Samuel Lavoie

5 papers · 2023–2024 · 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 🐣 Hot Topic Early Bird

Venues

NeurIPS (2) ECCV (1) ICLR (1) ICML (1)

Top co-authors

Aaron Courville (3) Aaron C. Courville (2) Ankit Vani (2) Michael Noukhovitch (2) Florian Strub (1) Andrew Gordon Wilson (1) Kenji Kawaguchi (1) Ranjay Krishna (1) Mido Assran (1) Danica J. Sutherland (1)

Research topics

Machine Learning (3) Artificial Intelligence (2) Deep Learning (2) Architectures (2) Core AI (2) Core Methods (2) Learning Types (2) Reinforcement Learning (1) Methods (1)

Keywords

representation learning (1) image classification (1) reinforcement learning (1) embedding learning (1) self-supervised learning (1) kl divergence (1) group sparsity (1) compositional generalization (1) model alignment (1) kolmogorov complexity (1) deep neural network (1) reward hacking (1) language model (1) iterated learning (1) zero-shot classification (1) visual feature (1) exponential moving average (1) caption diversity (1) text conditioning (1) simplicial embedding (1)

Papers

Modeling Caption Diversity in Contrastive Vision-Language Pretraining ICML 2024 SPARO: Selective Attention for Robust and Compositional Transformer Encodings for Vision ECCV 2024 Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings NeurIPS 2023 Language Model Alignment with Elastic Reset NeurIPS 2023 Simplicial Embeddings in Self-Supervised Learning and Downstream Classification ICLR 2023