AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
3 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Refining Compositional Diffusion (RCD) is proposed, a training-free guidance method that steers compositional sampling toward high-density, globally coherent plans and demonstrates that RCD consistently outperforms existing methods.
I-SplineFlow is introduced, which parameterizes the scheduler with integrated monotone splines (I-splines), and improves few-step FID over B\'ezier scheduling in most settings, most clearly at the lowest NFEs, and trains in minutes.
LogitLens analyses and a targeted LM head intervention support the conclusion that acoustic underuse is not explained solely by encoder-side information loss and that readout alignment can be a dominant bottleneck.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.