Visual agents must turn video observations into timely decisions to track progress and choose what to do next. Building on the emerging System One paradigm, we introduce VideoJev, a family of models that cast video understanding and interaction as structured decision tasks.
ORIGINAL PAPER
VideoJev: System One Model for Video Understanding and Interaction
WHAT WE KNOW
We adapt pretrained multimodal large language models (MLLMs) by replacing autoregressive answer decoding with a shared head that scores temporal intervals and textual options against video evidence. These scores yield event spans or answer choices, unifying temporal grounding and multiple-choice video question answering. This combines the semantic flexibility of MLLMs with efficient decisions that agents can use directly.
WATCH NEXT
Review the primary source, validate the main result, and establish whether any listed-company transmission is direct.
EVIDENCE
What the evidence supports so far
Research signals
inference-efficiency
multimodal
agent
What remains unverified
The full methodology, effect size, and limitations still require analyst review.
Company impact remains unverified until a direct economic transmission is established.