# ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models

arXiv: https://arxiv.org/abs/2603.25766 · HTML: https://mlsanity.com/paper/2603.25766/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in VLA for autonomous driving, one of 13 directions in Vision-language-action models.
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 26 Mar 2026.

## Placed in

- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)

## Builds on (most cited first, 24 of 24)

- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [GenAD: Generative End-to-End Autonomous Driving](https://mlsanity.com/paper/2402.11502/) (2024)
- [Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving](https://mlsanity.com/paper/2410.22313/) (2024)
- [Generalized Trajectory Scoring for End-to-end Multimodal Planning](https://mlsanity.com/paper/2506.06664/) (2025)
- [DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving](https://mlsanity.com/paper/2505.19381/) (2025)
- [MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer](https://mlsanity.com/paper/2403.02991/) (2024)
- [Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention](https://mlsanity.com/paper/2510.02912/) (2025)
- [SimScale: Learning to Drive via Real-World Simulation at Scale](https://mlsanity.com/paper/2511.23369/) (2025)
- [IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model](https://mlsanity.com/paper/2508.06571/) (2025)
- [DriveGPT: Scaling Autoregressive Behavior Models for Driving](https://mlsanity.com/paper/2412.14415/) (2024)

## Built on by (most cited first, 1 of 1)

- [DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies](https://mlsanity.com/paper/2610.09144/) (2026)

## Abstract (arXiv)

The integration of Vision-Language-Action (VLA) models into autonomous driving systems offers a unified framework for interpreting complex scenes and executing control commands. However, the necessity to incorporate historical multi-view frames for accurate temporal reasoning imposes a severe computational burden, primarily driven by the quadratic complexity of self-attention mechanisms in Large Language Models (LLMs). To alleviate this bottleneck, we propose ETA-VLA, an Efficient Token Adaptation framework for VLA models. ETA-VLA processes the past n frames of multi-view images and introduces a novel Intra-LLM Sparse Aggregator (ILSA). Drawing inspiration from human driver attention allocation, ILSA dynamically identifies and prunes redundant visual tokens guided by textual queries and temporal consistency. Specifically, we utilize a text-guided scoring mechanism alongside a diversity-preserving sparsification strategy to select a sparse subset of critical tokens, ensuring comprehensive awareness of the driving scene. Extensive experiments on the NAVSIM v2 demonstrate that ETA-VLA achieves driving performance comparable to state-of-the-art baselines while reducing computational FLOPs by approximately 32%. Notably, our method prunes 85% of visual tokens and reduces inference FLOPs by 61%, but still retaining 94% of the original accuracy on the NAVSIM v2 benchmark.