EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices

• URL: http://arxiv.org/abs/2602.15836v1
• Date: Mon, 12 Jan 2026 09:20:53 GMT
• Title: EdgeNav-QE: QLoRA Quantization and Dynamic Early Exit for LAM-based Navigation on Edge Devices
• Abstract summary: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control.<n> deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints and latency requirements.<n>We propose EdgeNav-QE, a novel framework that integrates Quantized Low-Rank Adaptation (QLoRA) with a dynamic early-exit mechanism to optimize LAMs for real-time edge navigation.
• Score: 5.926544683744667
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Action Models (LAMs) have shown immense potential in autonomous navigation by bridging high-level reasoning with low-level control. However, deploying these multi-billion parameter models on edge devices remains a significant challenge due to memory constraints and latency requirements. In this paper, we propose EdgeNav-QE, a novel framework that integrates Quantized Low-Rank Adaptation (QLoRA) with a dynamic early-exit (DEE) mechanism to optimize LAMs for real-time edge navigation. By quantizing the backbone to 4-bit precision and strategically placing early-exit branches, we enable the model to terminate inference early for simple navigation tasks while retaining full depth for complex decision-making. Experimental results on the Habitat-Sim environment with Matterport3D dataset using OpenVLA-7B backbone, demonstrate that EdgeNav-QE reduces inference latency by 82.7% and memory footprint by 66.7% compared to full-precision baselines, while maintaining 81.8% navigation success rate. Furthermore, it outperforms state-of-the-art static early-exit method by 17.9% in latency, demonstrating the superiority of content-aware adaptive computation for safety-critical applications.

