Audio-Visual Dataset Distillation aims to compress large-scale datasets into compact subsets while preserving the performance of the original data. However, conventional Distribution Matching (DM) methods struggle to capture intrinsic cross-modal alignment. Subsequent studies have attempted to introduce cross-modal matching, but two major challenges remain: (i) independently and randomly initialized encoders lead to inconsistent modality mapping spaces, increasing training difficulty; and (ii) direct interactions between modalities tend to damage modality-specific (private) information, thereby degrading the quality of the distilled data. T o address these challenges, we propose DA VDD, a pretraining-based decoupled audio-visual distillation framework. DA VDD leverages a diverse pre-trained bank to obtain stable modality features and uses a lightweight decoupler bank to disentangle them into common and private representations. T o effectively preserve cross-modal structure, we further introduce Common In-termodal Matching together with a Sample-Distribution Joint Alignment strategy, ensuring that shared representations are aligned both at the sample level and the global distribution level. Meanwhile, private representations are entirely isolated from cross-modal interaction, safeguarding modality-specific cues throughout distillation. Extensive experiments across multiple benchmarks show that DA VDD achieves state-of-the-art results under all IPC settings, demonstrating the effectiveness of decoupled representation learning for high-quality audio-visual dataset distillation.

The performance of image-based Reinforcement Learning (RL) agents can vary depending on the position of the camera used to capture the images. Training on multiple cameras simultaneously, including a first-person egocentric camera, can leverage information from different camera perspectives to improve the performance of RL. However, hardware constraints may limit the availability of multiple cameras in real-world deployment. Additionally, cameras may become damaged in the real-world preventing access to all cameras that were used during training. To overcome these hardware constraints, we propose Multi-View Disentanglement (MVD), which uses multiple cameras to learn a policy that is robust to a reduction in the number of cameras to generalise to any single camera from the training set. Our approach is a self-supervised auxiliary task for RL that learns a disentangled representation from multiple cameras, with a shared representation that is aligned across all cameras to allow generalisation to a single camera, and a private representation that is camera-specific. We show experimentally that an RL agent trained on a single third-person camera is unable to learn an optimal policy in many control tasks; but, our approach, benefiting from multiple cameras during training, is able to solve the task using only the same single third-person camera.