2 citations · 3 across the 5 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language Models
Niccolò Ronchetti
Mitigating catastrophic risks from large language models requires excising hazardous operational capabilities, such as cyberwarfare exploitation and pathogen enhancement, without d…
cs.LG2024
Conditional Idempotent Generative Networks
Niccolò Ronchetti
We propose Conditional Idempotent Generative Networks (CIGN), a novel approach that expands upon Idempotent Generative Networks (IGN) to enable conditional generation. While IGNs o…