SRCD distills head-class CAMs to resist shortcuts on tail classes
The method aggregates a few head-class activation maps into a teacher and reports consistent gains on long-tailed benchmarks.
4 stories, newest first · one card per story
The method aggregates a few head-class activation maps into a teacher and reports consistent gains on long-tailed benchmarks.
Source-side training dynamics can prospectively predict later out-of-distribution model failure.
Non-invasive brain-to-text models used word-timing shortcuts; removing them improves decoding.

Bristol researchers propose a drug-style dossier for testing medical AI reliability before clinical use.
Today 1.6K readers · 2.4K views · 775 reads · all time 189K views