NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
model improvement
Model improvement involves making changes or optimizations to enhance the performance, accuracy, or efficiency of an existing AI model. This can include algorithmic tweaks, architectural changes, or refinement of training data.
3 papers
LILO: Learning to Reason at the Frontier of Learnability
Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation
What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models