AAAI 2023 Fall Symposium Series

October 25-27, 2023 | Westin Arlington Gateway | Arlington, VA, USA

Sponsored by the Association for the Advancement of Artificial Intelligence 

The Association for the Advancement of Artificial Intelligence is pleased to present the 2023 Fall Symposium Series, to be held at the Westin Arlington Gateway in Arlington, Virginia, October 25-27, 2023. 

Symposia generally range from 40–75 participants each. Participation was open to active participants as well as other interested individuals on a first-come, first-served basis. Each participant was expected to attend a single symposium. 

The program included the following seven symposia: 

• Agent teaming in mixed-motive situations 
• Artificial Intelligence and Climate: The Role of AI in a Climate-Smart Sustainable Future 
• Artificial Intelligence for Human-Robot Interaction (AI-HRI) 
• Assured and Trustworthy Human-centered AI (ATHAI) 
• Integration of Cognitive Architectures and Generative Models 
• Second Symposium on Survival Prediction: Algorithms, Challenges, and Applications (SPACA) 
• Unifying Representations for Robot Application Development 

AAAI Code of Conduct for Events and Conferences 

All persons, organizations and entities that attend AAAI conferences and events are subject to the standards of conduct set forth on the AAAI Code of Conduct for Events and Conferences. 

Registration and General Information 

Registration is Closed

Registration Fees

The conference registration fee includes admission to one symposium, access to the electronic proceedings, coffee breaks, and the opening reception.  

Refund Requests

The deadline for refund requests is September 29, 2023. All refund requests must be made in writing to fssreg@aaai.org. A $50.00 processing fee will be assessed for all refunds.

Fee Schedule 

Member: $395.00 
Nonmember: $560.00 
Student Member: $225.00 
Nonmember student: $335.00 

AAAI Silver Registration 

(Includes 1 years of AAAI membership, plus the conference registration fee)  
Regular One-Year: $540.00 
Regular 3-Year: $830.00 
Regular 5-Year: $1,120.00 
Student (One-Year): $300.00 

Visa Information 

Letters of invitation can be requested by accepted FSS-23 authors or registrants with a completed registration with payment. You can access the visa letter form via the link in your registration confirmation email.

Hotel Information 

Our hotel block has sold out. If you are planning on attending the conference and have not secured a hotel reservation, search for hotel availability via our trusted partner aRes Travel.
Book online or call 1-800-559-3186 for assistance | International callers 1-619-546-5773
aRes Travel is a third-party travel planner. Rates, deposits, and cancellation policies may vary and are the responsibility of the guest. Questions on hotel policies or payments made on aRes website should be directed to the aRes Reservation Center or to the hotel directly.

For your convenience, AAAI has reserved a block of rooms at the Westin Arlington Gateway. The Westin Arlington Gateway is located in the Ballston area of Arlington. It is a short walk from the Ballston Metro Station, which allows guests to easily explore Arlington, downtown Washington, DC, Alexandria, or Georgetown. Reagan National Airport is easily accessible via the Washington Metro rapid transit.

The conference room rate per night is $209.00 (King/Double).  

Rates do not include applicable state and local taxes (approximately 13.25%), or hotel fees in effect at the time of the meeting. Symposium attendees must contact the Westin Arlington Gateway directly. Please request the group rate for the Association for the Advancement of Artificial Intelligence (AAAI) when reserving your room. The cut-off date for reservations is October 6, 2023 at 5:00 PM ET, local time at the hotel. Reservations after this date will be accepted based on availability at the hotel’s prevailing rate. All reservations must be secured by one night’s deposit per room, via credit card. Reservations may be cancelled with no penalty up to 5:00 pm, 72 hours prior to the date of arrival. After that time, a penalty of one night’s room and tax will be incurred. Upon check-in, date of departure must be confirmed. Early departure will result in a fee equal to one night’s guest room rate.  

