Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
Lists
Only you see this
Abstract
Universal video understanding requires modeling fine-grained visual and audio information over time in diverse real-world scenarios. However, the performance of existing models is primarily constrained by video-instruction data that represents complex audiovisual content as single, incomplete descriptions, lacking fine-grained organization and reliable annotation. To address this, we introduce: (i) ASID-1M, an open-source collection of one million structured, fine-grained audiovisual instruction annotations with single- and multi-attribute supervision; (ii) ASID-Verify, a scalable data curation pipeline for annotation, with automatic verification and refinement that enforces semantic and temporal consistency between descriptions and the corresponding audiovisual content; and (iii) ASID-Captioner, a video understanding model trained via Supervised Fine-Tuning (SFT) on the ASID-1M. Experiments across seven benchmarks covering audiovisual captioning, attribute-wise captioning, caption-based QA, and caption-based temporal grounding show that ASID-Captioner improves fine-grained caption quality while reducing hallucinations and improving instruction following. It achieves state-of-the-art performance among open-source models and is competitive with Gemini-3-Pro.
BibTeX
@misc{li2026towards,
author = {Yunheng Li and Hengrui Zhang and Meng-Hao Guo and Wenzhao Gao and Shaoyong Jia and Shaohui Jiao and Qibin Hou and Ming-Ming Cheng},
title = {{Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions}},
year = {2026},
eprint = {2602.13013},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2602.13013},
}