Apple researchers launch LVSum, a benchmark for timestamp-aware long video summarization
Apple ML Research · rss · 2026-07-20
- Apple ML Research introduces LVSum, a benchmark for timestamp-aware long video summarization.
- The benchmark targets a core failure mode in multimodal LLMs: keeping summaries both semantically correct and temporally grounded across long videos.
- LVSum includes 72 videos across 13 domains, with an average length of 16 minutes.
- Each video is human-annotated with up to 10 summaries that include temporal references, enabling fine-grained evaluation of alignment over time.
More from Multimodal
- Building an entire AI-generated cinematic world with CineMap and TapNow_AI — egeberkina · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26
- Bokeh Cosmic Nebula prompt template: out-of-focus orbs mimic interstellar clouds — LudovicCreator · 2026-10-26