Arnav Jhala
Computer Science
Associate Professor
Computer Science
402 Venture IV
919.513.6698 ahjhala@ncsu.edu WebsiteBio
Arnav Jhala is an Associate Professor in the Department of Computer Science at NC State University. He joined the faculty in 2016 as part of the Chancellor’s Faculty Excellence Program cluster in Visual Narrative and serves as co-director of the Digital Games Research Initiative.
Before joining NC State, Jhala was a founding faculty member in the Department of Computational Media at UC Santa Cruz. He has held positions at the USC Institute for Creative Technologies, Duke TIP, Virtual Heroes Inc. and the Indian Space Research Organization’s Space Applications Center.
Education
Ph.D. Computer Science NC State University 2009
M.S. Computer Science NC State University 2004
B.Eng Computer Engineering Gujarat University 2001
Area(s) of Expertise
Jhala’s research focuses on computational methods for representing and mediating human interpretation and communication of narrative in interactive visual media, including film and games. His group develops symbolic and probabilistic models for visual discourse and applies generative techniques to support automated and collaborative creation of visual narratives. His past projects include games for exploring aesthetic preferences, studying expert gameplay and modeling gestural aesthetics in dance.
Publications
- A Digital Program to Promote Sexual Communication Between Early Adolescents and Parents: Development and Acceptability Testing Results , The Journal of Sex Research (2025)
- Abstract 2353 Using Immersive Technologies to Teach Technical Skills in Biotechnology , Journal of Biological Chemistry (2025)
- Action-Dependent Optimality-Preserving Reward Shaping , (2025)
- GameTileNet: A Semantic Dataset for Low-Resolution Game Art in Procedural Content Generation , Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2025)
- Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors , Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (2025)
- Abstract 1497 Development and Evaluation of an Immersive and Interactive Virtual Cell Culture Training for Accessible Biotechnology , Journal of Biological Chemistry (2024)
- Student experiences with a molecular biotechnology course containing an interactive 3D immersive simulation and its impact on motivational beliefs , PLoS ONE (2024)
- Developing a Construction Domain–Specific Artificial Intelligence Language Model for NCDOT’s CLEAR Program to Promote Organizational Innovation and Institutional Knowledge , Journal of Computing in Civil Engineering (2023)
- A Digital Communication Twin for Addressing Misinformation: Vision, Challenges, Opportunities , IEEE Internet Computing (2022)
- Characterizing the perception of urban spaces from visual analytics of street-level imagery , AI & Society (2022)
Grants
Computers are increasingly being used to simulate and analyze complex social phenomena, but do not account geographical, cultural, economic, and sociopolitical systems that influence social relationships. We identify the need to account for real-world, localized information in social simulation. Our research objectives are to create computational models of social influence and opinion change that support believable social simulation and facilitate novel insights for experts through scaffolded interaction. This project, if successful, will contribute fundamental advances in computational social science, including advances individually in both computer science and social science as well as bidirectional exchange of ideas across disciplines.
This proposal includes scope to study the use of gamified modalities of curriculum for education and training in acquisition methods and simulation tools for the defense workforce.
The North Carolina Department of Transportation (NCDOT) created a new knowledge repository called Communicate Lessons, Exchange Advice, Record (CLEAR) as an official platform to store and retrieve knowledge. We will transfer a construction domain language model to improve the search capabilities of CLEAR database. A construction language inference model has already been developed as a prototype that can make meaningful connections between lessons learned and best practices within the construction domain vocabulary. A proof of concept will be validated by project managers on a set of pre-selected projects by the NCDOT Value Management Office.
1) Literature review of gamification of training, particularly in business or procurement fields. 2) Identify industry contacts that were used for interviews or focus groups to inform phase I products (organization names, points of contact, email and phone numbers) 3) Develop an attribute map of ideal game attributes for acquisition training based on stakeholder and expert interviews (in coordination with NPS MBA team) (link: https://executiveeducation.wharton.upenn.edu/thought-leadership/wharton-at-work/2012/07/attribute-map-2/#:~:text=An%20Attribute%20Map%20is%20a,position%20with%20respect%20to%20competitors.) 4) Identify other game features or design considerations gathered through stakeholder interviews or expert interviews. 5) Develop case vignettes of games being used in commercial or public business training to date. 6) Provide user feedback from MBA students playing the game prototype developed at NPS (will be provided to MBA students as an executable file). 7) Complete IRB preparation required for future Phase II experiments at NC State. 8) Finalize contact list and short capabilities statement for potential commercial partners for future game development at NC State.
transVRse is an automatic viewpoint computation and navigation support toolkit in VR. The current version is being used for the analysis of para-hydrogen pathways in dynamic molecular simulations by the Ab Inito Materials Simulations Group at Duke and Hyperpolarization Lab at NCSU.
We are interested in projects that will develop and demonstrate methods and tools to identify data relevant to a given analytic question within diverse and potentially large data sets. The process of finding the ����������������right��������������� data to support an analysis could potentially introduce significant errors and biases, and so methods and tools for data triage must be characterized in a way that makes clear their appropriate use in rigorous analytic processes. Finally, data increasingly must be discovered within less traditional formats, such as audio or speech recordings or video, that challenge more common triage and search techniques.
This project seeks to create an intelligent monitoring and visualization framework for communication across different groups involved in design, development, and release of hardware and software products within Lenovo.