Westin Arlington Gateway 
801 North Glebe Road,
Arlington, Virginia 22203 USA 

Transportation to the Hotel 

For complete transportation information and directions, please see 
https://www.marriott.com/hotels/maps/travel/wasag-the-westin-arlington-gateway/ and scroll down to “Getting Here.” 
Hotel Parking: On-site parking fee is 40 USD daily 

Disclaimer 
In offering the Westin Arlington Gateway (hereinafter referred to as “Supplier”), and all other service providers for the AAAI Fall Symposium Series, the Association for the Advancement of Artificial Intelligence acts only in the capacity of agent for the Supplier, which is the provider of hotel rooms and transportation. Because the Association for the Advancement of Artificial Intelligence has no control over the personnel, equipment or operations of providers of accommodations or other services included as part of the Symposium program, AAAI assumes no responsibility for and will not be liable for any personal delay, inconveniences or other damage suffered by symposium participants which may arise by reason of (1) any wrongful or negligent acts or omissions on the part of any Supplier or its employees, (2) any defect in or failure of any vehicle, equipment or instrumentality owned, operated or otherwise used by any Supplier, or (3) any wrongful or negligent acts or omissions on the part of any other party not under the control, direct or otherwise, of AAAI. 

Submission Requirements 

Interested individuals should submit a paper or abstract by the deadline listed below, unless otherwise indicated by the symposium organizers on their supplemental website. Please submit your submissions directly to the individual symposium according to their directions. Do not mail submissions to AAAI. See the appropriate section in each symposium description for specific submission requirements. 

Submission Site 

Most symposium organizers have elected to accept submissions via EasyChair. Please be sure to select the appropriate symposium when submitting your work. For those not using EasyChair, please see the individual symposia for submission site details. 

Important Dates 

• By Aug 18: AAAI opens registration for Fall Symposium Series 
• July 21 (unless otherwise noted): Papers due to organizers 
• August 18 (unless otherwise noted): Organizers send notifications to authors 
• September 1 (recommended): Fall Symposium Series final papers due to organizers 
• September 29: Registration deadline 

Onsite Registration Schedule 

When you arrive at the Westin Arlington Gateway, please check in at the registration area for your badge. Registration hours will be: 

General Event Schedule 
Each Symposium schedule may vary 

Additional Information: 

Inquiries concerning the symposia may be directed to the symposium co-chairs at FSSChairs@aaai.org 

Fall Symposium Series-23 Co-Chairs 

• Christopher Geib (SIFT, USA)    
• Ron Petrick (Heriot-Watt University, UK) 

General inquiries regarding the symposium series should be directed to AAAI at fssreg@aaai.org 

---

Agent Teaming in Mixed-Motive Situations 

This symposium focuses on agent teaming in mixed-motive situations that arise naturally when agents have different goals, incentives, and decision-making processes. In this symposium, we consider an “agent” to be either a goal-directed computational agent, whether embodied or not, or a human. Agents may be tempted to prioritize their individual interests over the long-term success of the group, leading to competition, cooperation, coordination, or indifference toward other agents. To navigate these dynamics, agents need to understand the goals and intentions of others, identify potential allies or adversaries, align their values with others, and carefully manage information sharing with other agents. Additionally, when humans and computational AI agents collaborate in mixed teams, additional complexities arise, including issues of language comprehension, decision-making transparency, and social cue interpretation. 

This symposium emphasizes the key challenges in agent teaming within mixed-motive situations: How should agents take actions, given that actions reveal information to allies, adversaries, and other agents? How can agents take actions for goal/intention alignment? How can agents identify allies, adversaries, or other agents and model sub teams? What kinds of representations best enable mixed-motive interactions? How can agents assess the intent and proficiency of other agents? How can agents assess the degree of cooperation by other agents? How should agents communicate with allies, adversaries, or other agents? 

Topics 

The symposium invites submissions related (but not limited) to the following topics in mixed-motive situations involving computational AI agents (AI-AI/human-AI interactions). 

• Strategies for proficiency communication with allies, adversaries, or other agents 
• Strategies for controlled deception (hiding information from adversaries but sharing information with allies) 
• Methods for goal alignment through goal and intention communication 
• Strategies for negotiation and consensus 
• Assessment of proficiency of self and other agents 
• Assessment of goals, intentions of self, and other agents 
• Identification of allies, adversaries, or other agents 
• Identification and modeling of subteams and subteam goals/intentions 
• Metrics for assessment of proficiency, degree of cooperation, and other related team measures 

Symposium Format 

The symposium will include invited keynote talks, panels, breakout discussions, accepted papers talks, and a poster session. 

