AI / ML Researcher

Portrait of Sofiane Ennadir

I work across the full model lifecycle, from large-scale self-supervised pre-training of multi-modal and world-model backbones, to post-training that couples learned representations to reinforcement-learning agents.

I am an AI/ML Researcher at King AI Labs (Microsoft Gaming), where I build predictive world models on heterogeneous game signals and connect them to in-game decision-making. My work is grounded in the theoretical foundations, generalization, and safety of modern deep learning, and validated at scale in large gaming environments.

I previously completed my PhD in the School of Electrical Engineering and Computer Science at the KTH Royal Institute of Technology, supervised by Professors Michalis Vazirgiannis and Henrik Boström, and funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP). My dissertation, On the Adversarial Robustness of Graph Neural Networks, developed theoretically grounded attacks and defenses, work that now informs how I think about the safety of pre-trained systems.

I also had the pleasure of spending a summer at the Flatiron Institute (Simons Foundation) with the Polymathic AI / Foundation Models for Science initiative, working with Leopoldo Sarra and Siavash Golkar on extending Joint-Embedding Predictive Architectures (JEPA) to time series (TS-JEPA).

Earlier, I earned an MSc in Applied Mathematics from École Polytechnique and an engineering degree from EMINES at Mohammed VI Polytechnic University (UM6P), Morocco.

Research

One thread runs through my work: how representations are learned at scale, connected to agents, and made reliable.

01 · Pre-training

Self-Supervised & Multi-modal Pre-training

Predictive world models and JEPA-style objectives; self-supervised representation learning across modalities and temporal graphs, with a focus on representation collapse and normalization.

JEPAWorld modelsSSLTemporal graphs
02 · Post-training

World Models & RL

Context-conditioned world models that bridge representation pre-training and policy learning by coupling pre-trained backbones to reinforcement-learning agents for in-game decision-making (model-based RL).

Model-based RLAgentsFine-tuning
03 · Theory & Safety

Generalization & Robustness

Theoretical foundations of Transformer-based models, including expressivity of pooling and preprocessing effects, alongside the adversarial robustness and safety of deep learning systems.

TransformersGeneralizationRobustness

News

  • 2026 · "Understanding Early Collapse in Predictive World-Model Pretraining" accepted to the World Models Workshop @ ICLR 2026.
  • 2026 · "Be Wary of Your Time Series Preprocessing" accepted to the AI4TS Workshop @ AAAI 2026.
  • Sep 2025 · "Virtual Nodes Go Temporal" accepted for an Oral presentation at LOG 2025!
  • Sep 2025 · Two papers accepted at NeurIPS 2025.
  • May 2025 · Talk on GNN robustness at the Metis Spring School, Rabat, Morocco.
  • Feb 2025 · Survey "Expressivity of Representation Learning on Continuous-Time Dynamic Graphs" accepted to TMLR with a Survey Certification.
  • Sep 2024 · "Joint Embeddings Go Temporal" accepted to the Time Series in the Age of Large Models Workshop @ NeurIPS 2024.
  • Sep 2024 · "If You Want to Be Robust, Be Wary of Initialization" accepted to NeurIPS 2024.

Selected Publications

Self-Supervised & Multi-modal Pre-training
  1. S. Ennadir*, L. Zólyomi*, O. Smirnov* · World Models Workshop, ICLR, 2026.
  2. S. Ennadir, Y. Jedra, O. Smirnov, L. Cao · Learning on Graphs (LOG), 2025.  [PDF] []
  3. S. Ennadir, S. Golkar, L. Sarra · TSALM Workshop, NeurIPS, 2024.  [PDF] [Code] []
  4. S. Ennadir*, G. Zarzar*, F. Cornell*, L. Cao, O. Smirnov, T. Wang, L. Zólyomi, B. Brinne, S. Asadi · TMLR, 2025.  [PDF] [Code] []
Transformer-based Models & Generalization
  1. S. Ennadir*, L. Zólyomi*, O. Smirnov, T. Wang, J. Pertoft, F. Cornell, L. Cao · NeurIPS, 2025.  [PDF] []
  2. S. Ennadir*, T. Wang, O. Smirnov, L. Cao, S. Asadi · AI4TS Workshop, AAAI, 2026.
Safety & Robustness
  1. S. Ennadir*, O. Smirnov*, Y. Abbahaddou, L. Cao, J. Lutzeyer · NeurIPS, 2025.  [PDF] []
  2. S. Ennadir, J. Lutzeyer, M. Vazirgiannis, E. Bergou · NeurIPS, 2024.  [PDF] [Code] []
  3. Y. Abbahaddou*, S. Ennadir*, J. Lutzeyer, M. Vazirgiannis, H. Boström · ICLR, 2024.  [PDF] [Code] []
  4. S. Ennadir, Y. Abbahaddou, J. Lutzeyer, M. Vazirgiannis, H. Boström · AAAI, 2024.  [PDF] [Code] []

* denotes equal contribution.

Experience

AI/ML Researcher · King AI Labs (Microsoft Gaming)

Aug 2024 – Present · Stockholm, Sweden
  • Multi-modal pre-training & representation. Built self-supervised, multi-modal pre-training that learns unified representations from heterogeneous game signals, improving downstream player embeddings and recommendation.
  • World models, from pre-training to RL. Pre-trained predictive world models on multi-modal game data, extending temporal JEPA and mitigating early representation collapse, then coupled them to RL agents via context-conditioned world models (model-based RL).
  • Architecture & training foundations. Grounded these systems in theory, particularly pooling in Transformers and normalization/preprocessing effects, to improve pre-training stability and quality.

Technical Expertise

Pre-training

Self-supervised and multi-modal pre-training of LLM, world-model, and time-series backbones (JEPA, DINO), including objective design and representation-collapse / normalization diagnostics.

Post-training

Connecting pre-trained world models to reinforcement-learning agents (model-based / context-conditioned RL) and fine-tuning foundation models for real-world applications.

Scale & Infrastructure

Large-scale distributed training (DDP) and end-to-end experimentation on HPC clusters (A100 / H100), from data ingestion and experiment tracking to reproducible evaluation.

  • Python
  • PyTorch
  • DDP
  • A100 / H100
  • JEPA
  • Model-based RL

Teaching & Service

Teaching

  • Graph Curvature as a Lens on Adversarial Robustness in GNNs · LOGML Summer School, Imperial College London.
  • Introduction to LLMs & Deep Learning on Graphs · École Polytechnique, Paris.
  • Deep Learning for Time Series, NLP and Graphs · École Polytechnique Executive Education, Paris.

Selected Talks

  • Representation Learning and World Models for Games · Imperial College London 2026.
  • Virtual Nodes Go Temporal · Temporal Graph Reading Group, 2026.
  • From Bounds to Defenses: A Comprehensive Look at GNN Robustness · Metis Spring School, 2025.
  • Theoretically Upper-Bounding the Expected Adversarial Robustness of GNNs · Collective ML, 2024. [Slides]
  • Adversarial Robustness of GNNs · MoroccoAI webinar. [Slides | Recording]

Reviewing

NeurIPS (Top Reviewer, 2025), ICLR, ICML (Top Reviewer, 2026), AAAI, and TMLR.

Awards & Honors

  • WASP Doctoral Scholarship · Knut and Alice Wallenberg Foundation, 2021.
  • OCP Full Excellence merit scholarship for outstanding entrance-examination results, 2014.