arxiv
PublishedSeptember 3, 2026 at 4:00 AM
CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning
Publisher summary· verbatim
arXiv:2607.20129v2 Announce Type: replace Abstract: Quantized small reasoning models can enter repetitive or otherwise unproductive trajectories, yet standard decoding does not adapt to the trajectory as it unfolds. We study MGT-B, a fixed, weight-preserving controller that converts overlapping wind
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