arXiv:2604. 03919v2 Announce Type: replace-cross Abstract: We present the first systematic study of Sparse Autoencoders (SAEs) on video representations.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
arXiv:2607. 17770v1 Announce Type: cross Abstract: Within Explainable Artificial Intelligence, mechanistic interpretability uses Sparse Autoencoders (SAEs) to extract more interpretable features from neural representations.
arXiv:2606. 07687v1 Announce Type: cross Abstract: Video world models are increasingly used to provide predictive visual representations, yet it remains unclear which pretraining signals induce action-relevant structure in their latent spaces.
arXiv:2606. 13289v1 Announce Type: cross Abstract: Holistic visual tokenizers are fundamental to unified multimodal models (UMMs) as they map diverse visual inputs into a unified representation space.
arXiv:2606. 17437v1 Announce Type: cross Abstract: Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges.
arXiv:2410. 19553v2 Announce Type: replace-cross Abstract: This paper explores the impact of occlusions in video action detection.
arXiv:2607. 12774v1 Announce Type: cross Abstract: This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition.