[visionlist] Training School: Representation Mediated Multimodality (January 29 - Feb 2, 2024)

Mehul Bhatt Mehul.Bhatt at oru.se
Sat Sep 16 05:33:30 -04 2023

Call for Participation  /  EU COST Action `Multi3Generation' Training School

Training School 2024:

Representation Mediated Multimodality:
Grounded Representation, Reasoning, and Learning for Interactive Interpretation

January 29 - February 2 2024 - University of Malta, Malta.

Initiative of EU COST Action   >   Multi3Generation. https://multi3generation.eu<https://multi3generation.eu/>
Past Occurrence   >   Training School 2022. https://codesign-lab.org/school2022/

Please note:

- All participants, including selected students, will be fully-funded

- Students who participated in Training School 2022 are not eligible to re-apply


The training school on ``Representation Mediated Multimodality'' provides a consolidated perspective on the theoretical, methodological, and applied understanding of representation mediated multimodal sensemaking at the interface of language, knowledge representation and reasoning, and visuo-auditory computing. Intended purposes -addressed in the school- encompass diverse operative needs such as explainable multimodal commonsense understanding, multimodal generation/synthesis for communication, multimodal summarisation, multimodal interpretation guided decision-support, adaptation & autonomy, and analytical visualisation.

The training school particularly consolidates and presents a novel and emerging view of state-of-the-art multimodal, neurosymbolic grounding primarily through a confluence of methods in Artficial Intelligence, Computational Linguistics, Vision, Speech and their impact on interactional and communicative acts/artefacts in everyday life and specialist professional work. Here, multimodal interpretation is to be construed in the context of diverse forms of imagery, e.g., encompassing perceptual and communicative data sources such as image, video, language, audition, text, eye-tracking, neurophysiological markers in behavioural / clinical settings.

In this backdrop, the training school particularly focusses on grounded knowledge representation, reasoning, and learning (for linguistic purposes) through the following emerging research-driven themes that are of high interest:

  *   Space and Language
  *   Computational Linguistics
  *   Cognitive Linguistics
  *   Cognitive Vision
  *   Vision and Language
  *   Neurosymbolism
  *   Narrative - Discourse
  *   Computational Models of Narrative
  *   Speech and Language Technologies
  *   Human-Centred AI

The principal training school programme --consisting of keynotes, invited talks, and tutorials-- will categorically address questions such as:

  *   Explainability and transparency in multimodal models
  *   Neurosymbolism / Interaction between symbolic and sub-symbolic representations in models
  *   Commonsense knowledge representation and reasoning, and its role in multimodal models
  *   Complementarity / redundancy among data sources or modalities
  *   Situated reasoning, e.g., for language generation, decision-making

Of particular significance to the training school are themes that benefit both public and private human-centred technological services most directly affecting EU citizens in an accessible, multilingual Europe, and have strong economic and societal impacts. The training school will focus on human-machine interaction considerations in select application areas of emerging societal significance, such as autonomous systems, cognitive robotics, multi-lingual language technologies.

Location: Malta   /  University of Malta - Valetta Campus  /  Lecture Room 201

Travelling Info   /   https://www.um.edu.mt/campuses/valletta/

The school is being organised as part of the COST action Multi3Generation (https://multi3generation.eu<https://multi3generation.eu/>)

For more information on the school and programme visit: https://codesign-lab.org/school2024/<https://codesign-lab.org/school202/>


Participants are expected to primarily be doctoral candidates and research-driven students. Participants interested in obtaining a scholarship should submit an application to participate as per Application Guidelines (details below). Selected applicants will be financially supported for their participation in the school.

The Scholarship includes travel expenses and a daily allowance which covers accommodation, meals, and local travel expenses. The exact amount of the scholarship is based on the expected costs and the maximal amount for reimbursement will be communicated after acceptance.


Applications are accepted and evaluated in two rounds, with a first deadline on Oct 20 2023, and a second deadline on Dec 10 2023; after this date, new applications will only be considered if there are still places available (please note that places are limited even if a scholarship is not sought).

  *   Application to participate (with scholarship): PRESENTLY OPEN   /   Submit:  https://easychair.org/conferences/?conf=school2024
  *   Expression of interest to participate (without scholarship):   PRESENTLY OPEN   /   Email:  contact School Chair


For participation with a scholarship, the Training School is primarily (but not exclusively) aimed at early stage doctoral researchers and research-inclined students enrolled full-time in an advanced educational programme.

Eligible candidates have to comply with the COST Vademecum (https://www.cost.eu/uploads/2021/04/Vademecum-28-April-2021.pdf), i.e., they shall be affiliated to an academic institution, organisation or company which has within its remit a clear association with performing research and is from a COST Full Member, a COST Cooperating Member country, or a Near Neighbour Country (NNC) (https://www.cost.eu/about/members/).

Eligible candidates need to submit the following items in a single PDF document via Easychair:

  1.  One-page CV
  2.  Reference letter by principal research/thesis advisor, motivating the need for financial support
  3.  In max 300 words, Research Description (if already pursuing a thesis or similar), or else a Motivating Statement of Interest in the topics of the school. If applicable, also include at most two brief citations to your own most relevant peer-reviewed publications (do not cite unpublished or informal publications).
  4.  Candidates who receive a Scholarship to join the Training School are expected to participate and present their research in a doctoral colloquium during the school; further guidelines about the doctoral colloquium will be provided with the letter of acceptance.


Applicants will be selected based on personal research interest and experience relevant to the school’s theme and topics. The selection committee will do their best in terms of ensuring fair and inclusive distribution with respect to gender, geographic location.

Following acceptance, applicants will have to register via the e-COST platform and add their banking and other details in order to receive a formal invitation via e-COST and be eligible for reimbursement of costs. A requirement to be reimbursed is that accepted participants officially apply to become members of Multi3Generation (details will be provided as part of the notification).


Training School 2024 Chairs

  *   Mehul Bhatt (Örebro University, Sweden)
  *   Albert Gatt (Utrecht University, Netherlands)
  *   Adrian Muscat (University of Malta, Malta)
  *   Aykut Erdem (Koc University, Turkey)

Doctoral Colloquium Chair

  *   Jakob Suchan (Constructor University, Germany)

[Apologies for cross-postings]


Professor - School of Science and Technology
Örebro University, SWEDEN
https://mehulbhat.org<mailto:mehul.bhatt@oru.se>  /  mehul.bhatt at oru.se<mailto:mehul.bhatt at oru.se>

CoDesign Lab EU   /   Cognition. AI. Interaction. Design.
https://codesign-lab.org<mailto:mehul.bhatt@oru.se>   /   info at codesign-lab.org<mailto:info at codesign-lab.org>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20230916/0d850ce2/attachment.html>

More information about the visionlist mailing list