PhD Position in Semantics-Aware Modeling: The ENACT AI Cluster is offering a PhD position focused on the semantics-aware modeling and generation of co-verbal gestures using multimodal language models. This research initiative is part of the ANR project Syncogest, aiming to enhance the interaction of Embodied Conversational Agents (ECAs) with humans.
PhD Position in Semantics-Aware Modeling and Generation of Co-Verbal Gestures
Designation
PhD Position
Table
| Attribute | Details |
|---|---|
| Research Area | Language, Speech, Audio, and Multimodal Learning |
| Location | Villers lès Nancy, France |
| Contract Type | Fixed-term (3 years) |
| Remuneration | €2300 gross/month |
| Start Date | October 1, 2026 |
| Application Deadline | February 28, 2026 |
Eligibility/Qualification
- Required:
- Master’s degree in Computer Science, AI, Data Science, or a closely related field.
- Strong Python programming skills and experience with machine learning frameworks.
- Solid foundations in machine and deep learning.
- Ability to read and critically analyze scientific literature in English.
Description
This PhD project is anchored in the ANR SYNCOGEST initiative. Researchers will explore the intersection of multimodal communication, developing methodologies for semantic annotation, gesture prediction, and controlled gesture generation.
Main Research Axes
- Semantic Annotation Augmented by MLLM: Automate the annotation of the SYNCOGEST corpus using multimodal language models.
- Predicting Expertise from Perceptual to Semantic: Develop a model to map naive gesture descriptions to expert-level labels.
- Semantically Controlled Generation: Integrate semantic representations into gesture generation models for improved accuracy.
How to Apply
Interested candidates should submit their applications online through the Inria website. Ensure to provide a valid email address to save your application.
Last Date to Apply
February 28, 2026
For more information, potential applicants can contact the PhD Supervisor, Ouni Slim, at slim.ouni@loria.fr.
