Metraipolis › archive › dc_6ff8689db875

Power-of-Two Leaky Integrate-and-Fire Neurons for Event-Driven Vision-Language-Action Inference — arXiv:2610.33658

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.33658
License (as archived): CC0-1.0
Archived: 2026-10-27T07:57:11.665Z
SHA-256 of the archived text: e150dcd0f98879ead82b00a1f90d7388ec4e0070abcafd48bc6ab6e33812fa56
Stable URL of this page: https://metraipolis.com/documento/dc_6ff8689db875

How to cite

Power-of-Two Leaky Integrate-and-Fire Neurons for Event-Driven Vision-Language-Action Inference — arXiv:2610.33658 — arXiv (en), https://arxiv.org/abs/2610.33658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6ff8689db875 (Metraipolis archive dc_6ff8689db875, sha256 e150dcd0f98879ead82b00a1f90d7388ec4e0070abcafd48bc6ab6e33812fa56)

BibTeX

@misc{dc6ff8689db875,
  title = {Power-of-Two Leaky Integrate-and-Fire Neurons for Event-Driven Vision-Language-Action Inference — arXiv:2610.33658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6ff8689db875; sha256 e150dcd0f98879ead82b00a1f90d7388ec4e0070abcafd48bc6ab6e33812fa56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language-action (VLA) models have demonstrated strong capabilities in robotic manipulation, yet their reliance on dense, continuous-valued computation presents a fundamental challenge for energy-constrained deployment. Inspired by the sparse, event-driven signaling and temporal integration mechanisms of biological neurons, a promising alternative is to introduce spiking computation into VLA models. However, enabling such computation without restructuring pretrained policies or compromising closed-loop control remains an open challenge. To address this challenge, we introduce the Power-of-Two Leaky Integrate-and-Fire (PoT-LIF) neuron, which emits signed spikes with power-of-two amplitudes. By combining magnitude-coded spike events with residual-preserving membrane dynamics, PoT-LIF enables continuous information to be progressively represented through discrete spikes. The Heartbeat formulation further localizes this process within weighted projections, bridging biologically inspired spiking computation and pretrained VLA architectures without modifying their external inference interfaces. We integrate PoT-LIF into the vision projection, vision-language projection, and action projection of $\pi_{0.5}$ and evaluate both operating modes over 2,000 paired closed-loop LIBERO episodes per configuration. Standard-mode PoT-LIF VLA achieves success rates of 96.90% and 96.35% at $T = 1$ and $T = 2$, respectively, while Heartbeat mode achieves 97.25% and 96.90% at $T = 2$ and $T = 4$, compared with 96.70% for the original continuous-activation $\pi_{0.5}$ baseline. At $T = 1$ with a 60.01% firing rate, PoT-LIF uses approximately 1/7.67 of the dense-reference arithmetic energy, corresponding to a modeled reduction of 86.95%.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33658 — 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 2026-10-27T07:55:30.657Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).