works on

From the 1 of 5 linked papers with an AI index.

most citedLess Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy

1 citations · 1 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG2026

The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models

Fabio Arnez, Alexandra Gomez-Villa

The paper demonstrates that employing the SIGReg anti‑collapse regularizer in Joint‑Embedding Predictive Architectures turns their training objective into a valid variational free…

cs.CV20261 cited

Less Precise Can Be More Reliable: A Systematic Evaluation of Quantization's Impact on VLMs Beyond Accuracy

Aymen Bouguerra, Daniel Montoya, Alexandra Gomez-Villa +2

Vision-Language Models (VLMs) such as CLIP have revolutionized zero-shot classification and safety-critical tasks, including Out-of-Distribution (OOD) detection. However, their hig…

cs.LG2026

Oracle-Guided Soft Shielding for Safe Move Prediction in Chess

Prajit T Rajendran, Fabio Arnez, Huascar Espinoza +2

In high stakes environments, agents relying purely on imitation learning or reinforcement learning often struggle to avoid safety-critical errors during exploration. Existing reinf…

cs.LG2025

The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns

Elyes Hajji, Aymen Bouguerra, Fabio Arnez

Large Language Models (LLMs) are increasingly deployed in safety-critical domains, yet remain susceptible to hallucinations. While prior works have proposed confidence representati…

cs.CV2025

FindMeIfYouCan: Bringing Open Set metrics to , and Out-of-Distribution Object Detection

Daniel Montoya, Aymen Bouguerra, Alexandra Gomez-Villa +1

State-of-the-art Object Detection (OD) methods predominantly operate under a closed-world assumption, where test-time categories match those encountered during training. However, d…