Tutorials
Local Mechanisms of Compositional Generalization in Conditional Diffusion
Conditional diffusion models appear capable of compositional generalization, i.e., generating convincing samples for out-of-distribution combinations of conditioners, but the mechanisms underlying thi
Conditional diffusion models appear capable of compositional generalization, i.e., generating convincing samples for out-of-distribution combinations of conditioners, but the mechanisms underlying this ability remain unclear. To make this concrete, we study length generalization, the ability to generate images with more objects than seen during training. In a controlled CLEVR setting (Johnson et al.,2017), we find that length generalization is achievable in some cases but not others, suggesting that models only sometimes learn the underlying compositional structure. We then investigate…
Related
- Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs
- ODE-free Neural Flow Matching for One-Step Generative Modeling
- Conditional flow matching for physics-constrained inverse problems with finite training data
- The Power of Power Law: Asymmetry Enables Compositional Reasoning
Source: Apple ML Research | 2026-04-28