# Saliency-Aware Quantized Imitation Learning for Efficient Robotic Control

arXiv: https://arxiv.org/abs/2505.15304 · HTML: https://mlsanity.com/paper/2505.15304/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Efficient VLA inference and adaptation, one of 13 directions in Vision-language-action models.
- Builds on 44 of its 60 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- Vision-language-action models / [Efficient VLA inference and adaptation](https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Up or Down? Adaptive Rounding for Post-Training Quantization](https://mlsanity.com/paper/2004.10568/) (2020)
- [DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients](https://mlsanity.com/paper/1606.06160/) (2016)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction](https://mlsanity.com/paper/2102.05426/) (2021)
- [PACT: Parameterized Clipping Activation for Quantized Neural Networks](https://mlsanity.com/paper/1805.06085/) (2018)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)

## Built on by (most cited first, 12 of 12)

- [A Survey on Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2510.24795/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models](https://mlsanity.com/paper/2602.13710/) (2026)
- [Revisiting Parameter Redundancy in Vision-Language-Action Models: Insights from VLM-to-VLA Adaptation](https://mlsanity.com/paper/2606.31382/) (2026)
- [QuantWAMs: Calibrating at the Right Granularity for World Action Models](https://mlsanity.com/paper/2607.28405/) (2026)
- [Device-Conditioned Neural Architecture Search for Efficient Robotic Manipulation](https://mlsanity.com/paper/2604.10170/) (2026)
- [APEX-RBD: Mixed-Precision Exploration Framework for Hardware-Efficient Robot Dynamics Accelerator Design](https://mlsanity.com/paper/2609.05161/) (2026)
- [Efficient Vision-Language-Action Management and Serving for Robot Factories](https://mlsanity.com/paper/2609.12075/) (2026)
- [Predict Before You Deploy: Offline Prediction of Quantization-Induced Task Degradation for World Action Models](https://mlsanity.com/paper/2609.19441/) (2026)
- [ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2610.08444/) (2026)
- [Lamarck's Driving School: Discovering Autonomous Driving Training Strategies through Evolutionary Competition](https://mlsanity.com/paper/2610.11662/) (2026)
- [Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2610.15675/) (2026)

## Abstract (arXiv)

Deep neural network (DNN)-based policy models, such as vision-language-action (VLA) models, excel at automating complex decision-making from multi-modal inputs. However, scaling these models greatly increases computational overhead, complicating deployment in resource-constrained settings like robot manipulation and autonomous driving. To address this, we propose Saliency-Aware Quantized Imitation Learning (SQIL), which combines quantization-aware training with a selective loss-weighting strategy for mission-critical states. By identifying these states via saliency scores and emphasizing them in the training loss, SQIL preserves decision fidelity under low-bit precision. We validate SQIL's generalization capability across extensive simulation benchmarks with environment variations, real-world tasks, and cross-domain tasks (self-driving, physics simulation), consistently recovering full-precision performance. Notably, a 4-bit weight-quantized VLA model for robotic manipulation achieves up to 2.5x speedup and 2.5x energy savings on an edge GPU with minimal accuracy loss. These results underline SQIL's potential for efficiently deploying large IL-based policy models on resource-limited devices.