AI Paper Atlas

Research map / Architectures and efficiency / Quantization

FP=XINT: Representing Neural Networks via Low-Bit Series Basis Functions

Boyang Zhang, Daning Cheng, Yunquan Zhang, Jiake Tian, Jing Li, Fangming Liu

AAAI 2026 · Architectures and efficiency › Quantization · approach: Binary neural networks · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
expand full-precision model into low-bit series basis models (no calibration or fine-tuning) vs best PTQ baselineResNet-50 · ImageNet W4A4top-1 accuracy: 75.09 -> 77.03Improved
series expansion vs CL-Calib at 2-bit weights, 2-bit activationsResNet-50 · ImageNet W2A2top-1 accuracy: 58.30 -> 62.13Improved
series expansion vs PTQ baselines on BERT W4A4BERT · SQuAD1.1F1: 75.97 -> 79.30Improved
series expansion vs GPTQ on 4-bit LLMLLaMA3-8B · MMLU averageaccuracy: 63.0 -> 64.7Improved
increase number of expansion terms (ablation)ResNet-50 · ImageNet INT4accuracyMixed
disable clipping (Wsa = 0) in saturation basis (ablation)series expansion · ResNet-18/50accuracyNo clear effect
expand weights beyond 2-3 terms (ablation)series expansion · variousaccuracyNo clear effect
use 4-bit basis instead of 8-bit basisResNet-50 · efficiencylatency (ms): 0.74 (down 30%)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy