FreeFlow is a hierarchical transformer for optical flow estimation that eliminates traditional flow-specific inductive biases such as correlation volumes and feature warping. It relies on a single feed-forward encoder–decoder architecture that incorporates window attention, shifted-window attention, and reduced-resolution global attention. This design allows the model to scale with capacity while achieving state‑of‑the‑art accuracy on Sintel, KITTI‑2015, and Spring benchmarks, all while remaining memory efficient at 1080p inference.
arXiv:2606. 27449v1 Announce Type: new Abstract: Multi-head attention conventionally partitions the hidden dimension equally across all heads at every layer, enforcing an identical representational subspace dimension (dh = dmodel/h) throughout the models depth.
By Shubham Aggarwal
arXiv:2609.39748v1 Announce Type: new
Abstract: Scaling has become a primary driver of progress in language and vision foundation models, yet its role in precise correspondence matching remains under...
By Yongjian Zhang, Longguang Wang, Zhuo Song, Zhiheng Fu, Liang Lin, Yulan Guo
arXiv:2607. 00774v1 Announce Type: cross Abstract: Recent recursive Transformer studies have primarily reused shared parameters across computation steps to construct compact, parameter-efficient models.
By Sang In Lee, Jihun Park
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.
By Ruyi Xu, Guangxuan Xiao, Yukang Chen, Liuning He, Yao Lu, Song Han
MoE-ViE introduces a Mixture-of-Experts vision encoder that scales efficiently for image and video understanding, outperforming dense counterparts across various sizes. The study shows fine‑grained MoE topologies provide significant gains, and proposes an auxiliary‑loss‑free balancing variant and a specialized MoE kernel to reduce inference latency. With frame‑level distillation and a novel freezing mechanism, the largest MoE‑ViE model matches state‑of‑the‑art zero‑shot performance while being 1.7× larger and 76% faster, and it outperforms other encoders when paired with a language model on both image and video benchmarks.
GaLe is a memory‑efficient technique that allows pretrained neural networks to run on resource‑constrained devices without retraining. It splits feature maps into a local exact component that keeps fine details and a global approximate component that preserves long‑range dependencies, enabling global operations and attention mechanisms typical of hybrid CNN‑transformer models. On ImageNet, GaLe matches exact‑inference accuracy while delivering up to 65% speedup and 90% RAM reduction on a Cortex‑M33, and it works across classification, detection, and generation tasks.
By Alberto Ancilotto, Elisabetta Farella
arXiv:2507.18405v3 Announce Type: replace-cross
Abstract: Vision Transformers (ViTs) face two limitations: the rigid resolution dependency of positional embeddings, which complicates cross-resolution...
By Simin Huo, Ning Li
arXiv:2404.06135v4 Announce Type: replace
Abstract: The Transformer architecture has achieved remarkable success in natural language processing and high-level vision tasks over the past few years. Ho...
By Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien, Ming-Hsuan Yang
arXiv:2607. 14898v1 Announce Type: cross Abstract: Real-time video generation demands fast decoding as much as fast denoising, yet current latent video diffusion models rely on 3D convolutional decoders that are slow and memory-intensive at high resolutions or for long video.
By Minguk Kang, Suha Kwak
arXiv:2509.22650v3 Announce Type: replace
Abstract: Most existing approaches to referring segmentation achieve strong performance only through fine-tuning or by composing multiple pre-trained models,...
By Anna Kukleva, Enis Simsar, Alessio Tonioni, Muhammad Ferjad Naeem, Federico Tombari, Jan Eric Lenssen, Bernt Schiele
PixelUMM is an encoder‑free model that unifies image and video understanding and generation directly in pixel space. It represents images as spatial patches and videos as spatiotemporal tubelets, feeding both through single‑layer linear projections into a shared multimodal backbone. The Mixture‑of‑Transformers architecture blends shared attention with task‑specific parameters, enabling autoregressive text prediction, pixel‑space flow matching, and clean‑pixel video generation, and experiments show competitive performance across tasks while providing design insights for future pixel‑space multimodal models.
By Cong Wei, Xuanchi Ren, Bryan Chu, Weiming Ren, Huan Ling, Jiahui Huang, Laura Leal-Taix\'e, Sanja Fidler, Wenhu Chen, Zian Wang, Jay Zhangjie Wu