Submission 

Regular papers (6 pages + references), Position papers (2 pages + references), and Summary of previously published papers (2 pages) in standard double-column AAAI Proceedings Style via the AAAI submission site. For those interested, accepted papers will be published by AAAI as part of the AAAI Fall Symposium Series. 

Important dates (tentative) 

• Paper submission deadline: August 17, 2023 
• Paper notifications: August 30, 2023 
• Camera-ready submission: September 15, 2023 

Organizing Committee 

• Suresh Kumaar Jayaraman (Carnegie Mellon University), sureshkj@andrew.cmu.edu
• Jacob Crandall (Brigham Young University), 
• Jiaoyang Li (Carnegie Mellon University), 
• Gordon Briggs (Naval Research Laboratory), 
• Aaron Steinfeld (Carnegie Mellon University), 
• Michael A. Goodrich (Brigham Young University), 
• Reid Simmons (Carnegie Mellon University), 
• Holly Yanco (University of Massachusetts Lowell). 

 For More Information  

More information on the symposium can be found: https://successmuri.org/workshops/fss23/  

Artificial Intelligence and Climate: The Role of AI in a Climate-Smart Sustainable Future 

Climate change is one of the most pressing challenges of our time, posing an existential threat to civilization and the planet. Artificial Intelligence (AI) can and, when appropriate, must play a key role in accelerating the transition to a low-carbon economy in order to stave off the risk of catastrophic warming. Recent advances in AI should be harnessed in order to increase the scale and speed at which low-carbon technologies are developed and deployed. AI can also help civilization to adapt to a warming planet and provide a greater understanding of climate science and climate impacts including floods, droughts, wildfires, negative effects on agriculture, extreme wind and temperature fluctuations, and their effect on society. At the same time, AI is a multi-purpose tool, which means it has the potential to accelerate many applications that increase greenhouse gas emissions, as well as having a carbon footprint itself.

We hope the symposium will provide a forum to present novel AI use-cases, technical advances in the state-of-the-art, approaches and lessons learned from current implementations, and broader policy and governance frameworks. The forum will invite participation from academia, industry, government, and civil society to better understand how different sectors can work together to overcome the challenges faced when using AI to address climate challenges.

Topics include:

• Mitigation (e.g., AI to accelerate decarbonization of the main greenhouse gas emitting sectors)
• Adaptation (e.g., AI to better predict and respond to climate hazards)
• Climate Science (e.g., AI for improving or augmenting Earth system models)
• Cross-cutting Issues (e.g.,Ai for climate finance, ethics, governance )
• AI’s Impact on Climate (e.g., Assessing AI’s carbon footprint and benefits)

See an extended list of potential topics on our website: https://www.climatechange.ai/events/aaaifss2023

Symposium Format

The symposium will include keynote talks, panels, presentations of contributed work, poster sessions, and discussion sessions.

Submissions

We are accepting paper submissions for position, review, or research articles in two formats: (a) short papers (2-4 pages) and (b) full papers (6-8 pages). All submissions will undergo peer review and authors will have the option to publish their work in an open access proceedings site. Papers can be submitted through the AAAI Fall 2023 Symposia EasyChair site: https://easychair.org/my/conference?conf=230 (track: “Artificial Intelligence and Climate: The Role of AI in a Climate-Smart Sustainable Future”)

Submissions due 29 July, 2023.

Supplemental Website

See the following website for full details on submitting your paper.
https://www.climatechange.ai/events/aaaifss2023

Organizing Committee

Utkarsha Agwan (UC Berkeley), Feras A. Batarseh (Virginia Tech), Dr. Thomas Brunschwiler (IBM Research Europe – Zurich), Priya L. Donti (MIT) – Co-Chair , Christoph Funk (Centre for International Development and Environmental Research (ZEU)), Melissa Hatton (Capgemini Government Solutions) – Co-Chair, Srinivasan Keshav (University of Cambridge), Alice Lépissier (Brown University), Marina Lesse (Energy Academic Group, Naval Postgraduate School), Peetak Mitra ( Excarta), Jorge Montalvo (Centrica), Sebastian Ruf (Intercontinental Exchange (ICE)), Jim Spohrer (ISSIP), Frank Stein (Virginia Tech) – Co-Chair, Gege Wen (Stanford), Andrew Williams (Mila – Quebec Artificial Intelligence Institute), Ziyi Yin (Georgia Institute of Technology)

