AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

MJEPA: A Simple and Scalable Joint-Embedding Predictive Architecture for Audio-Visual Learning

Revant Teotia, Adrien Bardes, Michael Rabbat, Sumit Chopra, Matthew Muckley, Nicolas Ballas

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Self-supervised audio-visual representation learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
share one encoder across audio and video without cross-modal alignment (ablation)Unimodal baselines · AudioSet-20K (audio input)mAP: 30.87 -> 28.70Hurt
share one encoder across audio and video without cross-modal alignment (ablation)Unimodal baselines · AudioSet-20K (video input)mAP: 19.84 -> 17.90Hurt
add cross-modal prediction losses to the shared encoder (ablation)Shared encoder · AudioSet-20K (audio input)mAP: 28.70 -> 33.52Improved
add cross-modal prediction losses to the shared encoder (ablation)Shared encoder · AudioSet-20K (video input)mAP: 17.90 -> 19.58Improved
add cross-modal prediction losses to the shared encoder (ablation)Shared encoder · AudioSet-20K (audio-video input)mAP: 32.38 -> 36.34Improved
add joint audio-video encoding with its intra and cross-modal losses (ablation)Shared encoder + cross-modal alignment · AudioSet-20K (audio input)mAP: 33.52 -> 38.89Improved
add joint audio-video encoding with its intra and cross-modal losses (ablation)Shared encoder + cross-modal alignment · AudioSet-20K (video input)mAP: 19.58 -> 25.38Improved
add joint audio-video encoding with its intra and cross-modal losses (ablation)Shared encoder + cross-modal alignment · AudioSet-20K (audio-video input)mAP: 36.34 -> 42.90Improved
add video-only VideoMix2M data (ablation)MJEPA ViT-L · AudioSet-20K (audio input)mAP: 38.89 -> 40.00Improved
add video-only VideoMix2M data (ablation)MJEPA ViT-L · AudioSet-20K (video input)mAP: 25.38 -> 29.63Improved
scale the encoder from ViT-L to ViT-g (ablation)MJEPA + data scaling · AudioSet-20K (audio-video input)mAP: 45.31 -> 45.44Improved
add AudioSet audio-visual data to video-only training (ablation)MJEPA ViT-L · Kinetics-400top-1 accuracy (%): 80.6 -> 84.7Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy