For the three different model scales—1.8M, 3.8M and 6.8M parameters—we allocated 24, 28 and 36 hours of training time, respectively

We conducted training on eight 40GB A100 GPUs · 2025

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

1 Pith paper citing it

browse 1 citing papers

representative citing papers

cs.CV · 2025-01-23 · conditional · novelty 6.0

A 4-bit quantized spike-driven transformer with multi-bit training and binary inference achieves 80.3% ImageNet accuracy with 6.8M parameters.

Showing 1 of 1 citing paper.

Quantized Spike-driven Transformer cs.CV · 2025-01-23 · conditional · none · ref 9
A 4-bit quantized spike-driven transformer with multi-bit training and binary inference achieves 80.3% ImageNet accuracy with 6.8M parameters.