DECODE identifies and separately edits modality-specific neurons in MLLMs to prevent knowledge edits from reverting under unimodal queries.
Drifting Away from Truth: GenAI-Driven News Diversity Challenges LVLM-Based Misinformation Detection,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
This survey introduces the C5 Interaction Model as a unifying taxonomy to synthesize proactive detection methods for GenAI-enabled adversarial narratives across socio-technical and computational research streams.
citing papers explorer
-
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons in MLLMs
DECODE identifies and separately edits modality-specific neurons in MLLMs to prevent knowledge edits from reverting under unimodal queries.
-
Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey
This survey introduces the C5 Interaction Model as a unifying taxonomy to synthesize proactive detection methods for GenAI-enabled adversarial narratives across socio-technical and computational research streams.