MScT LLGA

Two refresher courses:

• Refresher in Statistics (APM_51438_EP, Marine Le Morvan, Inria)
• Refresher in Computer Science (CSC_51440_EP, Amal Dev Parakkat, Telecom Paris)

All subsequent M1 courses are 36h and will credit 4.5 ECTS. Note that students need to mandatorily either choose a Deep Learning course either in Period 1 (CSC_51054_EP) or in Period 2 (APM_52183_EP).

Mandatory:

• Machine Learning (MDC_51006_EP, Erwan Le Pennec and Jesse Reed, EP)

3 courses among:

• Deep Learning (Recommended option, CSC_51054_EP, Michalis Vazirgiannis, Johannes Lutzeyer and Ye Zhu, EP)
• Signal Processing (Recommended option, APM_51055_EP, Rémi Flamary, EP)
• Emerging Subjects in Machine Learning and Collaborative Learning (Recommended option, APM_51178_EP, Aymeric Dieleveut and El Mahdi El Mhamdi, EP)
• Computer Animation (CSC_51085_EP, Mathieu Desbrun and Marie-Paule Cani, Inria & EP)
• Image Analysis and Computer Vision (CSC_51073_EP, Mathieu Brédif, Univ Gustave Eiffel)
• Topological Data Analysis (CSC_51056_EP, Steve Oudot, EP & Inria)
• Digital Representation and Analysis of Shapes (CSC_51074_EP, Mathieu Desbru and Pooran Memari, EP & Inria)
• Probability Theory for ML: Applications to Monte Carlo Methods and Generative Models (APM_51056_EP, Alain Durmus, EP)
• DataBase Management System (CSC_51053_EP, Loana Manolescu, Inria)
• Statistical Learning Theory (APM_51059_EP, Karim Lounici, EP)

+ Mandatory non-scientific courses:

• Introduction to Marketing and Strategy (IME_51456_EP, Philippe Ginier-Gillet, EP)
• Sport
• Humanities
• Foreign Languages

Mandatory:

• Reinforcement Learning and Autonomous Agents (CSC_52081_EP, Jesse Read, EP)
• Graph Machine and Deep Learning for Generative AI (CSC_52072_EP, Johannes Lutzeyer and Michalis Vazigiannis, EP)
• Introduction to Text Mining and NLP (CSC_52082_EP, Michalis Vazirgiannis and Davide Buscaldi, EP & Université Sorbonne Paris Nord)

1 course among:

• Multimodal Generative AI (Recommended option, CSC_52002_EP, Vicky Kalogeiton, EP)
• Statistics in Action (Recommended option, APM_52066_EP, Zacharie Naulet, EP & INRAE)
• Deep Learning (Recommended option, APM_52183_EP, Kevin Scaman)
• Computational Optimal Transport for ML and Fairness (Recommended option, Rémi Flamary, EP)
• Optimization for AI (APM_52067_EP, Luiz Chamon and Aymeric Dieuleveut, EP)
• Optimization and Responsible AI for Sustainability (CSC_52073_EP, Sonia Vanier, EP)
• Advanced Deep Learning (CSC_52087_EP, Vicky Kalogeiton, Johannes Lutzeyer, Ye Zhu and Xi Wang, EP)
• Image Synthesis: Theory and Practice (CSC_52084_EP, Tamy Boubekeur, Telecom ParisTech)
• Social Media and Communication: Probabilistic Models and Algorithms (APM_51058_EP, Laurent Massoulie, Inria)

+ Mandatory non-scientific courses:

• Either Entrepreneurship for Sustainability (IME_52068_EP, Chloé Steux, 3 ECTS) Or Case studies on Innovation (IME_52062_EP, Philippe Ginier-Gillet, 3 ECTS)
• Sport
• Humanities
• Foreign Languages

INT_52406_EP - Research-Oriented Internship (4 to 6 months, 20 ECTS)

No refresher course is provided but students directly entering in the M2 and lacking background in language and graph modeling are welcome to follow the M1 refresher course in Computer Science. The detailed curriculum for M2 is currently under development. However, below we provide a preliminary overview of the core and introductory courses that students are expected to take.

CSC_53432_EP - Large Language Models (24h, 2 ECTS), Guokan Shang (MBZUAI) (contact: guokan.shang@mbzuai.ac.ae)

This course offers a deep dive into Large Language Models (LLMs), blending essential theory with hands-on labs to develop both practical skills and conceptual understanding—preparing you for roles in LLM development and deployment.
The curriculum begins with a brief overview of key historical NLP techniques. It then transitions to the transformer architecture, focusing on its attention mechanism and tokenization—the core of modern LLMs. Pre-training objectives such as masked/denoising language modeling and causal language modeling will also be covered, forming the basis for models like BERT, GPT, and T5. The course then examines LLM post-training techniques used to refine pre-trained models, including instruction tuning (SFT), reinforcement learning from human feedback (e.g., PPO/DPO), and reinforcement learning from verifiable rewards (e.g., GRPO). Finally, the course will address LLM application and future directions—including RAG, agents, multimodality, and alternative model architectures.

CSC_53431_EP - Analysis and Deep Learning on Geometric Data (24h, 2 ECTS), Maks Ovsjanikov (EP) (contact: maks@lix.polytechnique.fr)

This course will introduce students to advanced topics in modern geometric data analysis with focus on a) mathematical foundations (discrete differential geometry, mapping, optimization), and b) deep learning for best performing methods. We will give an overview of the foundations in shape analysis and processing before moving to modern techniques based on deep learning for solving problems such as shape classification, correspondence, parametrization, etc.

To be completed soon.

MDC_54430_EP - Transverse project (8 ECTS): Students will work half a day a week on a transverse project, corresponding to a challenging question either raised by an industrial partner or by a researcher in the domain spanned by the programme.

IME_50430_EP - Seminar on ethical issues, law and novel applications of AI (6 ECTS), Véronique Steyer veronique.steyer@polytechnique.edu Students will be sensitized to ethical issues and law, and introduced to novel applications of artificial intelligence and visual computing through a weekly seminar with key-note talks from both institutional and industrial partners.

Courses in humanities, languages and sports (8 ECTS total) These courses will be similar to those of the other graduate degrees at Ecole Polytechnique.

INT_54490_EP - Internship either in the R&D department of a company or in a research lab (5 to 6 months, 24 ECTS).