Google's StreamVibe: proactive streaming video agents that track evolving user intent
google · hf · 2026-10-27
Google and researchers from UCSB, Stanford, Oxford and others introduce StreamVibe, shifting vision-language models from passive offline understanding to proactive, intent-aware online interaction.
Key components:
- StreamVibe-Bench: a new benchmark with 4.1K evaluation and 85K training samples spanning explicit, implicit, and dynamic user intents;
- StreamVibe-VL: a streaming proactive model that infers implicit intents from continuous video observations and adapts interactions as intents evolve;
- StreamVibe-Harness: maintains user intents as persistent states with flexible lifecycles via hierarchical memory tracking intent and environmental state.
Experiments show StreamVibe-VL preserves strong general video understanding while improving proactive interaction.
More from Research
- Researcher argues DoM steering is no more transparent than gradient-based vector selection — johnhewtt · 2026-10-27
- DoM steering working at a localized layer doesn't prove localization is correct — johnhewtt · 2026-10-27
- MPI's Alien Recombination method finds concept blends beyond human cognitive reach — profjamesevans · 2026-10-27
- Podcast: James Evans on why reasoning models simulate societies of thought — profjamesevans · 2026-10-27
- PikasekoHash-256: experimental AVX-512 hash function hits ~24 GB/s on one Zen 5 core — ssh4net · 2026-10-27
- DoM steering success isn't strong evidence for interpretability localization — johnhewtt · 2026-10-27