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.
By Kaustubh Kapil, Kishor P. Upla
arXiv:2606. 17961v1 Announce Type: cross Abstract: Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs.
By Andrea Santomauro, Luigi Portinale, Giorgio Leonardi
arXiv:2602. 03282v2 Announce Type: replace-cross Abstract: A common assumption in representation learning is that globally well-distributed embeddings support robust and generalizable representations.
By Jiwan Chung, Seon Joo Kim
arXiv:2603. 22278v2 Announce Type: replace-cross Abstract: Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to bind objects with their properties and spatial relations.
By Kelly Cui, Nikhil Prakash, Shoval Messica, Ayush Raina, David Bau, Antonio Torralba, Tamar Rott Shaham
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.
By Jin Yu, Juyoun Park
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.