From the 1 of 5 linked papers with an AI index.
1 citations · 1 across the 3 of their papers we have counts for
5 papers
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…
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…
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…
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…
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…