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

• URL: http://arxiv.org/abs/2603.16952v2
• Date: Thu, 19 Mar 2026 02:29:21 GMT
• Title: Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies
• Abstract summary: Deployment Gauntlet organizes constraints into eight coupled barriers.<n> Reliable deployment depends on system-level co-design across memory, scheduling, communication, and model architecture.
• Score: 3.4385853021313593
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference [0.0]
  Fixed-depth speculative decoding has emerged as one promising technique, but in practice, it often leads to performance degradation due to bandwidth saturation, instability, or even catastrophic resource exhaustion resulting in system failure.<n>Our solution consists of four tightly-coupled components working together in a continuous feedback loop: an Adaptive Draft Controller, a Dynamic Policy Engine, a KV Cache Coordination Layer, and a Monitoring Engine.<n>While conventional approaches focus solely on maximizing throughput, we instead assess the effectiveness of our approach based on several key metrics including wasted drafted compute and inter-token latency dispersion alongside standard measures of speculative efficiency.
  arXiv  Detail & Related papers  (2026-07-04T13:39:40Z)
• Hierarchical Prompt-Domain Control and Learning for Resource-Constrained Agentic Language Models [0.0]
  Large Language Models are increasingly deployed inside agentic systems.<n>We propose a hierarchical control-and-learning framework in which a compact model is first distilled to learn the required output schema.<n>We show improved reliability and cost-efficiency over non-hierarchical, distillation-only, and non-distilled baselines.
  arXiv  Detail & Related papers  (2026-05-26T21:23:30Z)
• CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable LLM Interactions [3.8673630752805437]
  Inference-time control is the computational layer governing task framing and context selection.<n>We introduce emphCogniConsole, an architectural instantiation that externalizes this control into a structured interface.<n>Our results indicate that many observed failure modes, such as context drift and inconsistent constraint adherence, arise from under-specified control rather than insufficient capability.
  arXiv  Detail & Related papers  (2026-04-21T17:21:06Z)
• BarrierSteer: LLM Safety via Learning Barrier Steering [83.12893815611052]
  BarrierSteer is a novel framework that formalizes safety by embedding learned non-linear safety constraints directly into the model's latent representation space.<n>We show that BarrierSteer substantially reduces adversarial success rates, decreases unsafe generations, and outperforms existing methods.
  arXiv  Detail & Related papers  (2026-02-23T18:19:46Z)
• Constraining Streaming Flow Models for Adapting Learned Robot Trajectory Distributions [10.615762867055677]
  Streaming Flow Policies (SFPs) have emerged as a powerful paradigm for generating robot trajectories by integrating learned velocity fields directly in action space.<n>We propose Constraint-Aware Streaming Flow (CASF), a framework that augments streaming flow policies with constraint-dependent metrics that reshape the learned velocity field during execution.<n>We demonstrate CASF in simulated and real-world manipulation tasks, showing that it produces constraint-satisfying trajectories that remain smooth, feasible, and dynamically consistent.
  arXiv  Detail & Related papers  (2026-02-17T13:27:05Z)
• Rethinking Multi-Condition DiTs: Eliminating Redundant Attention via Position-Alignment and Keyword-Scoping [61.459927600301654]
  Multi-condition control is bottlenecked by the conventional concatenate-and-attend'' strategy.<n>Our analysis reveals that much of this cross-modal interaction is spatially or semantically redundant.<n>We propose Position-aligned and Keyword-scoped Attention (PKA), a highly efficient framework designed to eliminate these redundancies.
  arXiv  Detail & Related papers  (2026-02-06T16:39:10Z)
• Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework [5.833654928445309]
  We present ANCHOR, a modular framework that makes decoupling and explicit system-level primitives.<n>ANCHOR separates (i) Canonical Records, an evolvable contract for the standardized shared state, from (ii) a communication bus for many-to-many dissemination and feedback-oriented coordination.
  arXiv  Detail & Related papers  (2026-01-20T13:21:52Z)
• R-ConstraintBench: Evaluating LLMs on NP-Complete Scheduling [0.0]
  We present R-ConstraintBench, a framework that evaluates models on Resource-Constrained Project Scheduling Problems (RCPSP)<n>We instantiate the benchmark in a data center migration setting and evaluate multiple LLMs using feasibility and error analysis.<n> Empirically, strong models are near-ceiling on precedence-only DAGs, but feasibility performance collapses when downtime, temporal windows, and disjunctive constraints interact.
  arXiv  Detail & Related papers  (2025-08-21T03:35:58Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models [1.6874375111244326]
  The rapid growth of resource-constrained mobile platforms has increased the demand for computationally efficient neural network controllers (NNCs)<n>Deep neural networks (DNNs) demonstrate superior performance in control applications, their substantial computational complexity and memory requirements present significant barriers to practical deployment on edge devices.<n>This paper introduces a comprehensive model compression methodology that leverages component-aware structured pruning to determine the optimal pruning magnitude for each pruning group.
  arXiv  Detail & Related papers  (2025-08-11T16:16:51Z)
• UniConFlow: A Unified Constrained Generalization Framework for Certified Motion Planning with Flow Matching Models [16.275286046169594]
  Generative models have become increasingly powerful tools for robot motion generation, enabling flexible and multimodal trajectory generation across various tasks.<n>This paper proposes UniConFlow, a unified flow matching framework for trajectory generation that systematically incorporates both equality and inequality constraints.<n>We conduct mobile navigation and high-dimensional manipulation tasks, demonstrating improved safety and feasibility compared to state-of-the-art constrained generative planners.
  arXiv  Detail & Related papers  (2025-06-03T14:48:04Z)
• Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules [8.098452803458253]
  This paper proposes a model-agnostic framework for enforcing input-dependent linear equality and inequality constraints on neural network outputs.<n>The architecture combines a task network trained for prediction accuracy with a safe network trained using decision rules from the runtime and robust optimization to ensure feasibility across the entire input space.
  arXiv  Detail & Related papers  (2025-05-20T03:09:44Z)
• Diffusion Predictive Control with Constraints [51.91057765703533]
  Diffusion predictive control with constraints (DPCC) is an algorithm for diffusion-based control with explicit state and action constraints.<n>We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints.
  arXiv  Detail & Related papers  (2024-12-12T15:10:22Z)
• Temporal Feature Matters: A Framework for Diffusion Model Quantization [105.3033493564844]
  Diffusion models rely on the time-step for the multi-round denoising.<n>We introduce a novel quantization framework that includes three strategies.<n>This framework preserves most of the temporal information and ensures high-quality end-to-end generation.
  arXiv  Detail & Related papers  (2024-07-28T17:46:15Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.