Mistral-Nemo

Researchers propose a value-of-information router for block-sparse attention that dynamically doubles the kept key blocks when the top-k selection is uncertain, improving recall on LongBench-v2 from 0…

An independent researcher found that existing indirect prompt injection benchmarks like BIPIA, InjecAgent, and AgentDojo may produce unreliable scores due to reliance on LLM-judges and evaluation of e…