# Efficient VLA inference and adaptation Area: [Vision-language-action models](https://mlsanity.com/vla/index.md). HTML: https://mlsanity.com/vla/efficient-vla-inference-and-adaptation/ ## Key facts - Efficient VLA inference and adaptation: 237 papers on arXiv since 2024 (data through 7 Oct 2026). - 79 of its 237 mapped papers (33%) cite “FAST: Efficient Action Tokenization for Vision-Language-Action Models” (2025, arXiv 2501.09747). - 42 of its 237 mapped papers (18%) cite “EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models” (2025, arXiv 2506.10100). - 32 new papers 17 Sep–7 Oct. ## Most cited here - [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025), cited by 79 papers here - [EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models](https://mlsanity.com/paper/2506.10100/) (2025), cited by 42 papers here - [VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching](https://mlsanity.com/paper/2502.02175/) (2025), cited by 38 papers here - [MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation](https://mlsanity.com/paper/2503.20384/) (2025), cited by 31 papers here - [PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decoding](https://mlsanity.com/paper/2503.02310/) (2025), cited by 28 papers here - [SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning](https://mlsanity.com/paper/2509.05614/) (2025), cited by 24 papers here - [HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model](https://mlsanity.com/paper/2503.10631/) (2025), cited by 23 papers here - [Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control](https://mlsanity.com/paper/2412.01034/) (2024), cited by 22 papers here - [SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration](https://mlsanity.com/paper/2506.12723/) (2025), cited by 21 papers here - [VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference](https://mlsanity.com/paper/2512.01031/) (2025), cited by 21 papers here ## New (17 Sep–7 Oct) - [ActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2610.08444/) (2026-10-06) - [VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models](https://mlsanity.com/paper/2610.08133/) (2026-10-06) - [StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models](https://mlsanity.com/paper/2610.07756/) (2026-10-06) - [VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models](https://mlsanity.com/paper/2610.06271/) (2026-10-05) - [Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design](https://mlsanity.com/paper/2610.05062/) (2026-10-04) - [FastOPD: On-Policy Distillation for Lightweight VLA Deployment](https://mlsanity.com/paper/2610.02832/) (2026-10-02) - [CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation](https://mlsanity.com/paper/2610.02666/) (2026-10-02) - [TOAST: Stochastic Robot Action Tokenization for Autoregressive Vision-Language-Action Models](https://mlsanity.com/paper/2610.00899/) (2026-10-01) - [Toward Real-Time VLAs: Stage-Aware Two-Step Flow Denoising and System-Level Evaluation](https://mlsanity.com/paper/2609.39822/) (2026-09-30) - [Discrete Forcing: Infusing Discrete Guidance into Continuous Denoising for Few-Step Action Experts](https://mlsanity.com/paper/2609.39526/) (2026-09-30) - [Spike-driven Vision-Language-Action Model](https://mlsanity.com/paper/2609.39514/) (2026-09-30) - [DSDyn-VLA: A Dual-Stream Dynamic Manipulation Framework with Motion Perception, Future Awareness, and Realtime Correction](https://mlsanity.com/paper/2609.39198/) (2026-09-30) - [Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control](https://mlsanity.com/paper/2609.37772/) (2026-09-29) - [Reactive Real-Time Flow Policies via Asynchronous Distribution Alignment](https://mlsanity.com/paper/2609.36540/) (2026-09-29) - [Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning](https://mlsanity.com/paper/2609.34467/) (2026-09-29) - [Rethinking Causal Action Tokenization with Conditional Annealing in Flow Matching](https://mlsanity.com/paper/2609.35469/) (2026-09-28) - [ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning](https://mlsanity.com/paper/2609.34982/) (2026-09-28) - [Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies](https://mlsanity.com/paper/2609.34944/) (2026-09-28) - [Text-Vision Synergistic Token Caching: A Training-Free Framework for Efficient Vision-Language-Action Inference](https://mlsanity.com/paper/2609.34319/) (2026-09-28) - [RAVEL: Asynchronous Rolling Inference for Flow-Based Vision-Language-Action Models](https://mlsanity.com/paper/2609.34170/) (2026-09-28) - [Quantile Head for Vision-Language-Action Models](https://mlsanity.com/paper/2609.34061/) (2026-09-28) - [DS-VLA: A Dendritic-inspired Vision-Language-Action Model for Robust Action Control](https://mlsanity.com/paper/2609.32253/) (2026-09-26) - [Fast Plans, Faithful Actions: Closing the Planning-Execution Gap in Hierarchical Vision-Language-Action Models](https://mlsanity.com/paper/2609.30833/) (2026-09-25) - [Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs](https://mlsanity.com/paper/2609.29382/) (2026-09-24) - [Beyond Reconstruction Error: Analytical and Data-Driven Action Tokenization for Autoregressive Vision-Language-Action Models](https://mlsanity.com/paper/2609.25820/) (2026-09-22) - [FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding](https://mlsanity.com/paper/2609.24433/) (2026-09-21) - [SmoLSTM: A Compact Vision-Language-Action Model with Recurrent Memory that Persists](https://mlsanity.com/paper/2609.22854/) (2026-09-19) - [StateMem: Single-State Residual Memory with Adaptive Inference for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.22684/) (2026-09-19) - [Fewer Steps, Better Actions: Rethinking Flow-Matching Inference for VLA Policies](https://mlsanity.com/paper/2609.21216/) (2026-09-18) - [Catch Me If You Can: Real-Time Feedback Denoising for Responsive VLAs](https://mlsanity.com/paper/2609.21022/) (2026-09-17)