For More Information

Contact: climatechange.aaaifss2023@gmail.com
Website: https://www.climatechange.ai/events/aaaifss2023

Artificial Intelligence for Human-Robot Interaction (AI-HRI)

Since 2014, the Artificial Intelligence for Human-Robot Interaction (AI-HRI) symposium has been a successful venue for discussion and collaboration on the topic of AI applied to HRI, exploring diverse challenges and impacting communities spanning academia, industry, and government across the globe. In celebration of its 10th anniversary, we are reflecting on the achievements of the community as we transition to a new venue and spiritual successor, Technological Advances in Human-Robot Interaction (TAHRI).  We invite all contributions related to any topic on the intersection of AI and HRI, and welcome new researchers who wish to take part in this thriving and growing community. 

Topics

Format of Symposium

This year’s symposium will focus on the accomplishments in the field of AI-HRI as well as look to its future challenges, ranging from research directions to establishing an ongoing collaborative community. We invite symposium participants to present their own work as it contributes to understanding what matters towards these goals, though all research on AI-HRI will be considered.  
We will continue to include AI-HRI’s signature community-building efforts into the schedule, including paper presentations, poster sessions, and breakout group discussions. These are ideal within the symposium community, which is small enough that we can all learn each other’s names and faces, but large enough to draw an audience of people who have a real impact in our field. The discussions give perfect opportunities for new researchers to meet senior members in a more informal setting and to become more involved in future interactions and collaborations within the community. 

Submission Requirements 

Submissions should be 2-4 pages (not including references), introducing work that will receive feedback to prepare a follow-up submission to TAHRI. Please see the AAAI Author Kit (https://www.aaai.org/Publications/Templates/AuthorKit23.zip) for paper templates to ensure that your submission has the proper formatting, and please see the website for more details. Submit to: https://easychair.org/conferences/?conf=fss230 

Symposium Organizing Committee 

•     Richard G. Freedman (SIFT, USA) 
•     Emmanuel Senft (Idiap Research Institute, Switzerland) 
•     Muneeb I. Ahmad (Swansea University, UK) 
•     Zhao Han (Colorado School of Mines, USA) 
•     Justin W. Hart (University of Texas at Austin, USA) 
•     Ifrah Idrees (Brown University, USA) 
•     ‪Daniel Hernández García (Heriot-Watt University, UK) 
•     Ross Mead (Semio, USA) 
•     Jason R. Wilson (Franklin & Marshall College, USA) 

Main Contact: ai4hri@gmail.com 

 For More Information  

For more information please visit: https://ai-hri.github.io 

Assured and Trustworthy Human-centered AI (ATHAI) 

Artificial intelligence (AI) has emerged as a promising technology with the potential to transform multiple domains. However, the use of AI also poses significant risks and challenges that need to be addressed. To mitigate these risks, it is critical to ensure that AI systems are designed to operate safely, effectively, and reliably. Additionally, it is crucial to perform comprehensive test and evaluation (T&E) of these systems at multiple stages before deployment to identify and address any potential vulnerabilities or flaws.

This symposium will bring together stakeholders from industry, academia, and government to address the use of AI in different domains. Through a combination of keynote talks, interactive panel discussions, and poster sessions, we aim to define key technical terms and identify methods and best practices for ensuring the safety and effectiveness of assured AI. By establishing a common understanding of these concepts, the symposium will help to promote successful adoption and integration of assured AI principles to enable development of more robust and reliable systems.

