This work introduces SPECIFICITY PADDING that simply asks the model to copy a few random IDs from the prompt, and that alone makes a title-only request look more human than one that supplies the article's key ideas.
Diffusion language models (DLMs) promise fast parallel generation, yet high-quality samples often require large number of refinement steps, which diminishes their advantage in practice. This has led to massive interest in and rapid development of new methods for effective few-step generation. We show that much of the s...
H. Amin, Ming Yin, Rajiv Khanna· arXiv.org· 1 citation· ⚡1
Together, these results isolate a single governing quantity for scale-invariant optimization, providing a precise and actionable lens on training dynamics, optimizer behavior, and schedule design in modern deep learning.
H. Amin, Wei-Kai Chang, Rajiv Khanna· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.