Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions
This addresses the need for better video understanding models in AI by providing a scalable data curation pipeline and dataset, though it is incremental as it builds on existing MLLM methods.
The paper tackled the problem of limited video-instruction data for universal video understanding by introducing ASID-1M, a structured dataset with fine-grained annotations, and ASID-Captioner, a model trained on it, which improved caption quality and achieved competitive performance with Gemini-3-Pro on seven benchmarks.
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.