Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Neural Collapse Is Forbidden: Information Floors in Language Models
Bruno Abrahao
Within-class variance in language-model representations is commonly read as incomplete neural collapse. We argue it is allocated information storage, and that the allocation obeys…
cs.LG2026
GEODE: Angle-Adaptive OOD Detection with Universal Scorer Compatibility
Bruno Abrahao
Outlier Exposure (OE) is among the strongest training-based OOD detectors on standard benchmarks but exhibits scorer-dependent tradeoffs (e.g., strong on MSP, weak on KNN) and requ…
cs.LG2021
Model Rectification via Unknown Unknowns Extraction from Deployment Samples
Bruno Abrahao, Zheng Wang, Haider Ahmed +1
Model deficiency that results from incomplete training data is a form of structural blindness that leads to costly errors, oftentimes with high confidence. During the training of c…