# EffiComm: Bandwidth Efficient Multi Agent Communication

arXiv: https://arxiv.org/abs/2507.19354 · HTML: https://mlsanity.com/paper/2507.19354/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 17 of its 28 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

## Builds on (most cited first, 17 of 17)

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Scaling Vision with Sparse Mixture of Experts](https://mlsanity.com/paper/2106.05974/) (2021)
- [V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer](https://mlsanity.com/paper/2203.10638/) (2022)
- [OPV2V: An Open Benchmark Dataset and Fusion Pipeline for Perception with Vehicle-to-Vehicle Communication](https://mlsanity.com/paper/2109.07644/) (2021)
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2012.10992/) (2020)
- [Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps](https://mlsanity.com/paper/2209.12836/) (2022)
- [Learning Distilled Collaboration Graph for Multi-Agent Perception](https://mlsanity.com/paper/2111.00643/) (2021)
- [F-Cooper: Feature based Cooperative Perception for Autonomous Vehicle Edge Computing System Using 3D Point Clouds](https://mlsanity.com/paper/1909.06459/) (2019)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction](https://mlsanity.com/paper/2303.10552/) (2023)
- [BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities](https://mlsanity.com/paper/2310.14702/) (2023)
- [InsightDrive: Insight Scene Representation for End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.13047/) (2025)
- [VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection](https://mlsanity.com/paper/2303.10975/) (2023)
- [Select2Col: Leveraging Spatial-Temporal Importance of Semantic Information for Efficient Collaborative Perception](https://mlsanity.com/paper/2307.16517/) (2023)
- [Collaborative Perception Datasets in Autonomous Driving: A Survey](https://mlsanity.com/paper/2404.14022/) (2024)

## Built on by (most cited first, 2 of 2)

- [SlimComm: Doppler-Guided Sparse Queries for Bandwidth-Efficient Cooperative 3-D Perception](https://mlsanity.com/paper/2508.13007/) (2025)
- [Dense Coverage, Sparse Refinement: Byte-Constrained Cooperative Perception](https://mlsanity.com/paper/2609.29456/) (2026)

## Abstract (arXiv)

Collaborative perception allows connected vehicles to exchange sensor information and overcome each vehicle's blind spots. Yet transmitting raw point clouds or full feature maps overwhelms Vehicle-to-Vehicle (V2V) communications, causing latency and scalability problems. We introduce EffiComm, an end-to-end framework that transmits less than 40% of the data required by prior art while maintaining state-of-the-art 3D object detection accuracy. EffiComm operates on Bird's-Eye-View (BEV) feature maps from any modality and applies a two-stage reduction pipeline: (1) Selective Transmission (ST) prunes low-utility regions with a confidence mask; (2) Adaptive Grid Reduction (AGR) uses a Graph Neural Network (GNN) to assign vehicle-specific keep ratios according to role and network load. The remaining features are fused with a soft-gated Mixture-of-Experts (MoE) attention layer, offering greater capacity and specialization for effective feature integration. On the OPV2V benchmark, EffiComm reaches 0.84 mAP@0.7 while sending only an average of approximately 1.5 MB per frame, outperforming previous methods on the accuracy-per-bit curve. These results highlight the value of adaptive, learned communication for scalable Vehicle-to-Everything (V2X) perception.