Metraipolis › archive › dc_1fd9956ffd28
Spike-driven Vision-Language-Action Model — arXiv:2609.39514
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39514
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:13:50.878Z
- SHA-256 of the archived text
96152cec06b02b7616b55f25a60bd860317bd5f4b9983a7c5e4e980cf7020423- Stable URL of this page
https://metraipolis.com/documento/dc_1fd9956ffd28
How to cite
Spike-driven Vision-Language-Action Model — arXiv:2609.39514 — arXiv (en), https://arxiv.org/abs/2609.39514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1fd9956ffd28 (Metraipolis archive dc_1fd9956ffd28, sha256 96152cec06b02b7616b55f25a60bd860317bd5f4b9983a7c5e4e980cf7020423)
BibTeX
@misc{dc1fd9956ffd28,
title = {Spike-driven Vision-Language-Action Model — arXiv:2609.39514},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39514},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1fd9956ffd28; sha256 96152cec06b02b7616b55f25a60bd860317bd5f4b9983a7c5e4e980cf7020423},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-language-action (VLA) models bridge multimodal understanding and robotic control, advancing the dominant paradigm for embodied intelligence. However, most existing models rely on large Transformers, whose latency and energy costs hinder deployment on resource-constrained platforms. Through sparse event-driven computation, spiking neural networks offer a promising paradigm for high-performance and energy-efficient computing. Here, we propose the first Spike-driven VLA framework enabling end-to-end direct training for robotic manipulation, which mainly comprises three core components. First, we develop spiking visual and instruction encoders for multimodal perception, encoding visual observations and language instructions into sparse, reliable spike representations for subsequent cross-modal fusion. Then, we introduce Multi-Winner Spike Fusion for instruction-guided scene understanding, using bidirectional top-$k$ winner-take-all spike routing to suppress background interference and yield fused memory. Finally, we propose a Spike Action Chunking Transformer that incorporates spiking cross-attention over the fused memory and the current robot state, enabling efficient end-to-end generation of continuous action chunks for robotic control. Extensive experiments on LIBERO and Meta-World demonstrate that Spike-driven VLA achieves competitive performance with fewer parameters and lower estimated inference energy than conventional VLA models. This work establishes a foundational framework for neuromorphic VLA modeling, paving the way for future advances in resource-efficient embodied intelligence. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.39514 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:44:51.830Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).