PulseAugur
LIVE 14:50:12
research · [1 source] ·
0
research

Meta's Apollo model achieves SOTA open-weights video understanding up to one hour

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 1 source

Meta AI has released Apollo, an open-weight model capable of understanding video content up to one hour in length. This model achieves state-of-the-art performance on video understanding benchmarks. Apollo's architecture allows it to process significantly longer video inputs than previous models. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

RANK_REASON Release of an open-weight model with novel capabilities from a major AI lab.

Read on Smol AINews →

COVERAGE [1]

  1. Smol AINews TIER_1 ·

    Meta Apollo - Video Understanding up to 1 hour, SOTA Open Weights

    **Meta** released **Apollo**, a new family of state-of-the-art video-language models available in **1B, 3B, and 7B** sizes, featuring "Scaling Consistency" for efficient scaling and introducing **ApolloBench**, which speeds up video understanding evaluation by **41×** across five…

RELATED TOPICS