mlsanityData to 7 Oct 2026

Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies

arXiv 2603.16952 ↗First posted 16 Mar 2026cs.RO cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Deploying foundation models in embodied edge systems is fundamentally a systems problem, not just a problem of model compression. Real-time control must operate within strict size, weight, and power constraints, where memory traffic, compute latency, timing variability, and safety margins interact directly. The Deployment Gauntlet organizes these constraints into eight coupled barriers that determine whether embodied foundation models can run reliably in practice. Across representative edge workloads, autoregressive Vision-Language-Action policies are constrained primarily by memory bandwidth, whereas diffusion-based controllers are limited more by compute latency and sustained execution cost. Reliable deployment therefore depends on system-level co-design across memory, scheduling, communication, and model architecture, including decompositions that separate fast control from slower semantic reasoning.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 124 of its 211 references that are in the map. First posted on arXiv 16 Mar 2026.

Builds on

124 of 211 references.

References · 124

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  9. 2023FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioningcited by 2,551
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  11. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  12. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
38 more
  1. 2016Concrete Problems in AI Safetycited by 1,582
  2. 2018World Modelscited by 1,444
  3. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  4. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
  5. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  6. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  7. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,162
  8. 2019Event-based Vision: A Surveycited by 1,010
  9. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  10. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2019Fast Transformer Decoding: One Write-Head is All You Needcited by 700
  13. 2024KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cachecited by 604
  14. 2024KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantizationcited by 571
  15. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  16. 2020MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devicescited by 476
  17. 2022Efficient Test-Time Model Adaptation without Forgettingcited by 467
  18. 2024SpinQuant: LLM quantization with learned rotationscited by 446
  19. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  20. 2017Efficient Processing of Deep Neural Networks: A Tutorial and Surveycited by 427
  21. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  22. 2023Towards Stable Test-Time Adaptation in Dynamic Wild Worldcited by 409
  23. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  24. 2022Multimodal Learning with Transformers: A Surveycited by 399
  25. 2024SliceGPT: Compress Large Language Models by Deleting Rows and Columnscited by 378
  26. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  27. 2019Control Barrier Functions: Theory and Applicationscited by 332
  28. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  29. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
  30. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  31. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  32. 2024Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Securitycited by 257
  33. 2019End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Taskscited by 256
  34. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  35. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  36. 2019MLPerf Inference Benchmarkcited by 195
  37. 2022Robot Operating System 2: Design, Architecture, and Uses In The Wildcited by 190
  38. 2025LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Tokencited by 164

50 most cited of 124 All 124 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026G-Drift MIA: Membership Inference via Gradient-Induced Feature Drift in LLMscited by 6
  2. 2026SafeCommit: Certifying When Memory-Grounded Agents May Safely Actcited by 4
  3. 2026uScenes: A Multimodal RGB and 3D Sonar Dataset for Underwater Robot Perceptioncited by 2
  4. 2026RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Datacited by 1
  5. 2026LADBench: A Benchmark for Logical Fault Detection in Imagescited by 0
  6. 2026Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?
  2. 2026Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design
  3. 2026RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy
  4. 2026Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
  5. 2025Foundation Model Driven Robotics: A Comprehensive Review
  6. 2026HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory
  7. 2026TypeGo: An OS Runtime for Embodied Agents
  8. 2025P3: Toward Versatile Embodied Agents