I'm a grad student researcher focusing on LLM reasoning and self-improvement, as well as Machine Learning in general.
Aside from completing my M.Sc. in AI/ML at PSL University (under ENS, Mines and Dauphine), I'm currently working on semi-supervised learning with INSA Lyon (DISP Lab); and on reasoning methods in small LLMs independently.
We probe just how early a Large Language Model (LLM) internally commits to an eventual outcome by training linear classifiers on hidden states after the first 𝑡 reasoning tokens; showing that eventual correctness is highly predictable after only a few tokens. We show that, for harder questions, a drop in predictive accuracy highlights a selection artifact: hard items are disproportionately represented in long CoTs.
Semi-Supervised Pipeline for Etiological Diagnosis of Uveitis, building a data-efficient flow from patch-level embeddings to graph attention maps for ultra-wide-field fundus scans. The project combines MTSN contrastive training, One Vote Veto pseudo-labelling, and GACNN localisation with collaborators at INSA Lyon.
Latent-space guidance system for Meta's Coconut model, coupling latent reasoning tokens with a FAISS vector store to nudge reasoning traces in real-time. Currently integrating RL penalties to improve generalization on complex queries.
Starting with a pure python/pytorch re-implementation of GPT-2 as described in the original OpenAI paper, this project was extended via QLoRA to allow fine-tuning on messages to try to replicate given personalities.
This series reimplements feedforward networks in C++ and NumPy for handwriting recognition, music tagging, and more. Several optimizations (Dynamic tanH instead of LayerNorm for regularization, dropout, weight tying) improved the speed and performance of the C++ implementation to be far faster than their numpy counterparts.
A fine-tuned PatchCore pipeline that flags industrial soldering anomalies using anomalib's memory-bank k-NN scoring. I tuned thresholds and evaluation scripts so operators can catch rare defects without expanding labeling budgets.
py-scripts is a grab bag of Python utilities I rely on for automation and quick experiments. Expect everything from data wrangling helpers to small personal productivity hacks.