Cofounder, Aiwen Logiciels — MSc AI2D, Sorbonne University
Frédéric
Li Combeau
I build and study generative models, the kind that don't just render a plausible image but hold some usable notion of the scene behind it. I want to work on visual intelligence and generative models that understand the world.
Now Looking for a PhD in world models, representation learning and generative AI. Feel free to reach out if you have an open position.
01Experience & Research
-
Cofounder — Aiwen Logiciels
A software company building AI tools for businesses: physical climate risk analysis, contract review, early warning on client and supplier defaults, public-tender matching, automated SEO and a company data search engine.
-
Open-source contributor — Nightingale
Nightingale ↗ · karaoke from any song in your library, powered by neural networks
Mostly on the lyrics pipeline: alignment guided by LRC lyric files, a lyrics-timing fix, Japanese kanji read in sentence context for romaji, and reading notes on lyrics; plus a folders section in the library sidebar. My pull requests ↗
-
Fast Text-to-Panoramic 3D Gaussian Splatting via MeanFlow Distillation and Model Stitching
Research internship · PRS Group, ETH Zürich — in collaboration with Google
Supervised by Postdoc. Narnhofer, Prof. Schindler, Prof. Tombari (Google)
A paper is planned for submission.
-
Test-Time Adaptation to the Next Domain in Continual Learning
Research internship · CVM Lab, University of Tokyo
Supervised by Postdoc Michel, Prof. Yamasaki
Proposed a new, more realistic evaluation setup for combined continual-learning / test-time-adaptation deployment. A paper is planned for submission to CVPR 2027.
02Academic Projects
-
M2 project
Style Decomposition and Content Preservation for Artistic Style Transfer
Reimplementation of the paper from scratch, with additional experiments on reproducibility and generation parameters.
Original paper ↗ -
M2 project
Multimodal Visual Personalization of Generative Models via Individual Preference Learning
Added a multimodal (eye-tracking) signal and a new pipeline to improve image personalization, with a full evaluation of the resulting model.
Original Paper ↗ -
M2 project
highest grade
Tactical Optimism and Pessimism in RL
Reimplementation of the paper, with experiments on additional learnable parameters.
Original paper ↗ -
M1 semester project
highest grade
AFU: Actor-Free Critic Updates
Implementation and analysis of “AFU: Actor-Free critic Updates in off-policy RL for continuous control.” Found that AFU outperforms other algorithms in offline-to-online transition, but not in an off-policy uniform-sampling setting.
Github ↗ -
Bachelor's project
Smart Home
A small smart house built on Raspberry Pi and Arduino: MobileNet for person detection, a Firebase database, a mobile app and a PC interface.
03Background
Master's degree, AI2D (AI, Algorithms, Multi-Agent)
Sorbonne University - high honors
Deep Learning · Advanced Deep Learning (audited) · Multimodal AI · AI for Robotics (ranked 1st) · AI for Vision (extra course) · Advanced Optimization Methods and Applications · Human-AI Interaction
Extra course, Robotics
ENS Ulm
Bachelor's degree, Computer Science
Paris-Saclay University
Self-study, Mathematics and AI
Representation Learning (MVA master's course — audited material and lecture notes) · advanced mathematics from ENS Ulm, ENS Lyon and CPGE courses, mapped below.
Programming
Python, PyTorch, OpenCV, NumPy, SciPy, Pandas, scikit-learn, Seaborn
LLMs & engineering
LLMs, LangChain, RAG, agentic AI, Git/GitHub, pipelines, APIs
Languages
- French — native
- English — professional (TOEIC C1)
Other
- French driving licence
- First aid certificate (PSC1)
- Certificate of Musical Studies (11+ years of guitar and composition)
04Self-study
Mathematics and physics from the first year of CPGE to M1, rebuilt from CPGE, ENS Ulm and ENS Lyon lecture notes into one interactive course per topic. Prerequisites on the left, what they open up on the right.
05Side Projects
Smaller things, built outside of coursework, mostly to understand something by hand.
-
Deep Learning / TensorFlow - 2023
DCGAN for face generation
The faces are not very nice but I only trained for 20 epochs.
Github ↗ -
Deep Learning / TensorFlow - 2023
Object detection
Full implementation of YOLO from scratch for object detection.
Github ↗ -
Deep Learning / TensorFlow - 2023
Emotion detection
Implementation of a deep learning model for detecting emotions in facial expressions.
Github ↗ -
Deep Learning / TensorFlow - 2023
Malaria detection
Implementation of multiple deep learning models and data augmentation techniques for detecting malaria in blood smears.
Github ↗ -
Computer Vision / OpenCV / MediaPipe - 2022
Detection and tracking
A set of computer vision experiments: face detection, hand tracking, pose estimation, and holistic (combined face + hands + pose) tracking.
Github ↗ -
Discord Bot / Node.js / Discord.js - 2022-2026
Discord Bot
Implementation of a Discord bot with various features and commands. Full RPG built from scratch, music player and fun commands.
06Off the clock
My hobbies and interests outside of work.
- Ongoing Composer, guitarist and pianist.
- 2024 Took part in Prologin, the French programming competition.
- 2018 Competed in the France Chess Championship at the regional level.
- Middle school A few charity sporting events for Action contre la Faim.
- Always History and hiking, usually not at the same time.
Here is a small selection of the games and anime I enjoyed the most.