AutoNeural: Co-Designing Vision-Language Models for NPU Inference

• URL: http://arxiv.org/abs/2512.02924v2
• Date: Mon, 08 Dec 2025 00:15:33 GMT
• Title: AutoNeural: Co-Designing Vision-Language Models for NPU Inference
• Authors: Wei Chen, Liangmin Wu, Yunhai Hu, Zhiyuan Li, Zhiyuan Cheng, Yicheng Qian, Lingyue Zhu, Zhipeng Hu, Luoyi Liang, Qiang Tang, Zhen Liu, Han Yang,
• Abstract summary: AutoNeural is an NPU-native VLM architecture co-designed for integer-only inference.<n>We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions.<n>Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines.
• Score: 24.05617280495125
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While Neural Processing Units (NPUs) offer high theoretical efficiency for edge AI, state-of-the-art Vision--Language Models (VLMs) tailored for GPUs often falter on these substrates. We attribute this hardware-model mismatch to two primary factors: the quantization brittleness of Vision Transformers (ViTs) and the I/O-bound nature of autoregressive attention mechanisms, which fail to utilize the high arithmetic throughput of NPUs. To bridge this gap, we propose AutoNeural, an NPU-native VLM architecture co-designed for integer-only inference. We replace the standard ViT encoder with a MobileNetV5-style backbone utilizing depthwise separable convolutions, which ensures bounded activation distributions for stable INT4/8/16 quantization. Complementing this, our language backbone integrates State-Space Model (SSM) principles with Transformer layers, employing efficient gated convolutions to achieve linear-time complexity. This hybrid design eliminates the heavy memory I/O overhead of Key-Value caching during generation. Our approach delivers substantial efficiency gains, reducing quantization error of vision encoder by up to 7x and end-to-end latency by 14x compared to conventional baselines. The AutoNeural also delivers 3x decoding speed and 4x longer context window than the baseline. We validate these improvements via a real-world automotive case study on the Qualcomm SA8295P SoC, demonstrating real-time performance for cockpit applications. Our results highlight that rethinking model topology specifically for NPU constraints is a prerequisite for robust multi-modal edge intelligence.

Related papers

• Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design [17.941176878609337]
  We bridge the gap between generative models and high-resolution neural simulations by introducing a scalable textitHardware-Algorithm Co-Design framework.<n>Our system delivers fluid 26.4 FPS and 48.3 FPS respectively, with an amortized effective latency of 2.7 ms.
  arXiv  Detail & Related papers  (2026-01-31T08:52:51Z)
• FastBEV++: Fast by Algorithm, Deployable by Design [5.339716421285263]
  This paper introduces FastBEV++, a framework engineered to reconcile state-of-the-art performance and on-vehicle deployment tractability.<n>We realize the "Deployable by Design" principle through a novel view paradigm that decomposes the monolithic projection into a standard Index-Gather-Reshape pipeline.
  arXiv  Detail & Related papers  (2025-12-09T04:37:46Z)
• Hardware-Aware Model Design and Training of Silicon-based Analog Neural Networks [33.83993649730681]
  We show that by retraining the neural network using a physics-informed hardware-aware model one can fully recover the inference accuracy of the ideal network model.<n>This is more promising for scalability and integration density than the default option of improving the fidelity of the analog neural network.
  arXiv  Detail & Related papers  (2025-12-08T10:11:13Z)
• Model-free front-to-end training of a large high performance laser neural network [0.0]
  We demonstrate a fully autonomous and parallel optical neural network (ONN) using off-the-shelf components.<n>Our ONN is highly efficient and is scalable both in network size and inference bandwidth towards the GHz range.<n>We show that our ONN can achieve high accuracy and convergence efficiency, even under limited hardware resources.
  arXiv  Detail & Related papers  (2025-03-21T08:43:02Z)
• BHViT: Binarized Hybrid Vision Transformer [53.38894971164072]
  Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN)<n>We propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations.<n>Our proposed algorithm achieves SOTA performance among binary ViT methods.
  arXiv  Detail & Related papers  (2025-03-04T08:35:01Z)
• Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity [39.483346492111515]
  Linear recurrent neural networks enable powerful long-range sequence modeling with constant memory usage and time-per-token during inference.<n>Unstructured sparsity offers a compelling solution, enabling substantial reductions in compute and memory requirements when accelerated by compatible hardware platforms.<n>We find that highly sparse linear RNNs consistently achieve better efficiency-performance trade-offs than dense baselines.
  arXiv  Detail & Related papers  (2025-02-03T13:09:21Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals [58.865901821451295]
  We present a novel two-stream feature fusion "Tensor-Convolution and Convolution-Transformer Network" (TCCT-Net) architecture. To better learn the meaningful patterns in the temporal-spatial domain, we design a "CT" stream that integrates a hybrid convolutional-transformer. In parallel, to efficiently extract rich patterns from the temporal-frequency domain, we introduce a "TC" stream that uses Continuous Wavelet Transform (CWT) to represent information in a 2D tensor form.
  arXiv  Detail & Related papers  (2024-04-15T06:01:48Z)
• Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs [74.83613252825754]
  "smart ecosystems" are being formed where sensing happens concurrently rather than standalone. This is shifting the on-device inference paradigm towards deploying neural processing units (NPUs) at the edge. We propose a novel early-exit scheduling that allows preemption at run time to account for the dynamicity introduced by the arrival and exiting processes.
  arXiv  Detail & Related papers  (2022-09-27T15:04:01Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Adversarially Robust and Explainable Model Compression with On-Device Personalization for Text Classification [4.805959718658541]
  On-device Deep Neural Networks (DNNs) have recently gained more attention due to the increasing computing power of mobile devices and the number of applications in Computer Vision (CV) and Natural Language Processing (NLP) In NLP applications, although model compression has seen initial success, there are at least three major challenges yet to be addressed: adversarial robustness, explainability, and personalization. Here we attempt to tackle these challenges by designing a new training scheme for model compression and adversarial robustness, including the optimization of an explainable feature mapping objective. The resulting compressed model is personalized using on-device private training data via fine-
  arXiv  Detail & Related papers  (2021-01-10T15:06:55Z)
• An Image Enhancing Pattern-based Sparsity for Real-time Inference on Mobile Devices [58.62801151916888]
  We introduce a new sparsity dimension, namely pattern-based sparsity that comprises pattern and connectivity sparsity, and becoming both highly accurate and hardware friendly. Our approach on the new pattern-based sparsity naturally fits into compiler optimization for highly efficient DNN execution on mobile platforms.
  arXiv  Detail & Related papers  (2020-01-20T16:17:36Z)

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.