LightNobel combines token-wise adaptive activation quantization with a custom accelerator to run protein structure prediction on sequences up to about 10,000 amino acids within 80GB memory.
Ballard, Joshua Bambrick, Sebastian W
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LightNobel: Improving Sequence Length Limitation in Protein Structure Prediction Model via Adaptive Activation Quantization
LightNobel combines token-wise adaptive activation quantization with a custom accelerator to run protein structure prediction on sequences up to about 10,000 amino acids within 80GB memory.