2 papers
cs.LG2026
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
Ilay Kamai, Hugues Van Assel, Aviv Regev +2
Cross-modal alignment (CA) and cross-modal prediction (CP) are the dominant paradigms for multimodal representation learning, yet there is no systematic understanding of when each…
cs.LG2026
Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Generation
Hugues Van Assel, Edward De Brouwer, Saeed Saremi +2
Generative modeling and self-supervised representation learning (SSL) optimize structurally different objectives: generative training rewards distributional fidelity, while SSL rew…