Residual Community Prototypes Under-Reject Held-Out Malware Families in FCG-MFD
Study finds Louvain community features fail to stably reject held-out malware families in FCG-based open-set recognition versus simple uncertainty.
Stories per day · 30 days
2 RSS
3 stories, newest first · one card per story
Stories tagged #evaluation-methodology
What Does an LLM-Agent Leaderboard Rank Actually Compare?
A methodological study shows close LLM-agent leaderboard rank gaps on SWE-bench and similar benchmarks often do not support superiority claims.
Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy
Researchers added Greek to the Cosmos3 vision-language-action policy using only machine-rephrased instructions, finding bilingual training reaches roughly two fifths of English performance.