From the 1 of 3 linked papers with an AI index.
3 papers
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…
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…
Visual Grounding Methods for Efficient Interaction with Desktop Graphical User Interfaces
El Hassane Ettifouri, Jessica López Espejel, Laura Minkova +2
Most visual grounding solutions primarily focus on realistic images. However, applications involving synthetic images, such as Graphical User Interfaces (GUIs), remain limited. Thi…