AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Highly Efficient and Effective LLMs with Multi-Boolean Architectures

Ba-Hien Tran, Van Minh Nguyen

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of LLMs · 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
increase number of Boolean kernels (ablation)MBOK · OPT smallapproximation error and perplexityImproved
train only the last Boolean kernel instead of the first (ablation)MBOK · OPT smallweight flips and perplexityImproved
use 3 Boolean kernels instead of 3-bit OPTQMBOK · OPT-125M WikiText2perplexity: 53.85 -> 29.10Improved
use 3 Boolean kernels instead of 3-bit OPTQMBOK · OPT-6.7B WikiText2perplexity: 14.86 -> 11.03Improved
native Boolean training instead of latent weights (ablation)MBOK · OPTconvergence speedImproved
use 3 kernels vs MoS 3 experts (ablation)MBOK · OPTperplexityImproved
allocate kernels by importance and residual error (fractional bits) (ablation)MBOK · OPT smallperplexityImproved
use MBOK at 2-bit budget instead of ShiftAddLLM 2.2-bitMBOK · OPT small C4perplexity: 435.84 -> 32.23Improved
use MBOK instead of BitNet b1.58 finetuning at 1.58 bitMBOK · OPT small C4perplexity: 10199.89 -> reasonable (not given)Improved
use BitBLAS 1-bit kernels instead of FP16 weightsMBOK · LLaMA large linear layerslatency speedup: up to 8.7xImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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