JoyAI-VL-Interaction: 8B real-time vision-driven interaction model

Loading video
Loading videoJD Open Source releases JoyAI-VL-Interaction, an 8B-scale real-time vision-driven interaction model under Apache 2.0, averaging 57.53 across 26 video understanding benchmarks, outperforming peers.
Category: research
Author: @ModelScope2022
Date: 2026-07-23T00:00:00
Duration: 185.063s





