Aurele Durand
Ingenieur · Chercheur · Entrepreneur
Innover utile, eclairer les debats, transmettre par la pensee critique.
J'explore les intersections entre intelligence artificielle, philosophie et mediation scientifique.
Competences
Un profil atypique entre technique et reflexion
IA & Developpement
Web & Data
Pensee critique
Mediation
A propos
Ingenieur de formation avec une passion pour la philosophie, je me consacre a rapprocher les sciences et les humanites. Mon parcours atypique me permet d'aborder les problemes sous des angles complementaires.
President de l'association Mythodologie, je developpe des outils educatifs pour la pensee critique et j'interviens en milieu scolaire sur les enjeux de l'IA, du climat et de la desinformation.
Actuellement, je travaille sur Psy-X, une plateforme educative combinant jeux sur les biais cognitifs et dialogue avec des philosophes via l'intelligence artificielle.
Voir mes travaux →
Veille automatisee
Articles et opportunites reperes par mon systeme de veille IA
Anatomy-R1: Enhancing Anatomy Reasoning in Multimodal Large Language Models via Anatomical Similarity Curriculum and Group Diversity Augmentation
arXiv:2512.19512v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive progress in natural image reasoning, yet their potential in medical imaging remains underexplored, especially in clinical anatomical surgical images. Anatomy understanding tasks demand precise understanding and clinically coherent answers, which are difficult to achieve due to the complexity of medical data and the scarcity of high-quality expert annotations. These challenges limit the effectiveness of conventional Supervised Fine-Tuning (SFT) strategies. While recent work has demonstrated that Group Relative Policy Optimization (GRPO) can enhance reasoning in MLLMs without relying on large amounts of data, we find two weaknesses that hinder GRPO's reasoning performance in anatomy recognition: 1) knowledge cannot be effectively shared between different anatomical structures, resulting in uneven information gain and preventing the model from converging, and 2) the model quickly converges to a single reasoning path, suppressing the exploration of diverse strategies. To overcome these challenges, we propose two novel methods. First, we implement a progressive learning strategy called Anatomical Similarity Curriculum Learning by controlling question difficulty via the similarity of answer choices, enabling the model to master complex problems incrementally. Second, we utilize question augmentation referred to as Group Diversity Question Augmentation to expand the model's search space for difficult queries, mitigating the tendency to produce uniform responses. Comprehensive experiments on the SGG-VQA and OmniMedVQA benchmarks show our method achieves a significant improvement across the two benchmarks, demonstrating its effectiveness in enhancing the medical reasoning capabilities of MLLMs. The code can be found in https://github.com/tomato996/Anatomy-R1
Epitome: Pioneering an Experimental Platform for AI-Social Science Integration
arXiv:2507.01061v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) enable unprecedented social science experimentation by creating controlled hybrid human-AI environments. We introduce Epitome (www.epitome-ai.com), an open experimental platform that operationalizes this paradigm through Matrix-like social worlds where researchers can study isolated human subjects and groups interacting with LLM agents. This maintains ecological validity while enabling precise manipulation of social dynamics. Epitome approaches three frontiers: (1) methodological innovation using LLM confederates to reduce complexity while scaling interactions; (2) empirical investigation of human behavior in AI-saturated environments; and (3) exploration of emergent properties in hybrid collectives. Drawing on interdisciplinary foundations from management, communication, sociology, psychology, and ethics, the platform's modular architecture spans foundation model deployment through data collection. We validate Epitome through replication of three seminal experiments, demonstrating capacity to generate robust findings while reducing experimental complexity. This tool provides crucial insights for understanding how humans navigate AI-mediated social realities, knowledge essential for policy, education, and human-centered AI design.
MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment
arXiv:2512.20950v1 Announce Type: cross Abstract: This paper presents our system for SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval. In an era where misinformation spreads rapidly, effective fact-checking is increasingly critical. We introduce TriAligner, a novel approach that leverages a dual-encoder architecture with contrastive learning and incorporates both native and English translations across different modalities. Our method effectively retrieves claims across multiple languages by learning the relative importance of different sources in alignment. To enhance robustness, we employ efficient data preprocessing and augmentation using large language models while incorporating hard negative sampling to improve representation learning. We evaluate our approach on monolingual and crosslingual benchmarks, demonstrating significant improvements in retrieval accuracy and fact-checking performance over baselines.
Projets
Des outils pour mieux penser et agir
Psy-X
Plateforme educative de pensee critique avec jeux sur les biais cognitifs et dialogue avec philosophes via IA.
Mythodologie
Association de mediation scientifique. Formations scolaires, projet SciLit (Erasmus+ 2025-2028).
Tractatus
Oeuvre philosophique modernisant Spinoza avec les sciences cognitives et le cerveau predictif.
ADN Skis
Co-fondateur d'une marque de skis artisanaux francais, alliage de performance et design.
SciLit
Projet Erasmus+ sur la litteratie scientifique avec 6 pays partenaires europeens.
Mise en mouvement
Recherche Shifters sur les freins psychologiques et leviers a l'action climatique.
Publications & Interventions
Travaux philosophiques et conferences
Tractatus de Cohaerentia
Une relecture de l'Ethique de Spinoza a travers le prisme des sciences cognitives et du cerveau predictif. 6 livres, 100 propositions.
En savoir plus →L'IA peut-elle nous aider a reflechir ?
Journee d'etude a l'Institut de Philosophie de Grenoble (IPhiG), printemps 2026. Collaboration avec Thierry Menissier.
En savoir plus →Travaillons ensemble
Vous cherchez un intervenant pour une conference, une formation a la pensee critique, ou un consultant en IA et philosophie ?
Me contacter