IWAI 2024

5th International Workshop
on Active Inference

9-11 September 2024 in Oxford, UK

Thank you all for making IWAI 2024 a great success! We hope to see you all again next year.

Also congratulations to the award winners:

Best Poster: David Hyland and Tomáš Gavenčiak
Toward a Game-Theoretic Foundation of Multi-Agent Active Inference

Best Presentation: Wouter W. L. Nuijten
Reactive Environments for Active Inference Agents with RxEnvironments.jl

Best Paper: Candice Pattisapu
Free Energy in a Circumplex Model of Emotions

The 5th International Workshop on Active Inference wants to bring together researchers on active inference as well as related research fields in order to discuss current trends, novel results and real-world applications. We have an interest in exploring the extent to which active inference can be used in modern machine learning settings, such as in hybrid setups combining it with deep learning, as well as to unify the latest psychological and neurological insights, and to determine how it can best be used to understand action, optimization and decision making.

Registration

Please register here. The registration will close at September 2nd. The registration fee includes coffee breaks, lunch (Mon, Tue, Wed), and dinner (Mon, Tue).


We also have discounted accommodation available for you to book (£75/night; with breakfast; ensuite bathrooms) at the conference venue. Update: Note that all rooms with ensuite bathrooms have been taken. We have now added rooms with shared bathroom facilities (£70/night; with breakfast). The rooms are arranged in corridors, with 6-10 rooms per floor and a ratio of 6 rooms to 1 bathroom. Bathrooms will be cleaned daily. This will be a unique opportunity to reside in an Oxford college accommodation. Also note that accommodation can be very hard to find during the summer due to tourism and other conferences occurring at the same time. Please note that you will have to make the booking before 16th August. To book, click here.

Programme

The workshop will take place September 9-11th. Find below the overview of the programme. The full workshop programme will be announced later.

Responsive image


Invited Speakers

Responsive image

Prof. Karl Friston

Wellcome Centre for Human Neuroimaging. University College London.


Responsive image

Prof. Ingmar Posner

Oxford Robotics Institute, Oxford University.


Responsive image

Dr. Emma Holmes

Department of Speech Hearing and Phonetic Sciences. University College London.


Responsive image

Prof. Chris Buckley

Department of Informatics. University of Sussex.


Responsive image

Prof. Rafal Bogacz

MRC Brain Network Dynamics Unit at the University of Oxford.


Responsive image

Prof. Pablo Lanillos

Donders Institute for Brain, Cognition and Behaviour, Radboud University.
Cajal International Center for Neuroscience, Spanish Research Council.


Accepted papers

Modeling Sustainability under Active Inference through resource management
Mahault Albarracin, Ines Hipolito, Maria Raffa, Paul Kinghorn

Contextuality, Cognitive engagement, and Active Inference
Avel Guénin Carlut

Reducing Intuitive-Physics Prediction Error through Playing
Olivier L. Georgeon, Béatrice de Montéra, Paul Robertson

Selection of Exploratory or Goal-Directed Behavior by a Physical Robot Implementing Deep Active Inference
Ko Igari, Kentaro Fujii, Gabriel W. Haddon-Hill, Shingo Murata

Towards Interaction Design with Active Inference: A Case Study on Noisy Ordinal Selection
Sebastian Stein, John H. Williamson, Roderick Murray-Smith

Online Structure Learning with Dirichlet Processes through Message Passing
Bart van Erp, Wouter W. L. Nuijten, Bert de Vries

Reactive Environments for Active Inference Agents with RxEnvironments.jl
Wouter W. L. Nuijten, Bert de Vries

Message Passing-based Bayesian Control of a Cart-Pole System
Sepideh Adamiat, Wouter M. Kouw, Bart van Erp, Bert de Vries

Belief sharing: a blessing or a curse
Ozan Catal, Toon Van de Maele, Riddhi J. Pitliya, Candice Pattisapu, Mahault Albarracin, Tim Verbelen

Exploring and Learning Structure: Active Inference Approach in Navigational Agents
Daria de Tinguy, Tim Verbelen, Bart Dhoedt

Coupled autoregressive active inference agents for control of multi-joint dynamical systems
Tim N. Nisslbeck, Wouter M. Kouw

Modelling Agency Perception in Depression Using Active Inference: A Multi-Agent Behavioural Study
Riddhi J. Pitliya, Robin A. Murphy

Embodied decisions, learning, and active inference
Matteo Priorelli, Ivilin Peev Stoianov, Giovanni Pezzulo

Learning in Hybrid Active Inference Models
Poppy Collis, Ryan Singh, Paul Kinghorn, Christopher Buckley

