Benoit Dufumier

5 papers · 2023–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze ❓ The Questioner (2)

Venues

ICLR (2) ICML (1) MICCAI (1) MIDL (1)

Top co-authors

Pietro Gori (3) Edouard Duchesnay (3) Carlo Alberto Barbano (2) Robin Louiset (2) Javiera Castillo Navarro (1) Raphaël Vock (1) Marco Grangetto (1) Enzo Tartaglione (1) Antoine Grigis (1) Grigis Antoine (1)

Research topics

Machine Learning (4) Core Methods (3) Learning Types (3) Application Areas (2) Artificial Intelligence (1) Computer Vision (1) Deep Learning (1) Core AI (1) Domain-Specific (1) Models (1) Optimization & Theory (1)

Keywords

representation learning (3) contrastive learning (2) data augmentation (1) multimodal learning (1) supervised contrastive learning (1) prior knowledge (1) mutual information (1) latent space (1) contrastive loss (1) conditional mean embedding (1) biased data (1) salient feature (1) kernel methods (1) synergistic information (1) common feature (1) classification term (1) contrastive vae (1) disentangling term (1)

Papers

Does Connectome Harmonic Analysis pass the Spin Test? MICCAI 2025 What to align in multimodal contrastive learning? ICLR 2025 SepVAE: a contrastive VAE to separate pathological patterns from healthy ones MIDL 2024 Integrating Prior Knowledge in Contrastive Learning with Kernel ICML 2023 Unbiased Supervised Contrastive Learning ICLR 2023