Connect Four AI
Building Connect Four agents from classical search to AlphaZero, with the environment, agents, and evaluation in one harness.
Minimax. Searches future states with alpha-beta pruning.
01
Research
Are Superpixels the Missing Ingredient for Robust ViT Pruning?
VISAPP 2026 · First author
Studying whether spatially coherent token selection improves the robustness of Vision Transformer pruning across classification and dense prediction.
From Complexity to Efficiency: Pruning Vision Transformers in Practice
EEAI 2025 · Second author
A taxonomy of ViT pruning methods, with selected token and patch merging strategies measured on an NVIDIA Jetson Orin AGX. Fewer tokens do not always mean lower latency.
02
Selected work
Research Agent
Question answering over papers, with answers grounded in retrieved passages and citations. Retrieval and generation are scored separately.
- PDFs
- Chunk
- Embed
- Retrieve
- Generate
- Cite
Retrieval evalHit@51.00MRR0.9720hand-labelled questions
03
Experience
CEA Paris-Saclay
Research — Efficient Vision Transformers
Token pruning, token merging, mixed precision.
2025–2026
Apple
Camera Hardware Engineering
Image processing, optical measurement, lab automation. One system cut measurement runtime by about half.
2023–2024
Toulouse INP – ENSEEIHT
Engineering Degree + MSc AI
Ranked first in the final AI specialization year.
Graduated 2026
04
About
I trained as an electrical and electronics engineer, spent a gap year on two Camera Hardware internships at Apple, then shifted during my final year toward machine learning at ENSEEIHT and joined CEA Paris-Saclay.
My current interests include representation learning, reinforcement learning, world models, and AI systems that have to operate under real constraints.