AEGIS localizes sparse semantic-injecting attention heads in diffusion models and applies similarity-aware repulsion at those heads to block visual synonym jailbreaks while preserving benign generation.
A mathematical framework for transformer circuits,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Mix-MoE applies separate LM and MT expert groups in two post-pretraining stages with Fourier-enhanced routing to reduce parameter interference and improve multilingual MT over baselines.
citing papers explorer
-
AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models
AEGIS localizes sparse semantic-injecting attention heads in diffusion models and applies similarity-aware repulsion at those heads to block visual synonym jailbreaks while preserving benign generation.
-
Mix-MoE: Improving Multilingual Machine Translation of Large Language Models through Mixed MoEs
Mix-MoE applies separate LM and MT expert groups in two post-pretraining stages with Fourier-enhanced routing to reduce parameter interference and improve multilingual MT over baselines.