SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
cs.CV, cs.AI, cs.RO
Submitted: 2025-09-06
Updated: 2026-10-30
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-1: Robotics Transformer for Real-World Control at Scale
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- VideoLLM: Modeling Video Sequence with Large Language Models
- LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- Evaluating Real-World Robot Manipulation Policies in Simulation
- SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
- Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control
- FORA: Fast-Forward Caching in Diffusion Transformer Acceleration
- Octo: An Open-Source Generalist Robot Policy
- Dexbotic: Open-Source Vision-Language-Action Toolbox
- SpeContext: Enabling Efficient Long-context Reasoning with Speculative Context Sparsity in LLMs
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
- EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
- VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs