Papers

Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.

Filtered by domain: streaming-video-understandingClear

Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams

26 Oct 2026

Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how reliably these models connect stream evidence and user needs to timely, sustained…

Omni models Streaming Video Understanding Video Understanding

70.1/h

Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 22,760 papers.