Internship Research / World Models for Networking

inria; France; Hybrid; EUR 13,000 - 18,000; Full time

Benefits offered by this job

Partial reimbursement of public travel

Teleworking possible

Professional equipment available

7 weeks annual leave + RTT days

Social, cultural and sports events

Job summary

Inria is offering a temporary internship focused on advancing World Models in networking. The project explores adapting LeWorldModel to dynamic wireless networks and evaluating predictive representations.

The selected candidate will reproduce leading JEPA-based methods and tailor them to a networking context, with hands-on work in Python and PyTorch. The internship emphasizes research quality, experimentation, and reporting, and it offers teleworking possibilities and access to Inria's research

Qualifications

• Solid background in ML with practical experience in Python and PyTorch.
• Interest in networking (wireless networks a plus).
• Familiarity with self-supervised learning, representation learning or reinforcement learning is a plus.

Responsibilities

• Study the World Model and JEPA literature, then reproduce and test the 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.

Skills

Python

PyTorch

Machine Learning

Self-supervised learning

Education

Master's student in ML/CS

Job description

Inria, the French national research institute for the digital sciences

Organisation/Company Inria, the French national research institute for the digital sciences Research Field Computer science Researcher Profile First Stage Researcher (R1) Application Deadline 31 Dec 2026 - 00:00 (UTC) Country France Type of Contract Temporary Job Status Full-time Hours Per Week 38.5 Offer Starting Date 4 Jan 2027 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Reference Number 2026-10661 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

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.

• 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