arXiv:2608.22368v1 Announce Type: new Abstract: While linear attention is a compelling mechanism for high-resolution object detection due to its reduced cost for global token mixing, converting the S...
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:2609.09863v1 Announce Type: new Abstract: Choosing a deep learning architecture for label-free single-cell classification remains an open question, with microscopy benchmarks reporting conflict...
The paper introduces QK Product Steering, a data‑free, training‑free method that edits the query‑key product in vision‑language models to reduce object hallucination. By suppressing a few dominant singular modes in selected middle layers and mapping the edited product back to query weights, the approach lowers hallucination rates without affecting inference cost. Experiments on three GQA‑based VLMs show a 4.0% average reduction in CHAIR$_s$, with the effect localized to symmetric mutual‑attention channels.
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
arXiv:2607. 06918v1 Announce Type: cross Abstract: Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks.
arXiv:2607. 15745v1 Announce Type: new Abstract: Common practice when training Convolutional Neural Networks (CNNs) is to use randomly shuffled mini-batches.
arXiv:2608.22996v1 Announce Type: new Abstract: Vision-Language Models (VLMs) perform well on diverse vision-language tasks, but transformer-based visual encoders split images into fixed-resolution s...
arXiv:2606. 05740v1 Announce Type: new Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias.
Vision Transformers underperform convolutional networks when training data is scarce, and distilling convolutional inductive biases from a CNN teacher is an effective remedy that leaves the deployed model unchanged. General-purpose feature distillation, however, transfers little in this setting.
arXiv:2609.16656v1 Announce Type: new Abstract: State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision...
U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck representation is still dominated by a limited s...