#compositional-generalization News & Analysis

3 articles tagged with #compositional-generalization. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

3 articles

AINeutralarXiv – CS AI · May 47/10

🧠

When Do Diffusion Models learn to Generate Multiple Objects?

Researchers have identified fundamental limitations in how text-to-image diffusion models handle multi-object generation, finding that scene complexity rather than data imbalance is the primary culprit. Through a controlled framework called MOSAIC, they demonstrate that counting objects is particularly difficult in low-data regimes and that compositional generalization collapses when training combinations are systematically excluded.

AINeutralarXiv – CS AI · May 286/10

🧠

Learning Compositional Latent Structure with Vector Networks

Researchers introduce Vector Networks (VN), a neural architecture that replaces dense weight matrices with libraries of reusable rank-1 weight atoms, enabling selective composition of network components for novel tasks. The approach demonstrates significant out-of-distribution generalization improvements—up to an order of magnitude better than baselines—when familiar elements must be recombined in new ways, addressing a fundamental limitation in deep learning's ability to handle compositional reasoning.

AINeutralarXiv – CS AI · May 76/10

🧠

Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize

Researchers identify a critical training window where Transformer models decide between memorization and reasoning, finding that applying weight decay during a specific 25% training phase matches full-training performance on compositional tasks. The discovery reveals sharp boundaries in this decision point, with timing shifts of just 100 optimization steps causing dramatic accuracy swings from chance performance to robust reasoning.