mlsanityData to 7 Oct 2026

CABLE: Cloud-Assisted Bandwidth-efficient LMM-based Encoding for V2X Systems

arXiv 2606.19258 ↗First posted 17 Jun 2026cs.CV cs.ROcited by 0

On the map: Multimodal LLMs / vision-language models → Visual token pruning and efficiency

Abstract (arXiv)

Cloud-hosted large multimodal models (LMMs) can provide strong open-vocabulary perception for Vehicle-to-Everything systems, but naively transmitting full-resolution frames from edge to cloud causes severe communication overhead and high cloud-side prefill latency. We present CABLE, a cloud-assisted bandwidth-efficient LMM-based encoding framework for edge-cloud perception. CABLE propagates the previous cloud segmentation mask on the edge using ego-motion compensation, refines it with residual-motion cues, and consolidates disconnected regions via a corridor envelope to form a robust region of interest (ROI). Only ROI-masked images are uploaded, while the cloud segmentation output is fed back as the prior for the next frame, forming a mask-to-ROI-to-LMM feedback loop. Experiments on five datasets (nuScenes, WOD-ZB, Waymo, KITTI, and CADC) show consistent communication savings while largely preserving perception, achieving 73--87% ROI pixel-coverage reduction with 5--8× estimated LMM prefill speedup at a modest detection-quality trade-off relative to full-frame inference.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 32 of its 51 references that are in the map. First posted on arXiv 17 Jun 2026.

Builds on

32 of 51 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models22 Mar

Other references · 31

  1. 2023Segment Anythingcited by 8,158
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2024GPT-4o System Cardcited by 4,467
  5. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  6. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2022Token Merging: Your ViT But Fastercited by 995
  9. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
  10. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  11. 2022V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformercited by 320
  12. 2021OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communicationcited by 304
19 more
  1. 2020V2VNet: Vehicle-to-Vehicle Communication for Joint Perception and Predictioncited by 292
  2. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 270
  3. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  4. 2021Learning Distilled Collaboration Graph for Multi-Agent Perceptioncited by 194
  5. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  6. 2020When2com: Multi-Agent Perception via Communication Graph Groupingcited by 157
  7. 2022V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Drivingcited by 157
  8. 2020Who2com: Collaborative Perception via Learnable Handshake Communicationcited by 127
  9. 2019BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systemscited by 94
  10. 2023Collaborative Perception in Autonomous Driving: Methods, Datasets and Challengescited by 87
  11. 2020Canadian Adverse Driving Conditions Datasetcited by 86
  12. 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 79
  13. 2018Edge Intelligence: On-Demand Deep Learning Model Co-Inference with Device-Edge Synergycited by 50
  14. 2023Among Us: Adversarially Robust Collaborative Perception by Consensuscited by 37
  15. 2022BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computingcited by 28
  16. 2021Task-driven Semantic Coding via Reinforcement Learningcited by 25
  17. 2025CoLMDriver: LLM-based Negotiation Benefits Cooperative Autonomous Drivingcited by 13
  18. 2024OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detectioncited by 9
  19. 2024MCDS-VSS: Moving Camera Dynamic Scene Video Semantic Segmentation by Filtering with Self-Supervised Geometry and Motioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
  2. 2023Leveraging the Edge and Cloud for V2X-Based Real-Time Object Detection in Autonomous Driving
  3. 2026RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models
  4. 2026DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems
  5. 2026Bandwidth-adaptive Cloud-Assisted 360-Degree 3D Perception for Autonomous Vehicles
  6. 2026Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization
  7. 2026INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language Inference
  8. 2025When MLLMs Meet Compression Distortion: A Coding Paradigm Tailored to MLLMs