explains the design of a social network analysis framework, developed under DARPA’s SocialSim program, with novel architecture that models human emotional, cognitive, and social factors. Our framework is both theory and data-driven, and utilizes domain expertise. Our simulation effort helps understanding how information flows and evolves...

Many of the most popular intelligent training systems, including driving and flight simulators, generate user time series data. This paper presents a comparison of representation options for two different student modeling problems: 1) early failure prediction and 2) classifying student activities. Data for this analysis was gathered from pilots exe...

The ever-increasing complexity of modern software engineering projects makes the usage of automated assistants imperative. Bots can be used to complete repetitive tasks during development and testing, as well as promoting communication between team members through issue reporting and documentation. Although the ultimate aim of these automated assis...

Good communication is indubitably the foundation of effective teamwork. Over time teams develop their own communication styles and often exhibit entrainment, a conversational phenomena in which humans synchronize their linguistic choices. This paper examines the problem of predicting team performance from embeddings learned from multiparty dialogue...

As the complexity of aircraft cockpit operations increases, training effectiveness must be improved, and learning accelerated. Virtual reality (VR) training is increasingly offered as a method for improving training efficacy given its ability to provide a rich sensory experience during learning. This paper describes a study examining how training e...

Social coding platforms, such as GitHub, serve as laboratories for studying collaborative problem solving in open source software development; a key feature is their ability to support issue reporting which is used by teams to discuss tasks and ideas. Analyzing the dialogue between team members, as expressed in issue comments, can yield important i...

Popularity and engagement are the currencies of social media platforms, serving as powerful reinforcement mechanisms to keep users online. Social coding platforms such as GitHub serve a dual purpose: they are practical tools that facilitate asynchronous, distributed collaborations between software developers while also supporting passive social med...

While there are many machine learning methods to classify and cluster sequences, they fail to explain what are the differences in groups of sequences that make them distinguishable. Although in some cases having a black box model is sufficient, there is a need for increased explainability in research areas focused on human behaviors. For example, p...

Our goal is to understand the characteristics of high-performing teams on GitHub. Towards this end, we collect data from software repositories and evaluate teams by examining differences in productivity. Our study focuses on the team formation phase, the first six months after repository creation. To better understand team activity, we clustered re...

This paper investigates the problem of predicting student flight performance in a training simulation from multimodal features, including flight controls, visual attention, and knowledge acquisition tests. This is a key component of developing next generation training simulations that can optimize the usage of student training time. Two types of su...

Understanding event sequences is an important aspect of game analytics, since it is relevant to many player modeling questions. This paper introduces a method for analyzing event sequences by detecting contrasting motifs; the aim is to discover subsequences that are significantly more similar to one set of sequences vs. other sets. Compared to exis...

Open source software development platforms are natural laboratories for studying the diffusion of innovation across human populations, enabling us to better understand what motivates people to adopt new ideas. For example, GitHub, a software repository and collaborative development tool built on the Git distributed version control system, provides...

This paper explores the value of weak-ties in classifying academic literature with the use of graph convolutional neural networks. Our experiments look at the results of treating weak-ties as if they were strong-ties to determine if that assumption improves performance. This is done by applying the methodological framework of the Simplified Graph C...

This paper explains the design of a social network analysis framework, developed under DARPA's SocialSim program, with novel architecture that models human emotional, cognitive and social factors. Our framework is both theory and data-driven, and utilizes domain expertise. Our simulation effort helps in understanding how information flows and evolv...

The aim of our research is to forecast the propagation of information related to cybersecurity threats and software vulnerabilities on social coding platforms such as GitHub. Users on social coding platforms exhibit repetitive behavior patterns that can be leveraged to predict trends in network evolution. These patterns exhibit greater consistency...

Burst analysis and prediction is a fundamental problem in social network analysis, since user activities have been shown to have an intrinsically bursty nature. Bursts may also be a signal of topics that are of growing real-world interest. Since bursts can be caused by exogenous phenomena and are indicative of burgeoning popularity, leveraging cros...

A physical selfie stick extends the user's reach, enabling the creation of personal photos that include more of the background scene. Conversely a quadcopter can capture photos at distances unattainable for the human, but teloperating a quadcopter to a good viewpoint is a non-trivial task. This paper presents a natural interface for quadcopter phot...

One of the advantages of teaching robots by demonstration is that it can be more intuitive for users to demonstrate rather than describe the desired robot behavior. However, when the human demonstrates the task through an interface, the training data may inadvertently acquire artifacts unique to the interface, not the desired execution of the task....

Social norms have been demonstrated to strongly affect people's health choices, yet they are often not included in health models due to the complex interdependencies of reasoning about norm adoption over a large population. This article introduces two agent‐based modeling frameworks designed explicitly for reasoning about the influence of social no...