Topics of interest (may include, but are not limited to):

• Methods and tools for assurance of AI
  • Hazard and risk identification and management
  • Human-AI interaction and other human factors
  • Scalability and interoperability of tools
  • Robustness, reliability, and traceability
  • Explainability, transparency, and bias
• AI for assurance in high-risk applications
  • Cybersecurity
  • Healthcare
  • Robotics
  • Autonomous Vehicles
• Assurance of emerging technologies (e.g. large foundation models)
• AI assurance implications for development of policy and regulatory strategies
• Technology transition to accelerate current needs for AI assurance

Format

The symposium will consist of a combination of invited keynote speakers, interactive panel discussions (along with audience Q&A), and poster sessions.

Submissions

Please submit extended poster abstracts (up to 2 pages, excluding references) on new research, preliminary results, or summaries of previous work via the EasyChair submission website. Accepted abstracts will be presented as lightning talks and posters.

Organizing Committee

Brian Hu, Kitware, Inc. (brian.hu@kitware.com)
Heather Frase, Center for Security and Emerging Technology (heather.frase@georgetown.edu)
Brian Jalaian, University of West Florida (bjalaian@uwf.edu)
Farshid Alambeigi, University of Texas at Austin (farshid.alambeigi@austin.utexas.edu)
S. Farokh Atashzar, New York University (f.atashzar@nyu.edu)
Ariel Kapusta, The MITRE Corporation (akapusta@mitre.org)
Patrick Minot, The MITRE Corporation (pminot@mitre.org)
Jie Ying Wu, Vanderbilt University (JieYing.Wu@vanderbilt.edu)

For More Information

Please see the symposium website.

Integration of Cognitive Architectures and Generative Models 

The purpose of this symposium is to explore possible integrations of cognitive architectures and generative models, two very different approaches for developing general embodied intelligent agents with possibly complementary strengths and weaknesses. An important goal is to understand the strengths, weaknesses, tradeoffs, and challenges among alternative approaches to integration, as well as potential directions for future research. We hope to include a broad range of researchers whose interests span cognitive architectures and generative models.  

 Topics (but are not limited to):  

1. Existing and hypothetical integrations of generative models as components of existing cognitive architectures.  
2. Novel architectures built with generative model components.  
3. Proposed integrations of underlying generative model technologies with cognitive architectures.   
4. Explorations/analyses of novel approaches to achieving specific cognitive capabilities (possibly as components of a cognitive architecture) using generative models, such as decision-making, planning, meta-cognition, episodic memory, online learning, grounding, and mental imagery.  
5. Applications of cognitive architectures to inform and guide multi-task training and learning from human feedback in generative models.   

Format

Sessions will be organized into topic areas based on interest as determined by submissions. Each session will include selected presentations of submitted papers, group discussions, and possibly a keynote speaker. The final session on the first day will be a poster session available to all authors of accepted papers. The morning session on the third day will be a chance to reflect on and discuss future directions.  

 Submissions

Authors may submit papers that are 2-8 pages long. These papers will be made available to attendees before the symposium and will be used by the organizing committee to decide on session topics and presentations. Authors of accepted papers that are not presented will be invited to participate in a poster session in the final session of the first day. In choosing presenters, our bias will be toward papers that engage one of the topics described above or other topics related to the integration of generative models and cognitive architectures.   

 See the AAAI Author Kit to ensure that your submission has the proper formatting.  

  Please submit papers to: https://easychair.org/my/conference?conf=fss230

 Organizing Committee   

• John Laird, Center for Integrated Cognition/IQMRI, john.laird@cic.iqmri.org  
• Christian Lebiere, Carnegie Mellon University, cl@cmu.edu  
• David Reitter, Google Deepmind, reitter@google.com   
• Paul S. Rosenbloom, University of Southern California, rosenbloom@usc.edu  
• Andrea Stocco, University of Washington, stocco@uw.edu  

 For More Information  

https://integratedcognition.ai/fss-2023

Second Symposium on Survival Prediction: Algorithms, Challenges, and Applications (SPACA) 

Survival analysis attempts to estimate the time until a specified event (eg, death of a patient) occurs, or some related survival measures, and is widely applicable for survival prediction and risk factor analysis. A key challenge in learning effective survival models is that this time-to-event data is subject to “censoring’’ so that the time to event is only known up to a bound for such instances. We seek contributions from researchers from diverse fields including machine learning, healthcare, medicine, finance and engineering. We anticipate this will foster interdisciplinary collaborations and will catalyze the development of the next generation of the survival prediction algorithms.  

