Pith. sign in

Spiking deep convolutional neural networks for energy-efficient object recognition

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

FAS: Fast ANN-SNN Conversion for Spiking Large Language Models

cs.LG · 2025-02-06 · conditional · novelty 6.0

FAS converts pretrained LLMs to spiking LLMs by fine-tuning with QCFS and then calibrating thresholds and initial membrane potentials, reaching near-LLM accuracy at 8-16 timesteps with large claimed energy savings.

citing papers explorer

Showing 1 of 1 citing paper.

  • FAS: Fast ANN-SNN Conversion for Spiking Large Language Models cs.LG · 2025-02-06 · conditional · none · ref 8

    FAS converts pretrained LLMs to spiking LLMs by fine-tuning with QCFS and then calibrating thresholds and initial membrane potentials, reaching near-LLM accuracy at 8-16 timesteps with large claimed energy savings.