2 papers
cs.CR2026
PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents
He Zhang, Feilong Li, Dingning Long +5
Smart-home assistants increasingly use multimodal large language models (MLLMs) that perceive video and audio directly. This raises a safety question specific to the home: can the…
cs.IR2026
LLM-Based Generative Retrieval for Snapchat Content Recommendation
Liam Collins, Jiwen Ren, Donald Loveland +19
Pretrained large language models (LLMs) are promising retrieval engines because they combine rich semantic priors, strong sequence modeling capabilities, and favorable scaling beha…