# DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception

Source: [DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception](<https://www.sota2.com/research/paper/6a3e0770206542251d7cb39e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-02T05:00:13.059Z

Authors: Tianle Zhu, Haohua Que, Handong Yao, Hongyi Xu, Zhipeng Bao

Published: 2026-06-24T21:31:13.000Z

## Abstract

High-precision remote perception is often hindered by the severe bandwidth constraints of Vehicle-to-Everything (V2X) networks. We propose \\textit{DinoLink}, a token-centric compression framework that replaces raw pixel streaming with discrete semantic communication for vehicle-cloud collaborative inference. DinoLink employs a dual-sparsity architecture: a saliency-aware selector prunes redundant background tokens, while a Residual Vector Quantization (RVQ) module collapses features into compact codebook indices. By transmitting only lightweight indices and positional priors, DinoLink achieves a $139\\times$ bitrate reduction compared to uncompressed transmission while maintaining a competitive 32.8\\% mAP on the nuScenes dataset. Deployment simulations further demonstrate a $34.5\\times$ acceleration in narrow-band environments, such as LoRa. Our results substantiate DinoLink as a robust, bandwidth-efficient frontend for high-fidelity remote perception in constrained V2X scenarios. The code is publicly available at https://github.com/UGA-MOBILITY-LAB/dino\_link.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Object Detection on nuScenes (5,000 image subset)](<https://www.sota2.com/research/sota/object-detection-on-nuscenes-5-000-image-subset.md>): Object Detection; nuScenes 5,000 image subset; BPP: 0.021.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.26398>)

[PDF](<https://arxiv.org/pdf/2606.26398.pdf>)