Planning to avoid ambiguous states through Gaussian approximations to non-linear sensors in active inference agents
Wouter M. Kouw

Free Energy in a Circumplex Model of Emotions
Candice Pattisapu, Tim Verbelen, Riddhi J. Pitliya, Alex B. Kiefer, Mahault Albarracin

Epistemic Value Anticipation into the Deep Active Inference Model
Nikita Fedosov

Accepted posters

Structured Active Inference
Toby St Clere Smithe

Sample as you Infer: Predictive Coding with Langevin Dynamics
Umais Zahid, Zafeirios Fountas

Deep Active Inference with Reconstructive and Contrastive Learning
Kentaro Fujii, Takuya Isomura, Shingo Murata

Intelligent Service Adaptations through Active Inference Agents
Boris Sedlak, Victor Casamayor Pujol, Praveen Kumar Donta, Schahram Dustdar

Active Vision and Neural Imprecision
Robert Peel Worden

Synaptic pruning is equivalent to online Bayesian model selection
Ukyo T. Tazawa, Takuya Isomura

Parallel Tracking of Hypotheses for Rapid Position Inference
Paul Robertson, Robert Laddaga

Active inference model of fast prism adaptation using the mixture of policy matrices
Megumi Yoshihara, Takuya Isomura

Environment-Centric Active Inference
Kanako Esaki, Tadayuki Matsumura, Takeshi Kato, Shunsuke Minusa, Yang Shao, Hiroyuki Mizuno

Reverse engineering of generative models
Takuya Isomura

Inventory Ordering Behavior in The Context Of Intermittent Demand by Active Inference
Wanshan Zhu, Mengke Xuan

Towards an active inference model of pedagogy
Francesco Balzan, Mahault Albarracin, Maurizio Gabbrielli

Blending differential flatness and active inference
Hugues Mounier

Attractors in Avian Song: A Nonlinear Approach to Understanding Complex Vocal Behaviors
Navyanth Kusampudi

Towards computationally efficient and explainable active inference
Aswin Paul, Adeel Razi

Empirical evaluation of a formal model of interpersonal inference
Ronald Sladky, Federica Riva, Claus Lamm

Active inference-based modeling of human driver collision avoidance behavior
Julian Frederik Schumann, Johan Engström, Matthew O'Kelly, Jens Kober, Arkady Zgonnikov

Autonomous Navigation under Uncertainty with Diffusion-Based Motion Prediction and Active Inference
Yufei Huang, Yulin Li, Andrea Matta, Mohsen Jafari

Towards System Identification after Distribution Shifts during Closed-Loop Control with Intermittent Active Inference
Markus Klar, Henrik Gollee, Sebastian Stein, John Williamson, Roderick Murray-Smith

Tool generation for robotics tasks using implicit representations and foundational models
Abián Torres, Ricardo Sanz, Pablo Lanillos

How precise is precision defined in computational psychiatry?
Alexander Schneider, Ronald Sladky, Ulrich S. Tran, Bianca Schuster

Sophisticated Planning with Theory of Mind
Tim Verbelen, Ozan Catal, Toon Van de Maele, Riddhi J. Pitliya, Mahault Albarracin, Candice Pattisapu

Active inference as a general framework for modeling human driving behavior
Johan Engstrom, Matthew O'Kelly, Leif Johnson, Azadeh Dinparastdjadid, Shu-Yuan Liu, Joao Messias

Thoughtseeds: Evolutionary Priors, Nested Markov Blankets and the Emergence of Cognition
Prakash Chandra Kavi, Gorka Zamora-López, Daniel Ari Friedman

Multi-Level Active Inference with ActiveInference.jl
Peter Thestrup Waade, Christoffer Lundbak Olesen, Jonathan Ehrenreich Laursen, Samuel William Nehrer, Chris Mathys

Neural Associative Skill Memories
Pranav Mahajan, Tianjin Li, Mufeng Tang, Ioannis Havoutis, Ben Seymour

A computational modeling of the Wisconsin Card Sorting Task as goal-oriented behavior via active inference
Daiki Goto, Hayato Idei

Modelling Body-ownership Illusion using Free Energy Principle and Model Selection
Filip Novicky, Ajith Anil Meera, Pablo Lanillos

Toward a Game-Theoretic Foundation of Multi-Agent Active Inference
David Hyland, Tomáš Gavenčiak, Lancelot Da Costa, Conor Heins, Vojtech Kovarik, Julian Gutierrez, Michael J. Wooldridge, Jan Kulveit

Modeling Collective Search in Human Data: A Novel Approach Based on Active Inference in Multi-Agent Systems
Julian Gullett, Zachary Fulker, Christoph Riedl

Addressing the Subsumption Thesis: A Formal Bridge between Microeconomics and Active Inference
Noé Romeo Kuhn

Predictive Minds: LLMs As Atypical Active Inference Agents
Jan Kulveit, Clem von Stengel, Roman Leventov

Behavioral Model Comparison for Reversal Learning in a Three-Armed Bandit
Alessandra Nicoletta Cruz Yu, Ryan Smith, Laura Berner, Vincenzo Fiore

Active Inference and Impact: A Mutualistic Exploration of Nonfiction Literature for Greater Life Fulfillment
Anna Pereira

Sponsors

This event is made possible with the support of




Venue

The workshop will take place at Corpus Christi College, in Oxford, UK.


