AudioVisual-Caption/ASID-Captioner-3B
Image-Text-to-Text • 5B • Updated
• 646 • 3
AI & ML interests
Video Understanding, Audio-Visual, Multimodal LLMs, Video Captioning, Instruction Tuning, Dataset Curation, Qwen-based, Open-source, Fully-Open-MLLMs
Recent Activity
View all activity
Papers
View all Papers
Organization Card
ASID-Caption
[🏠 Homepage] [📖 Arxiv Paper] [🤗 Models & Datasets] [💻 Code]
We build ASID-Caption, a data-and-model suite for fine-grained audiovisual video understanding.
Our goal is to move beyond “one video → one generic caption” by providing attribute-structured supervision and quality-verified annotations, enabling models to produce more complete, more controllable, and more temporally consistent descriptions that cover both visual content and audio cues.
What we release
- ASID-1M: a large-scale collection of attribute-structured audiovisual instructions with both single-attribute and all-attributes training formats.
- ASID-Verify: a scalable curation pipeline that generates, ensembles, verifies, and refines annotations to improve semantic and temporal consistency.
- ASID-Captioner: Qwen2.5-Omni-based audiovisual captioning models fine-tuned on ASID-1M.
Research interests
- Video understanding & video captioning
- Audio-visual learning
- Multimodal LLMs / instruction tuning
- Data curation, verification, and quality control