Related papers

• LAPF: LLM-Agent-Based Path Finder Using the UAVScenes Dataset [8.27333944529512]
  This paper proposes an LLM-Agent-Based Path Finder (LAPF) framework for autonomous UAV navigation in town-scale outdoor environments.<n>LAPF extends LLM-assisted navigation by integrating perception, memory, planning, and action modules into a closed-loop cognitive architecture.<n>LAPF achieves mean path lengths of 512.83 m and 506.37 m, compared to the straight-line optimum of 497.33 m.
  arXiv  Detail & Related papers  (2026-08-15T11:28:21Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• EdgeLPR: On the Deep Neural Network trade-off between Precision and Performance in LiDAR Place Recognition [1.8005402526211627]
  This work explores efficient LiDAR-based place recognition for EdgeAI by leveraging Bird's Eye View representations.<n>Experiments reveal trade-offs between accuracy, robustness, and efficiency.<n>Results are a strong basis for future research on 'use-case'-aware quantisation of Neural Networks for Edge deployment.
  arXiv  Detail & Related papers  (2026-05-04T06:52:14Z)
• Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection [53.59823657644554]
  We propose an Adaptive Multi-stage non-edge Pruning framework for Edge Detection(Amped)<n>Amped identifies high-confidence non-edge tokens and removes them as early as possible to substantially reduce computation.<n>To mitigate the structural complexity of existing edge detection networks, we introduce a simple yet high-performance Transformer-based model, termed Streamline Edge Detector(SED)
  arXiv  Detail & Related papers  (2026-03-29T12:26:35Z)
• ReMemNav: A Rethinking and Memory-Augmented Framework for Zero-Shot Object Navigation [35.416693138335354]
  Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments.<n>Recent advancements in vision-language models provide promising commonsense reasoning capabilities for this task.<n>We propose a novel hierarchical navigation framework named ReMemNav, which seamlessly integrates panoramic semantic priors and episodic memory.
  arXiv  Detail & Related papers  (2026-03-25T09:07:32Z)
• ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation [50.35621223011076]
  We introduce ABot-N0, a unified Vision-Language-Action (VLA) foundation model that achieves a Grand Unification'' across 5 core tasks.<n>ABot-N0 utilizes a hierarchical Brain-Action'' architecture, pairing an LLM-based Cognitive Brain for semantic reasoning with a Flow Matching-based Action Expert for precise, continuous trajectory generation.
  arXiv  Detail & Related papers  (2026-02-12T05:30:20Z)
• EdgeFlex-Transformer: Transformer Inference for Edge Devices [2.1130318406254074]
  We propose a lightweight yet effective multi-stage optimization pipeline designed to compress and accelerate Vision Transformers (ViTs)<n>Our methodology combines activation profiling, memory-aware pruning, selective mixed-precision execution, and activation-aware quantization (AWQ) to reduce the model's memory footprint without requiring costly retraining or task-specific fine-tuning.<n>Experiments on CIFAR-10 demonstrate that the fully optimized model achieves a 76% reduction in peak memory usage and over 6x lower latency, while retaining or even improving accuracy compared to the original FP32 baseline.
  arXiv  Detail & Related papers  (2025-12-17T21:45:12Z)
• Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models [97.55009021098554]
  This work aims to identify the key determinants of SLMs' real-device latency and offer generalizable principles and methodologies for SLM design and training.<n>We introduce a new family of hybrid SLMs, called Nemotron-Flash, which significantly advances the accuracy-efficiency frontier of state-of-the-art SLMs.
  arXiv  Detail & Related papers  (2025-11-24T08:46:36Z)
• Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving [24.706739338133236]
  We propose Nav-EE, a navigation-guided early-exit framework that precomputes task-specific exit layers offline and dynamically applies them online.<n>Experiments show that Nav-EE achieves accuracy comparable to full inference while reducing latency by up to 63.9%.
  arXiv  Detail & Related papers  (2025-10-02T08:37:58Z)
• Nav-R1: Reasoning and Navigation in Embodied Scenes [16.10022718760368]
  Em navigation requires agents to integrate perception, reasoning, and action.<n>Existing approaches often suffer from incoherent and unstable reasoning traces.<n>We propose Nav-R1, an embodied foundation model that unifies reasoning in embodied environments.
  arXiv  Detail & Related papers  (2025-09-13T16:31:03Z)
• DORAEMON: Decentralized Ontology-aware Reliable Agent with Enhanced Memory Oriented Navigation [55.888688171010365]
  DORAEMON is a cognitive-inspired framework consisting of Ventral and Dorsal Streams that mimics human navigation capabilities.<n>We evaluate DORAEMON on the HM3D, MP3D and GOAT datasets, where it achieves state-of-the-art performance on both success rate (SR) and success weighted by path length (SPL) metrics.
  arXiv  Detail & Related papers  (2025-05-28T04:46:13Z)
• SenseExpo: Efficient Autonomous Exploration with Prediction Information from Lightweight Neural Networks [3.6404856388891793]
  SenseExpo is an efficient autonomous exploration framework based on a lightweight prediction network.<n>Our smallest model achieves better performance on the KTH dataset than U-net and LaMa.
  arXiv  Detail & Related papers  (2025-03-20T10:07:51Z)
• MPVO: Motion-Prior based Visual Odometry for PointGoal Navigation [3.9974562667271507]
  Visual odometry (VO) is essential for enabling accurate point-goal navigation of embodied agents in indoor environments. Recent deep-learned VO methods show robust performance but suffer from sample inefficiency during training. We propose a robust and sample-efficient VO pipeline based on motion priors available while an agent is navigating an environment.
  arXiv  Detail & Related papers  (2024-11-07T15:36:49Z)
• Angle Robustness Unmanned Aerial Vehicle Navigation in GNSS-Denied Scenarios [66.05091704671503]
  We present a novel angle navigation paradigm to deal with flight deviation in point-to-point navigation tasks. We also propose a model that includes the Adaptive Feature Enhance Module, Cross-knowledge Attention-guided Module and Robust Task-oriented Head Module.
  arXiv  Detail & Related papers  (2024-02-04T08:41:20Z)
• Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation [72.24964965882783]
  Reinforcement learning (RL) is a promising approach for robotic navigation, allowing robots to learn through trial and error.<n>Real-world robotic tasks often suffer from sparse rewards, leading to inefficient exploration and suboptimal policies.<n>We introduce Confidence-Controlled Exploration (CCE), a novel method that improves sample efficiency in RL-based robotic navigation without modifying the reward function.
  arXiv  Detail & Related papers  (2023-06-09T18:45:15Z)
• DeepGEMM: Accelerated Ultra Low-Precision Inference on CPU Architectures using Lookup Tables [49.965024476651706]
  DeepGEMM is a lookup table based approach for the execution of ultra low-precision convolutional neural networks on SIMD hardware. Our implementation outperforms corresponding 8-bit integer kernels by up to 1.74x on x86 platforms.
  arXiv  Detail & Related papers  (2023-04-18T15:13:10Z)
• Efficient and Robust LiDAR-Based End-to-End Navigation [132.52661670308606]
  We present an efficient and robust LiDAR-based end-to-end navigation framework. We propose Fast-LiDARNet that is based on sparse convolution kernel optimization and hardware-aware model design. We then propose Hybrid Evidential Fusion that directly estimates the uncertainty of the prediction from only a single forward pass.
  arXiv  Detail & Related papers  (2021-05-20T17:52:37Z)

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.