[
    {
        "id": "osp-17082",
        "type": "article-journal",
        "title": "LeAVJEPA: A Minimalist Architecture for Audio-Visual Self-Supervised Learning",
        "author": [
            {
                "family": "Robson",
                "given": "Benjamin"
            },
            {
                "family": "Mentu",
                "given": "Santeri"
            },
            {
                "family": "Zhao",
                "given": "Wenshuai"
            },
            {
                "family": "Solin",
                "given": "Arno"
            }
        ],
        "URL": "https://omanscience.com/en/articles/leavjepa-a-minimalist-architecture-for-audio-visual-self-supervised-learning",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Prior audio-visual self-supervised learning methods rely on mechanisms such as EMA target encoders, prediction heads, reconstruction decoders, and contrastive losses. We introduce LeAVJEPA, the first audio-visual encoder trained under LeJEPA's collapse-free objective. A single early-fusion Vision Transformer processes audio, video, and joint audio-video inputs. Modality dropout treats a missing modality as another view of the same event, making cross-modal alignment implicit in the objective. The model aligns global embeddings with modality-specific local embeddings, and SIGReg prevents representational collapse. A controlled ablation identifies modality dropout as the key mechanism for audio-visual alignment. Despite the architectural simplicity, LeAVJEPA reaches 36.0 mAP on AudioSet-20K and 91.3% accuracy on ESC-50 under frozen evaluation. After fine-tuning, it reaches 61.1% accuracy on VGGSound, and its embeddings support zero-shot audio-visual retrieval."
    }
]