mlsanityData to 7 Oct 2026

RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models

arXiv 2603.07949 ↗First posted 9 Mar 2026cs.DC cs.ROcited by 4

On the map: Vision-language-action models → Efficient VLA inference and adaptation

Abstract (arXiv)

Vision Language Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) inference offers an effective fix by easing edge-device computing pressure to meet real-time needs. However, existing ECC frameworks are suboptimal for VLA models due to two challenges: (1) Mainstream environment-oriented edge-cloud partitioning methods are susceptible to interference from visual noise; (2) Existing edge-cloud partitioning methods overlook the step-wise redundancy unique to embodied tasks, thereby disrupting the physical continuity of motion. To address these issues, we propose a novel ECC inference framework, termed RAPID. Specifically, we developed an implementation tailored to the proposed framework. Experiments demonstrate this achieves a speedup of up to 1.73x with only 5%~7% overhead.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models. Builds on 32 of its 34 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

32 of 34 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models2 Mar
  2. 2025SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning6 Sep

Other references · 30

  1. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  2. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  5. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  6. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  7. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  8. 2022Fast Inference from Transformers via Speculative Decodingcited by 1,615
  9. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  11. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  12. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
18 more
  1. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  2. 2023VILA: On Pre-training for Visual Language Modelscited by 686
  3. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  4. 2023Splitwise: Efficient generative LLM inference using phase splittingcited by 536
  5. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  6. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  7. 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
  8. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 216
  9. 2019Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computingcited by 150
  10. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devicescited by 120
  11. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  12. 2025FREE: Fast and Robust Vision Language Models with Early Exitscited by 12
  13. 2025VITA-VLA: Efficiently Teaching Vision-Language Models to Act via Action Expert Distillationcited by 11
  14. 2025Fast and Cost-effective Speculative Edge-Cloud Decoding with Early Exitscited by 8
  15. 2026AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edgecited by 7
  16. 2025AVERY: Intent-Driven Adaptive VLM Split Computing via Embodied Self-Awareness for Efficient Disaster Response Systemscited by 4
  17. 2024Hierarchical Large Language Models in Cloud Edge End Architecture for Heterogeneous Robot Cluster Controlcited by 2
  18. 2026EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devicescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awarenesscited by 6
  2. 2026Jetson-PI: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inferencecited by 3
  3. 2026RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Modelscited by 2
  4. 20262D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awarenesscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer
  2. 2025EdgeVLA: Efficient Vision-Language-Action Models
  3. 2026EcoVLA: Energy-Efficient Device-Edge Co-Inference for Vision-Language-Action Models under Real-Time Constraints
  4. 2026Progressive Semantic Communication for Efficient Edge-Cloud Vision-Language Models
  5. 2026How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
  6. 2025ActionFlow: A Pipelined Action Acceleration for Vision Language Models on Edge
  7. 2026Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization
  8. 2026Vision-Language Models on the Edge for Real-Time Robotic Perception