Cover Image

HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Zihao, Mao, Zhihao, Tian, Sicheng, Li, Maoliang, Chen, Jiayu, Sun, Xinhao, Zhang, Zhaobo, Liu, Xuanzhe, Cao, Donggang, Mei, Hong, Chen, Xiang
Format:	Preprint
Published:	2026
Subjects:	Robotics Databases Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models
by: Zheng, Zihao, et al.
Published: (2026)

VLN-Cache: Enabling Token Caching for VLN Models with Visual/Semantic Dynamics Awareness
by: Zheng, Zihao, et al.
Published: (2026)

RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

RAPID: Redundancy-Aware and Compatibility-Optimal Edge-Cloud Partitioned Inference for Diverse VLA Models
by: Zheng, Zihao, et al.
Published: (2026)

STaRR: Spatial-Temporal Token-Dynamics-Aware Responsive Remasking for Diffusion Language Models
by: Sun, Xinhao, et al.
Published: (2025)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
by: Jiang, Feng, et al.
Published: (2025)

HeRo: Adaptive Orchestration of Agentic RAG on Heterogeneous Mobile SoC
by: Li, Maoliang, et al.
Published: (2026)

StarSD: One-for-Many Speculative Decoding
by: He, Junhao, et al.
Published: (2026)

DReSD: Dense Retrieval for Speculative Decoding
by: Gritta, Milan, et al.
Published: (2025)

ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization
by: Chen, Jiayu, et al.
Published: (2026)

FedHQ: Hybrid Runtime Quantization for Federated Learning
by: Zheng, Zihao, et al.
Published: (2025)

DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing
by: Li, Ke, et al.
Published: (2026)

DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation
by: Zheng, Zihao, et al.
Published: (2025)

Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation
by: Chen, Jiayu, et al.
Published: (2026)

ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
by: Kang, Jialiang, et al.
Published: (2025)

TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
by: Gong, Shukai, et al.
Published: (2025)

AdaSD: Adaptive Speculative Decoding for Efficient Language Model Inference
by: Lu, Kuan-Wei, et al.
Published: (2025)

AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative Decoding
by: Li, Zikun, et al.
Published: (2025)

Computational geometry in Heisenberg group Heis^3
by: Marenich, Andrey
Published: (2002)

Traversal Verification for Speculative Tree Decoding
by: Weng, Yepeng, et al.
Published: (2025)

MIRAGE: Runtime Scheduling for Multi-Vector Image Retrieval with Hierarchical Decomposition
by: Li, Maoliang, et al.
Published: (2025)

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding
by: Chen, Zhuoming, et al.
Published: (2024)

DiP-SD: Distributed Pipelined Speculative Decoding for Efficient LLM Inference at the Edge
by: Xu, Yaodan, et al.
Published: (2026)

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models
by: Ni, Yunsheng, et al.
Published: (2024)

PipeSD: An Efficient Cloud-Edge Collaborative Pipeline Inference Framework with Speculative Decoding
by: Han, Yunhe, et al.
Published: (2026)

Component-Aware Self-Speculative Decoding in Hybrid Language Models
by: Borobia, Hector, et al.
Published: (2026)

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications
by: Oliaro, Gabriele, et al.
Published: (2024)

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding
by: Sun, Shuoyang, et al.
Published: (2026)

Speculative Safety-Aware Decoding
by: Wang, Xuekang, et al.
Published: (2025)

Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance
by: Wang, Songsheng, et al.
Published: (2025)

SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
by: Wang, Hanzhen, et al.
Published: (2025)

2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
by: Zheng, Zihao, et al.
Published: (2026)

Scaling Laws for Speculative Decoding
by: Yan, Siyuan, et al.
Published: (2025)

CASCADE: Context-Aware Relaxation for Speculative Image Decoding
by: Yildirim, Selin, et al.
Published: (2026)

SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices
by: Svirschevski, Ruslan, et al.
Published: (2024)

RAD: Redundancy-Aware Distillation for Hybrid Models via Self-Speculative Decoding
by: Hoshino, Yuichiro, et al.
Published: (2025)

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
by: Su, Xin, et al.
Published: (2026)

Speculative Speculative Decoding
by: Kumar, Tanishq, et al.
Published: (2026)

TAPS: Target-Aware Prefix Tree Selection for Diffusion-Drafted Speculative Decoding
by: Wang, Zhuoyu, et al.
Published: (2026)