Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos

2026-07-17

AI Summary

Existing audio-visual large models struggle to effectively comprehend long-duration, complex real-world content. To address this limitation, this work proposes an open audio-visual large language model that jointly models cross-modal, temporal, and compositional semantics in long videos. The approach leverages a newly curated Audio-Visual-Skills dataset, employs a three-stage progressive curriculum training strategy, and introduces a temporally aligned audio-visual interleaved chain-of-thought reasoning framework. This methodology substantially enhances both performance and interpretability in long-form video understanding, outperforming existing open-source models by significant margins across more than fifteen multimodal benchmarks. Notably, it even surpasses certain larger closed-source systems on specific tasks, demonstrating exceptional generalization capability and practical potential.

Abstract

We present Audio-Visual Flamingo (AV-Flamingo), a fully open state-of-the-art audio-visual large language model (AV-LLM) for joint understanding and reasoning over audio, images, and long-form videos. Unlike prior AV-LLMs that primarily focus on short clips, AV-Flamingo is designed for understanding and reasoning over long and complex real-world (audio-visual) videos. To support this, we make three key contributions: (i) Audio-Visual-Skills, a large-scale collection of real-world videos with ~7M caption and question-answer training instances designed to emphasize temporal, compositional, and cross-modal audio-visual reasoning; (ii) a novel three-stage curriculum that progressively trains the model from short-range perception to long-horizon multi-event reasoning; and (iii) Temporal Audio-Visual Interleaved Chain-of-Thought, a reasoning framework that explicitly grounds intermediate reasoning steps to timestamps in long audio-visual streams, improving temporal alignment and interpretability. Extensive experiments across 15+ audio-visual, omni-modal, audio, and vision benchmarks show that AV-Flamingo outperforms similarly sized open models by clear margins and remains highly competitive with, and in some cases surpasses, much larger open-weight and closed models, particularly on long and complex real-world audio-visual understanding and reasoning tasks. Beyond benchmark performance, AV-Flamingo exhibits strong real-world utility and transfers well to unseen tasks, highlighting its robustness and generalization ability.

Problem

• audio-visual understanding
• long-form videos
• complex videos
• temporal reasoning
• cross-modal reasoning

Innovation

• audio-visual large language model
• long-form video understanding
• temporal reasoning
• cross-modal alignment
• curriculum learning