DinoLink - A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception: Provenance, Traceability, and Auditability
Keywords:
resource-efficient autonomous perception, data provenance and auditability, evidence synthesis, reproducibility, research evaluationAbstract
A defensible evidence chain must show where data originated, how records were transformed, and which decisions can be reconstructed after publication. This structured evidence review evaluates "DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception" alongside nine author-disjoint, topically matched publications in resource-efficient autonomous perception. It compares construct definitions, evaluation choices, operating assumptions, and reported limitations instead of treating bibliographic similarity as empirical equivalence. Viewed through data provenance and auditability, the map separates claims supported by the available record from questions that still require full-text extraction, replication, or new experiments. The synthesis is interpretive rather than meta-analytic and therefore does not present a pooled effect estimate or a new causal result. The resulting agenda emphasizes versioned data lineage, transformation logs, access controls, and auditable links between evidence and decisions.
References
- Zhu, T., Que, H., Yao, H., Xu, H., & Bao, Z. (2026). DinoLink: A Token-Centric Representation Compression Framework for Bandwidth-Constrained Collaborative V2X Perception. arXiv. https://doi.org/10.48550/arXiv.2606.26398
- Costa, B.-T., Pereira, C., & Maykol Pinto, A. (2025). PerceptNet-V2X: Perception Network for Vehicle to Everything Scenarios in Autonomous Driving. IEEE Access, 13, 182645-182660. https://doi.org/10.1109/access.2025.3624285
- Chandrashekhar, B., & Shakkeera, L. (2025). Reinforcement learning in Autonomous vehicle communication under V2X Framework using edge computing and Privacy-Preserving AI. 2025 2nd International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS), 1-8. https://doi.org/10.1109/iccams65118.2025.11234562
- Guo, A., Zhang, S., Tang, E., Gao, X., Pang, H., Tian, H., Mu, Y., Wen, W., Fang, C., & Chen, Z. (2025). When Autonomous Vehicle Meets V2X Cooperative Perception: How Far Are We?. 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE), 1169-1181. https://doi.org/10.1109/ase63991.2025.00101
- Asaju, B.-J., Jung, W., & Wakili, A. (2025). A Survey of Multi-Layered Cybersecurity Threats in Connected and Autonomous Vehicles: Risks from Edge Computing and V2x Protocols. . https://doi.org/10.2139/ssrn.5260375
- Garcia, C.-E., Camana, M.-R., Mohammad, A.-B., Querol, J., & Chatzinotas, S. (2024). Edge Learning Optimization in Task-Oriented NOMA Communications for Autonomous Vehicle Perception. 2024 IEEE Wireless Communications and Networking Conference (WCNC), 1-6. https://doi.org/10.1109/wcnc57260.2024.10570514
- Wang, S. (2025). Edge Intelligence for V2X Communications: Advances in Collaborative Perception and Privacy Preservation. Journal of Big Data and Computing, 3(4), 73-81. https://doi.org/10.62517/jbdc.202501409
- Richards, E., Thapa, B., & Mashayekhy, L. (2025). Edge-Enabled Collaborative Object Detection for Real-Time Multi-Vehicle Perception. 2025 IEEE International Conference on Edge Computing and Communications (EDGE), 13-22. https://doi.org/10.1109/edge67623.2025.00011
- Roy, A. (2025). Beyond V2X: A Review of Large Language Models in In-Vehicle Autonomous Driving Systems. . https://doi.org/10.36227/techrxiv.175571972.28517288/v1
- Soorchaei, B.-E., Raftari, A., & Fallah, Y.-P. (2025). Extensible Heterogeneous Collaborative Perception in Autonomous Vehicles with Codebook Compression. Robotics, 14(12), 186. https://doi.org/10.3390/robotics14120186
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Convergence in Science and Society
This work is licensed under a Creative Commons Attribution 4.0 International License.