Skip to content
Preprint

Deltoris: Enabling Real-time VLA Inference in Embodied AI via Bit-level Sparsity and Speculative Inference

Aug 2026 · 1 citation · 108 references
Computer Science

TL;DR

Deltoris is presented, an algorithm-hardware co-design framework for efficient diffusion-based VLA inference that exploits the temporal similarity of consecutive inputs and proposes a temporal-aware bit-sparsity algorithm that computes only the differences between consecutive inputs, eliminating redundant bit-level operations.

Abstract

Vision-language-action (VLA) models have emerged as a key component in embodied AI. Among existing approaches, diffusion-based VLA models achieve superior motion quality and generalization. However, diffusion-based VLA models are compute-intensive and must run at high control frequency, e.g., 50-200 Hz. Thus, it imposes strict latency and energy constraints on edge devices. In this work, we present Deltoris, an algorithm-hardware co-design framework for efficient diffusion-based VLA inference. First, we exploit the temporal similarity of consecutive inputs and propose a \textit{temporal-aware bit-sparsity} algorithm that computes only the differences between consecutive inputs, eliminating redundant bit-level operations. To further address the extra off-chip traffic introduced by our algorithm, we propose a \textit{speculative inference} technique, which amortizes data loading across multiple control steps. Lastly, to support these techniques, we co-design a dedicated accelerator with customized 1D systolic bit-serial PE arrays that eliminate PE workload imbalance. Our evaluation shows that Deltoris achieves up to 34.2$\times$ speedup over mobile GPUs and 6.1$\times$ over prior accelerators, while maintaining comparable accuracy.

View source

Similar papers

Preprint Sep 2026

FASA: Feedback-Aware Sampling Adaptation for Efficient Diffusion-Based VLA Models

Diffusion-based Vision-Language-Action (VLA) models achieve strong performance in embodied tasks, but their iterative sampling imposes heavy computational and memory-access cost, blocking real-time deployment on edge platforms. Existing acceleration methods either require expensive training (e.g., distillation, flow ma...

Yu-Cheng Han, Jianhan Wu, Xiaoyang Qu et al. · 0 citations
Preprint Aug 2026

FlashVLA: Streaming Action Decoding for Fast and Asynchronous VLA Inference

FlashVLA is introduced, a streaming action decoding framework that addresses both challenges in a unified formulation and can achieve $\geq$30\,Hz control frequency on a single GPU with smooth asynchronous inference in real-world deployment.

Ze-Kai Li, Jiarui Tang, Zhijian Liu · 5 citations
#edge computing Preprint Oct 2026

Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design

This work describes four representative VLA models on an edge GPU server and two onboard SoCs, using single-inference profiling and 43,200 closed-loop episodes, and guides joint design of VLA model architectures, hardware, and runtime policies.

Seonghun Jung, Sieun Moon, Jiyoung Jeong et al. · 0 citations
Sep 2026

FIVE-VLA: Fast and EffectIVE Autonomous Driving with Recurrent Action Memory

Recurrent Action Memory (RAM) is proposed, a lightweight module that conditions action prediction on previous action tokens, providing temporal context critical for manoeuvres such as overtaking and emergency braking.

Kemal Oksuz, Alexandru Buburuzan, Yu-Han Yao et al. · 0 citations
#edge computing Preprint Sep 2026

ComVLA: Communication-Aware Split Inference for VLA Models in 6G-Connected Robotics

ComVLA is proposed, a framework that uses the dense semantic information contained in the language guidance to adapt the VLA token budget to the channel capacity, and demonstrates that co-designing VLA inference and wireless communication is a practical direction for 6G-connected robotics.

Bo-Liang Liu, Wint Yi Poe, Jing-Yun Di et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.