← Back to all news
arXiv Machine Learning By Zhe Feng, Longfei Liu, Wei Liu, Kai Chen, Jiangjiang Kong, Wei Zhou, Yifeng Qian, Dexiong Chen, Xuanlong Yu, Xi Shen

GTR: Gated Token Recurrence for Efficient Dense Prediction

Read the original on arXiv Machine Learning →

The paper introduces Gated Token Recurrence (GTR), a softmax‑free recurrent vision backbone that replaces global softmax attention with gated linear attention, alternating scan directions, and enhanced SwiGLU blocks. GTR is distilled from a DINOv3 teacher using only final‑layer patch‑token alignment, and achieves strong performance on COCO object detection (58.9 box AP) with very low latency (1.908 ms on an RTX 4090). The backbone also transfers to multiple dense prediction tasks and runs efficiently on edge hardware via a specialized CUDA operator and TensorRT deployment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computer Vision
Oct 9

RT-DETRv4: Painlessly Furthering Real-Time Object Detection with Vision Foundation Models

RT-DETRv4 introduces a cost‑effective distillation framework that leverages Vision Foundation Models to improve lightweight real‑time object detectors. The method uses a Deep Semantic Injector to embed high‑level VFM representations into deep detector layers and a Gradient‑guided Adaptive Modulation strategy to adjust semantic transfer intensity based on gradient norms. These techniques yield consistent performance gains across DETR‑based models without adding inference overhead, achieving state‑of‑the‑art COCO AP scores at high FPS.

By Zijun Liao, Yian Zhao, Xin Shan, Yu Yan, Chang Liu, Lei Lu, Xiangyang Ji, Jie Chen
computer-visionefficiencybenchmarks
More like this →
arXiv Computer Vision
Oct 27

VGGT-$\Omega$

arXiv:2605.15195v2 Announce Type: replace Abstract: Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also prov...

By Jianyuan Wang, Minghao Chen, Shangzhan Zhang, Nikita Karaev, Johannes Sch\"onberger, Patrick Labatut, Piotr Bojanowski, David Novotny, Andrea Vedaldi, Christian Rupprecht
multimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Oct 23

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

EdgeCrafter presents a compact Vision Transformer framework tailored for edge dense prediction tasks such as object detection, instance segmentation, and human pose estimation. By employing task-specialized distillation and an edge-friendly encoder-decoder design, the ECDet backbone achieves 51.7 box AP with under 10 M parameters, while its extensions reach 48.4 mask AP and 74.8 keypoint AP using only COCO annotations. Pretraining on Objects365 further boosts performance, demonstrating that lightweight ViTs can compete with CNN-based models on resource-constrained devices.

By Longfei Liu, Yongjie Hou, Yang Li, Qirui Wang, Youyang Sha, Yongjun Yu, Yinzhi Wang, Peizhe Ru, Xuanlong Yu, Xi Shen
llmscomputer-visionefficiency
More like this →