arXiv:2603. 13994v2 Announce Type: replace-cross Abstract: Vision foundation models trained with self-supervised objectives achieve strong performance across diverse tasks and exhibit emergent object segmentation properties.
Video object segmentation (VOS) is a fundamental task in video understanding, requiring accurate delineation and consistent tracking of objects across frames. While supervised methods achieve strong performance, they rely on densely annotated datasets that are costly to obtain and have limited domain coverage.
arXiv:2607. 02404v1 Announce Type: cross Abstract: Image encoders trained with LeJEPA can deliver strong features for downstream tasks, but, like other image-level self-supervised methods, typically require large training datasets.
arXiv:2607. 09024v1 Announce Type: cross Abstract: Driven by next-token prediction, NLP shifted from task-specific models into powerful generalist foundation models.
arXiv:2606. 23885v1 Announce Type: cross Abstract: Representation alignment has emerged as an effective approach to improve Multimodal Large Language Models (MLLMs) by regularizing their internal representations toward those of an external vision encoder.
arXiv:2607. 02386v1 Announce Type: cross Abstract: While Vision Transformers have achieved remarkable success across computer vision and language applications, the geometric evolution of their internal representations throughout training remains insufficiently understood.
Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut demonstrates that a Gated CNN block can match or exceed VMamba on image classification, questioning the necessity of SSMs for vision.
arXiv:2607. 18625v1 Announce Type: cross Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones.
arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.
arXiv:2308. 06035v4 Announce Type: replace Abstract: Humans routinely draw on visual context to predict upcoming words.
arXiv:2608. 10195v1 Announce Type: cross Abstract: Human vision organizes what it sees into wholes: same-colored points group into series, similar marks cohere into categories, and shapes complete into recognizable objects.
arXiv:2407. 21311v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data.
arXiv:2606. 28399v1 Announce Type: cross Abstract: The structure of human visual representations underpins our capacity for adaptive behaviour.