2 papers
cs.LG2026
Improving Generative Model Self-Training with Geometrically Modified Outputs
Patrick Batsell, Thomas Walker, Richard Baraniuk
Self-training generative models - the continued improvement of a model using its own outputs - is becoming increasingly important as high-quality training data becomes scarce. Howe…
cs.LG2025
Benchmarking Attribute Discrimination in Infant-Scale Vision-Language Models
Patrick Batsell, Satoshi Tsutsui, Bihan Wen
Infants learn not only object categories but also fine-grained visual attributes such as color, size, and texture from limited experience. Prior infant-scale vision--language model…