Object detection models based on convolutional neural networks (CNNs) demonstrate impressive performance when trained on large-scale labeled datasets. While a generic object detector trained on such a dataset performs adequately in applications where the input data is similar to user photographs, the detector performs poorly on small objects, parti...

In this paper we introduce the concept of network semantic segmentation for social network analysis. We consider the GitHub social coding network which has been a center of attention for both researchers and software developers. Network semantic segmentation describes the process of associating each user with a class label such as a topic of intere...

Social coding platforms, such as GitHub, can serve as natural laboratories for studying the diffusion of innovation through tracking the pattern of code adoption by programmers. This paper focuses on the problem of predicting the popularity of software repositories over time; our aim is to forecast the time series of popularity-related events (code...

One of the most challenging coordination problems in artificial intelligence is to achieve successful collaboration across large-scale heterogeneous systems that include Robots, Agents, and People (RAP). In the best case, these RAP systems are potentially capable of leveraging the strengths of the individual entities to achieve complex distributed...

Drones are a versatile platform for both amateur and professional photographers, enabling them to capture photos that are impossible to shoot with ground-based cameras. However, when guided by inexperienced pilots, they have a high incidence of collisions, crashes, and poorly framed photographs. This paper presents an intelligent user interface for...

Agent-based models are a powerful tool for predicting population level behaviors; however their performance can be sensitive to the initial simulation conditions. This paper introduces a procedure for leveraging large datasets to initialize agent-based simulations in which the population is abstracted into a set of archetypes. We show that these ar...

Cambridge Core - Computing and Society - Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Social Interactions in Virtual Worlds - edited by Kiran Lakkaraju July 2018

Many interesting real-world systems are represented as complex networks with multiple types of interactions and complicated dependency structures between layers. These interactions can be encoded as having a valence with positive links marking interactions such as trust and friendship and negative links denoting distrust or hostility. Extracting in...

One of the advantages of teaching robots by demonstration is that it can be more intuitive for users to demonstrate rather than describe the desired robot behavior. However, when the human demonstrates the task through an interface, the training data may inadvertently acquire artifacts unique to the interface, not the desired execution of the task....

This paper presents a practical approach towards implementing pathfinding algorithms on real-world and low-cost non- commercial hardware platforms. While using robotics simulation platforms as a test-bed for our algorithms we easily overlook real- world exogenous problems that are developed by external factors. Such problems involve robot wheel sli...

Although sources of social media data abound, companies are often reluctant to share data, even anonymized or aggregated, for fear of violating user privacy. This paper introduces an approach for learning the probability of link formation from data using generative adversarial neural networks. In our generative adversarial network (GAN) paradigm, o...

Many interesting real-world systems are represented as complex networks with multiple types of interactions and complicated dependency structures between layers. These interactions can be encoded as having a valence with positive links marking interactions such as trust and friendship and negative links denoting distrust or hostility. Extracting in...

This book compiles the most visionary papers from 10 workshops held at the International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017, held in Sao Paulo, Brazil, in May 2017. The 15 full papers presented in this volume were carefully reviewed and selected for inclusion in this volume. They deal with novel ideas proposing a ch...

This book features a selection of best papers from 13 workshops held at the International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017, held in Sao Paulo, Brazil, in May 2017. The 17 full papers presented in this volume were carefully reviewed and selected for inclusion in this volume. They cover specific topics, both theoret...

This report summarizes the 39 workshops held as part of the 2016 International Joint Conference on Artificial Intelligence, held in New York from July 9-11.

Networks extracted from social media platforms frequently include multiple types of links that dynamically change over time; these links can be used to represent dyadic interactions such as economic transactions, communications, and shared activities. Organizing this data into a dynamic multiplex network, where each layer is composed of a single ed...

Networks extracted from social media platforms frequently include multiple types of links that dynamically change over time; these links can be used to represent dyadic interactions such as economic transactions, communications, and shared activities. Organizing this data into a dynamic multiplex network, where each layer is composed of a single ed...

Most real-world social networks are inherently dynamic, composed of communities that are constantly changing in membership. To track these evolving communities, we need dynamic community detection techniques. This article evaluates the performance of a set of game theoretic approaches for identifying communities in dynamic networks. Our method, D-G...

Reinforcement learning (RL) is a popular choice for solving robotic control problems. However, applying RL techniques to controlling humanoid robots with high degrees of freedom remains problematic due to the difficulty of acquiring sufficient training data. The problem is compounded by the fact that most real-world problems involve continuous stat...

The aim of link prediction is to forecast connections that are most likely to occur in the future, based on examples of previously observed links. A key insight is that it is useful to explicitly model network dynamics, how frequently links are created or destroyed when doing link prediction. In this paper, we introduce a new supervised link predic...

This editorial to the summer 2015 AI Magazine introduces the special-issue articles on architectures for activity recognition and context-aware computing.