Unifying Speech Recognition, Synthesis and Conversion with Autoregressive Transformers Paper • 2601.10770 • Published Jan 15 • 4
Data-Efficient On-Policy Distillation for Automatic Speech Recognition Paper • 2605.28139 • Published May 27 • 3
Tiny-Engram: Trigger-Indexed Concept Tables for Generative Vision Paper • 2605.20309 • Published May 19
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Paper • 2609.18063 • Published 10 days ago • 18
The Other Half of the Memory Wall: Serving 35B MoEs from SSD with Trained Routing Prediction Paper • 2609.18063 • Published 10 days ago • 18