arXiv Computer Vision
Rethinking Vision Architectures with Gated Linear Attention and KAN
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Machine Learning
Jun 5
Exact Linear Attention
arXiv:2605. 18848v3 Announce Type: replace Abstract: This paper introduces Exact Linear Attention (ELA), a mechanism that achieves linear computational complexity for Transformer attention by exploiting the exact decomposition property of kernel functions, thereby eliminating approximation error.
arXiv Computer Vision
2d ago
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
arXiv:2605.12491v2 Announce Type: replace Abstract: Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design im...
arXiv AI
Aug 21
Core-KAN: Continuous Vision Kernels with Kolmogorov-Arnold Networks
arXiv:2608. 19817v1 Announce Type: cross Abstract: Conventional convolutional kernels are typically defined on fixed discrete grids, limiting their ability to accommodate heterogeneous local structures.
arXiv Computer Vision
Sep 23
Shallow to Deep: Aligning Token Pruning with Stage-wise Roles in LVLMs
The paper introduces STD, a hierarchical token pruning framework for Large Vision‑Language Models that aligns pruning strategies with the functional roles of different network stages. By using high‑frequency spectral analysis in shallow layers, Gaussian‑smoothed attention in intermediate layers, and a stability‑adaptive trigger in deep layers, STD preserves essential visual information while aggressively reducing token counts. Experiments demonstrate that STD outperforms existing pruning methods, achieving up to 94.4% token reduction and a 3.9× speed‑up on LLaVA‑NeXT‑7B.
arXiv Machine Learning
Jun 2
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
arXiv:2606. 00746v1 Announce Type: cross Abstract: Vision foundation models are bottlenecked by the quadratic cost of self-attention, which limits usable resolution and increases the cost of large-scale pretraining.
arXiv AI
Jun 2
On the Limits of Token Reduction for Efficient Unified Vision Language Training
arXiv:2606. 01503v1 Announce Type: cross Abstract: Unified vision-language models (VLMs) integrate visual understanding and visual generation within a single autoregressive backbone, but their joint training is computationally expensive and largely overlooked from an efficiency perspective.