# LiteVLA-H: Dual-Rate Vision-Language-Action Inference for Onboard Aerial Guidance and Semantic Perception

arXiv: https://arxiv.org/abs/2605.00884 · HTML: https://mlsanity.com/paper/2605.00884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Aerial and drone VLA, one of 13 directions in Vision-language-action models.
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Placed in

- Vision-language-action models / [Aerial and drone VLA](https://mlsanity.com/vla/aerial-and-drone-vla/)

## Builds on (most cited first, 16 of 16)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Running VLAs at Real-time Speed](https://mlsanity.com/paper/2510.26742/) (2025)
- [The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning](https://mlsanity.com/paper/2509.12594/) (2025)
- [ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queries](https://mlsanity.com/paper/2603.12942/) (2026)
- [VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments](https://mlsanity.com/paper/2512.15258/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf](https://mlsanity.com/paper/2602.18397/) (2026)
- [FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model](https://mlsanity.com/paper/2603.10712/) (2026)
- [AerialVLA: A Vision-Language-Action Model for UAV Navigation via Minimalist End-to-End Control](https://mlsanity.com/paper/2603.14363/) (2026)
- [π, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation](https://mlsanity.com/paper/2603.25038/) (2026)
- [SINGER: An Onboard Generalist Vision-Language Navigation Policy for Drones](https://mlsanity.com/paper/2509.18610/) (2025)
- [AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation](https://mlsanity.com/paper/2601.21602/) (2026)
- [LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics](https://mlsanity.com/paper/2603.03380/) (2026)
- [AnywhereVLA: Language-Conditioned Exploration and Mobile Manipulation](https://mlsanity.com/paper/2509.21006/) (2025)

## Abstract (arXiv)

Vision-language-action (VLA) models have shown strong semantic grounding and task generalization in manipulation, but aerial deployment remains difficult because drones require low-latency closed-loop guidance under strict onboard compute and communication constraints. We present LiteVLA-H, a compact 256M-parameter VLA system designed for dual-rate operation on an NVIDIA Jetson AGX Orin: a fast outer-loop guidance mode for short action-token outputs and a slower semantic mode for scene understanding, hazard description, and operator-facing narration. The central empirical observation is that, in this compact edge regime, end-to-end latency is dominated by multimodal pre-fill rather than by the marginal cost of decoding a few extra tokens. This motivates a scheduler that issues reactive action tokens at 50.65,ms (19.74,Hz) while still supporting sentence-level semantic outputs at 149.90--164.57ms (6.08--6.67,Hz) on the same embedded platform. To specialize the model without collapsing its descriptive competence, we use a knowledge-preserving fine-tuning recipe that mixes reactive flight data, aerial semantic data, and generic caption/VQA supervision. Beyond reporting current latency measurements, we position the system against recent state-of-the-art architectures, including AnywhereVLA, FutureVLA, and ReMem-VLA, showing that the measured action branch reaches a higher edge inference rate under our deployment conditions while retaining periodic semantic awareness.