📢 Call for Papers

The 7th Generation and Evaluation of Non-verbal Behaviour for Embodied Agents (GENEA) Workshop
October 5, 2026 (in person)
Held in conjunction with ACM ICMI 2026, Naples, Italy
Website: https://genea-workshop.github.io/2026/workshop/

We are pleased to share the Call for Papers for the 7th edition of the GENEA Workshop, focusing on the generation and evaluation of non-verbal behaviours such as gesticulation, facial expressions, and gaze – essential components of natural interaction with embodied agents, including virtual agents and social robots.

Currently, behaviour generation is typically powered by rule-based systems, data-driven approaches like generative AI, or hybrid models. For evaluation, both objective and subjective methods are used, though their application and validity are often debated. This workshop aims to bring together researchers from diverse disciplines working on various aspects of non-verbal behaviour generation, facilitating discussion on advancing both generation techniques and evaluation methodologies.

✨ Topics of Interest

We invite original contributions on topics including (but not limited to):

• Automated synthesis of facial expressions, gestures, and gaze movements, including multimodal synthesis

• Closed-loop / end-to-end non-verbal behaviour generation (from perception to action)

• Use of LLMs/VLMs in the context of non-verbal behaviour synthesis

• New datasets, annotation methods, and analyses of existing datasets related to non-verbal behaviour

• Cross-cultural and multilingual influences on non-verbal behaviour generation

• Cognitive and affective models for non-verbal behaviour generation

• Ethical considerations and biases in non-verbal behaviour synthesis

• Subjective and objective evaluation methods for any of the above topics

📝 Submission Types

We welcome:

• Long papers (8 pages)

• Short papers (4 pages)

All submissions should follow the double-column ACM conference format. Pages containing only references do not count toward the page limit. Papers must be submitted in PDF format via OpenReview and formatted for double-blind review. To encourage authors to make their work reproducible and reward the effort that this requires, we have introduced the GENEA Workshop Reproducibility Award. 

Accepted papers will be presented at the workshop and included in the ICMI companion proceedings.

🗓️ Important Dates (End of day, Anywhere on Earth)

• Paper abstract deadline: 2 July 2026

• Full submission deadline: 3 July 2026

• Notification of acceptance: 23 July 2026

• Camera-ready deadline: 31 July 2026

• Workshop date: 5 October 2026

👥 Organisers

• Taras Kucherenko – Electronic Arts (EA), Sweden

• Alice Delbosc – Davi, The Humanizers, France

• Gustav Eje Henter – KTH Royal Institute of Technology / Motorica AB, Sweden

• Oya Celiktutan – King’s College London, United Kingdom

• Eneko Atxa Landa – University of the Basque Country, Spain

• Jieyeon Woo – Korea Institute of Machinery and Materials, South Korea

• Haoyang Du – Technological University Dublin, Ireland

For more information, visit our website, contact us at genea-contact@googlegroups.com

Artificial Intelligence (AI) has historically relied on two components: data and algorithms. However, the conventional model-centric AI paradigm has historically prioritized algorithms, often treating data as static entities. Typically, data is initially collected, pre-processed, and held fixed, with a significant portion of development efforts dedicated to optimizing learned models. This conventional approach has led to the creation of increasingly intricate and opaque models, necessitating substantial training data. In contrast, the emerging data-centric AI paradigm is dedicated to systematically and algorithmically generating optimal data to feed Machine Learning (ML) models. The primary objective of data-centric AI approaches is to consistently enhance data quality, thereby achieving a level of model accuracy that was previously considered unattainable through model-centric techniques alone. This workshop aims to explore the transformative impact of recent advancements in the data-centric AI paradigm on the future of AI and ML. It serves as a platform for in-depth discussions and the exchange of scientific contributions, recent achievements, and open challenges.

Workshop Topics
We welcome submissions that explore the opportunities, perspectives, and research directions within the data-centric AI paradigm. Potential topics include, but are not limited to:

High-quality data preparation:
– Data cleaning, denoising, and interpolation
– Novel feature engineering pipelines
– Label Errors and Confident Learning (CL) 
— Selecting features and/or instances
– Performing outlier detection and removal
– Ensuring label consensus
– Producing consistent and low-noise training data
– Extracting smart data from raw data
– Creating training datasets for small data problems
– Handling rare classes and explaining important class coverage in big data problems
– Incorporating human feedback into training datasets
– Generating high-quality synthetic data
– Combining multi-view, multi-source, multi-objective datasets

Data-centric ML and Deep Learning approaches:
– Active learning to identify the most valuable examples to label
– Core-set learning to handle big data
– Semi-supervised learning, few-shot learning, weak supervision, confident learning to take advantage of the limited amount of labels or handle label noise
– Transfer learning and self-supervised learning algorithms to achieve rich data representations to be used with scarceness of labels
– Concept drift detection and management
– Adversarial learning to improve robustness and resilience

Responsible and Ethical AI:
– Ensuring fairness, bias, ethics, and diversity
– Green AI design and evaluation
– Scalable and reliable training
– Privacy-preserving and secure learning
– Reproducibility of AI

Data benchmark creation:
– Creating licensed datasets based on public resources
– Creating high-quality data from low-quality resources

Data-centric Explainable AI:
– Novel XAI methods to identify possible data issues in the learning stage
– XAI methods to generate features for machine learning problems

Applications of novel data-centric AI solutions:
– Healthcare and Medical Applications: Ensuring data diversity and generating realistic patient data without exposing sensitive information
– Autonomous Vehicles and Smart Cities: Simulating representative scenarios for software testing
– Cybersecurity and Fraud Detection: Detecting, exploring, or generating rare/edge cases and patterns for machine learning robustness
– Manufacturing and Industrial Applications: Ensuring coverage in equipment failures for stress testing
– Facial Recognition and Biometrics: Increasing diversity in images to reduce bias
– Legal and Military Applications: Fostering data quality for fair and explainable systems

Website
https://dearing-workshop.github.io

Submission Guidelines
The CMT submission portal is open.
Direct link: https://cmt3.research.microsoft.com/ECMLPKDDWT2026/Track/28/Submission/Create

Workshop Paper Submission Deadline
05-06-2026
 
Camera Ready Submission
10-07-2026

Accepted Formats
Regular research papers with 12 to 16 pages including references.
Short research papers of at most 6 pages including references, aiming at fostering discussion and collaboration (e.g., outlining new researching ideas).

Requirements
PDF submission via Microsoft CMT.
English language, conference template required.
Springer LNCS style. Templates: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines

Organizers
Donato Malerba – University of Bari Aldo Moro, Italy
Vincenzo Pasquadibisceglie – University of Bari Aldo Moro, Italy
Mara Sangiovanni – University Federico II of Naples, Italy
Miriam Seoane Santos – University of Porto, Portugal
Ricardo Cardoso Pereira – University of Coimbra, Portugal