From the 1 of 2 linked papers with an AI index.
2 papers
cs.AI2026
CUSUM-Shaped Inference-Time Monitoring and Targeted Re-Decoding for Quantized Small Language Model Reasoning
El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan +1
Quantized small autoregressive reasoning models can enter long, repetitive, or unproductive trajectories, yet inference-time compute is usually allocated without observing how a tr…
cs.AI2026
Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is the Wrong Observable for Decoding Monitors
El Hassane Ettifouri, Ayoub Belfatmi, Mahaman Sanoussi Yahaya Alassan +1
The paper shows that using centered token log‑probability as a monitor for quantized reasoning language models is ineffective, and proposes a training‑free calibrated e‑CUSUM decod…