Travel information

Most travel tickets to Oxford, whether it be for buses or trains, can be conveniently purchased online through Trainline. Note that there are ticket options for flexible travelling. If you're arriving in London by train at London St Pancras International Station, you can transfer to Oxford by train with typically one or two changes along the way. Tickets for these journeys can be booked via Trainline. Direct trains to Oxford depart from London Paddington and Marylebone Stations, both of which are easily accessible using the London Underground (the metro/subway system) where you can simply use contactless bank cards as tickets.

For a direct bus service from London to Oxford, you can opt for the Oxford Tube, which runs 24/7. Despite the name, it is a coach service, not to be confused with London's subway system, which is also known as the Tube. The journey by bus usually takes around 2 hours and departs from various locations, including Victoria Coach Station.

If you're flying into London via Heathrow Airport, a direct bus to Oxford is a swift option, taking approximately 1.5 hours with services like The Airline. If you prefer to travel by train, which may take longer, you'll need to journey into central London first before catching a train to Oxford. Trainline can provide you with the necessary travel routes and ticketing information. You can also reach Oxford by bus from other London airports or from cities across the UK via services such as National Express.

For travelling within Oxford, since it's a beautiful and small city that is cycling-friendly, you may walk, rent a bicycle, or use an e-scooter.

Visa for United Kingdom

Please check the UK Embassy or Consulate in your own country to check if you need a visa to come to the United Kingdom. Contact us in time if you need an invitation letter.

Call for papers

Papers on all subjects and applications of active inference and related research areas are welcome. The workshop's focus is on the technical implementation of the ideas. Consequently, topics of interest include (but are not limited to):

Important dates

Submission Deadline (Full Paper / Extended Abstract): May 31st, 2024 June 7, 2024
Acceptance Notification for the main round: July 14, 2024
Camera Ready Submission Deadline: September 2, 2024
Registration deadline: September 2, 2024
Workshop Date: September 9-11, 2024

Paper submissions

We welcome submissions of papers with up to 12 printed pages (excluding references) in LNCS format (click here for details). Submissions will be evaluated according to their originality and relevance to the workshop, and should have an abstract of maximum 250 words. Contributions should be in PDF format and submitted via OpenReview (click here).

All submitted papers will undergo a rigorous double-blind peer review process, and be selected based on originality, quality, soundness, and relevance. Submitted papers need to be anonymized with the best of efforts. It is allowed to have a (non-anonymous) online pre-print. Accepted papers will be published in the proceedings in the Springer CCIS series.

Extended abstract submissions

We also welcome submissions of extended abstracts with up to 2 printed pages (excluding references and figures) in LNCS format (click here for details). These can cover the material of a journal paper published by the author in the past 12 months, or can be an abstract of late breaking results. Contributions should be in PDF format and submitted via OpenReview (click here). Extended abstracts will not be published in the proceedings, but can be accepted as presentations or as posters to the workshop.

Organization

IWAI 2024 is made possible thanks to the following people.

Organizers

   General Chair: Tim Verbelen

   Local Organization Chair: Riddhi J. Pitliya

   Technical Program Chairs: Martijn Wisse, Ivilin Peev Stoianov

   Communication Chair: Pablo Lanillos

Organization committee

Christopher Buckley, University of Sussex, United Kingdom
Daniela Cialfi, Institute of Complex Systems (CNR); La Sapienza University of Rome, Italy
Pablo Lanillos, Donders Institute for Brain, Cognition and Behaviour, Netherlands
Riddhi J. Pitliya, Oxford University, United Kingdom
Noor Sajid, University College London, United Kingdom
Hideaki Shimazaki, Kyoto University, Japan
Ivilin Peev Stoianov, Institute of Cognitive Sciences and Technologies (ISTC), National Research Council (CNR), Italy
Tim Verbelen, VERSES, USA
Martijn Wisse, Delft University of Technology, Netherlands

Previous editions

2020 - Ghent (virtual)
2021 - Bilbao (virtual)
2022 - Grenoble
2023 - Ghent