Topics  

This symposium will focus on the following themes, covering four aspects of survival prediction tasks. Examples of topics of interest in each theme are provided.    

Format of Symposium  

The symposium will feature invited talks, paper and poster presentations, followed by discussion group sessions to explore open challenges and future directions in development of algorithms for survival prediction and their real-world adoption in various application domains.  

Submission Requirements  

Interested participants should submit either extended abstracts for the poster sessions (4 pages maximum) or full papers (6 pages maximum, excluding references) for position, review and work-in-progress pieces. We will also consider papers that include results that have already been published (with appropriate acknowledgement). 

Submissions should be formatted according to the AAAI template and submitted through the AAAI Fall Symposium Series EasyChair site. Authors of accepted papers may choose to have their paper included in the archival proceedings published by AAAI. This is optional—accepted papers where authors do not opt in for the proceedings will be published on the symposium website and will not be considered archival for resubmission purposes.  

Symposium Organizing Committee  

• Prof. Kevin S. Xu (main contact)  Case Western Reserve University , ksx2@case.edu  10900 Euclid Ave., Cleveland, OH 44106-7071, USA  Phone: (216) 368-0397      
• Prof. Russ Greiner , University of Alberta  rgreiner@ualberta.ca  
•  Prof. George H. Chen , Carnegie Mellon University , georgechen@cmu.edu   
• Dr. Weijing Tang , Harvard University , wtang.stat@gmail.com  
• Dr. Chirag Nagpal , Google Research , chiragn@cs.cmu.com  

Symposium URL  

https://sites.google.com/view/spaca-2023/home

Unifying Representations for Robot Application Development 

Behind any robot task or interaction is a representation that should (a) enable sufficient contextualization; (b) support any existing predefined, learned, and/or reusable skills onboard the robot; (c) be verifiable at design time and behave consistently at run-time; and (d) can be tested, executed, and modified for reuse on a variety of different robot morphologies. Enabling end users to express their intent within different representations has long played a pivotal role in robot application development, i.e., the construction of robot services, social interactions, and/or collaborative tasks.

The problem is that there is a lack of consistency and uniformity in how these representations are selected and used between robotics researchers. Thus, end users (i.e., robot application developers) face a myriad of challenges owing to this lack of cohesion.

The goals of the symposium will therefore be to (a) categorize current representational trends for robot application development, (b) discuss best practices for future adoption of languages, logical representations, development frameworks, etc. that integrate advances from the wider AI community, and (c) identify opportunities for collaboration between academia and industry.

Themes

•  Representations for robot applications, covering existing representations (e.g., finite state machines, behavior trees, etc.) or new, proposed representations.
• Standardization of representations and robot application development. This theme covers where/how to apply representations, how representations can further standardization, tools and techniques for standardization, and avenues for standardization between academia and industry.
• Application development (i.e., end-user development) interfaces, covering topics such as robot programming paradigms, programming interfaces, and debugging and runtime.
• Computational techniques made possible by specific representations, covering AI planning, formal methods, and machine learning for robotics.

Contributions

We welcome the following contribution types:

• Regular Research Papers (4-6 pages, AAAI format) describing robotics work related to any of the themes above.
• Artifact Papers (4-6 pages, AAAI format) describing artifacts (e.g., software tools or libraries) related to any of the themes above.
• Position Papers (2-4 pages, AAAI format), directly discussing themes outlined above.

Submissions should be made through EasyChair: https://easychair.org/my/conference?conf=fss230

Organizing Committee

David Porfirio (primary contact), U.S. Naval Research Laboratory, david.porfirio.ctr@nrl.navy.mil
Ross Mead, Semio
Laura M. Hiatt, U.S. Naval Research Laboratory
Mark Roberts, U.S. Naval Research Laboratory
Amin Atrash, Amazon Lab 126
Nick DePalma, Independent Researcher
Ruchen Wen, University of Maryland, Baltimore County

Laura Stegner, University of Wisconsin–Madison

For More Information

For more information, see the symposium website: https://sites.google.com/view/aaai-ur-rad-symposium

---

Sponsored by: