Internship Research / World Models for Networking

Inria; Palaiseau; Hybrid; EUR 11,000 - 17,000; Full time

Benefits offered by this job

Partial reimbursement of public travel

7 weeks annual leave + RTT

Teleworking possible

Professional equipment provided

Social, cultural and sports events

Job summary

Inria Saclay Centre recherche un stagiaire en Recherche appliquée sur les World Models pour les réseaux. Vous explorerez des approches de modélisation interne et leur adaptation à des problèmes de réseaux sans fil, avec une mise en œuvre en Python et PyTorch.

Le stage vise à reproduire et tester des modèles LeWM/J EPA, puis à adapter un modèle aux applications réseau et évaluer les résultats expérimentalement dans un cadre académique.

Qualifications

• Solide formation en apprentissage automatique et deep learning.
• Expérience pratique en Python et PyTorch.
• Intérêt pour les réseaux; familiarity avec self-supervised learning, representation learning ou reinforcement learning est un plus.

Skills

Machine Learning

Deep Learning

Networking interest

Self-Supervised Learning

Reinforcement Learning

Tools

Python

PyTorch

Job description

Internship Research / World Models for Networking

Created in 2008, the Inria Saclay Center is located at the heart of the Paris-Saclay scientific and technological excellence cluster, which alone accounts for 15% of French research. Serving the development of the Université Paris-Saclay and the Institut Polytechnique de Paris, the Inria Saclay center employs 80 people in research support services and 500 scientists of 54 nationalities.

Benefiting from continuous growth, the center now has a total of 42 project-teams and two in the process of being created, including 21 jointly with the Institut Polytechnique de Paris, 16 with the Université Paris-Saclay, as well as 7 Inria EPs, including one in collaboration with Onera and one with the Pôle Universitaire Centre Val de Loire. These research teams are spread over more than ten sites.

World Models are a family of models that offer an alternative to classical approaches such as vision models or large language models. Instead of mapping inputs to outputs, they learn an internal representation of a “world” and predict how that world evolves over time and in response to actions. This makes them natural candidates for prediction, simulation and planning.

These models are known to be hard to train. Many recent approaches build on the Joint-Embedding Predictive Architecture (JEPA) [1–4], which predicts in a learned representation space rather than reconstructing raw inputs. Within this line of work, LeWorldModel (LeWM) [5, 6] was recently proposed. It trains end to end in a stable way and has shown good properties for training.

Objectives

The LeWM methodology is general, but so far it has mainly been applied to image inputs. This internship will explore how it can be adapted to networking problems. Wireless networks are a good fit for this approach: their state, such as topology, connectivity and traffic, changes over time and in response to decisions. Prior work in the team has studied related problems [7].

Work plan

• Study the World Model and JEPA literature, then reproduce and test the existing LeWM model.
• Choose a suitable networking application and an input representation, based on feasibility and relevance.
• Adapt and retrain the model on this application, possibly through a sequence of tasks of increasing complexity.
• Evaluate the results experimentally and analyze both the predictions and the learned representations.

Candidate profile

• Solid background in machine learning and deep learning, with practical experience in Python and PyTorch
• Interest in networking (wireless networks are a plus, but not required)
• Familiarity with self-supervised learning, representation learning or reinforcement learning is a plus

References

[1] Y. LeCun, “A Path Towards Autonomous Machine Intelligence,” OpenReview, 2022.
[2] M. Assran et al., “Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture” (I-JEPA), CVPR 2023.
[3] A. Bardes et al., “Revisiting Feature Prediction for Learning Visual Representations from Video” (V-JEPA), TMLR 2024.
[4] M. Assran et al., “V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning,” arXiv:2506.09985, 2025.
[5] R. Balestriero and Y. LeCun, “LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics,” arXiv:2511.08544, 2025.
[6] L. Maes, Q. Le Lidec, D. Scieur, Y. LeCun, and R. Balestriero, “LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels,” arXiv:2603.19312, Mar. 2026.
[7] F. Marcoccia, V. Fagoo, G. M. de Saint Julien, C. Adjih, T. Watteyne, and P. Mühlethaler, “NetDiff: Graph Diffusion with Improved Global Capabilities to Generate and Update Mobile Network Topologies,” ICML 2026.

Avantages

• Partial reimbursement of public transport costs
• Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
• Possibility of teleworking and flexible organization of working hours
• Professional equipment available (videoconferencing, loan of computer equipment, etc.)
• Social, cultural and sports events and activities