jdopensource/JoyAI-VL-Interaction
JoyAI-VL-Interaction Dataset The first open, vision-driven real-time interaction model β it watches a live video stream and decides on its own when to speak, stay silent, or delegate. π Paper Β· π Project Page & Demos Β· π» GitHub Β· π€ Paper Page Dataset Description This repository contains the aligned interaction training data released as part of the JoyAI-VL-Interaction project. The dataset consists of over 4 million time-aligned video-language interactionβ¦ See the full description on the dataset page: https://huggingface.co/datasets/jdopensource/JoyAI-VL-Interaction.
| Author / organization | jdopensource |
|---|---|
| License (as declared) | apache-2.0 |
| Downloads | 509 (as reported by Hugging Face) |
| Likes | 25 |
| Created | 19 June 2026 |
| Last updated at source | 23 June 2026 |
Recent changes
- 16 Oct 2026 Description: none β JoyAI-VL-Interaction Dataset The first open, vision-driven real-time interaction model β it watches a live video stream and decides on its own when to speak, stay silent, or delegate. π Paper Β· π Project Page & Demos Β· π» GitHub Β· π€ Pape
- 16 Oct 2026 Topics added task_categories:video-text-to-text removed safetensors, qwen3_vl, video-text-to-text
- 16 Oct 2026 Task: video-text-to-text β none
Changes detected by Silytics between refreshes of the source.
More from jdopensource
Silytics shows public metadata from Hugging Face and links to the original. Information may be incomplete or out of date. Last refreshed 16 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.