AI Paper Atlas

Research map / Architectures and efficiency / Quantization

PT$^2$-LLM: Post-Training Ternarization for Large Language Models

Xianglong Yan, ChengZhu Bao, Zhiteng Li, Tianao Zhang, Kaicheng Yang, Haotong Qin, Ruobing Xie, Xingwu Sun, Yulun Zhang

ICLR 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of LLMs · 7 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
add Iterative Ternary Fitting (ablation)PT2-LLM on LLaMA-2-7B · WikiText2perplexity: 22.88 -> 15.47Improved
add Activation-aware Grid Alignment (ablation)PT2-LLM on LLaMA-2-7B · 7 zero-shot tasksavg accuracy: 37.11 -> 42.86Improved
add ITF (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 247.75 -> 83.76Improved
add AGA (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 247.75 -> 47.83Improved
add AGA on top of ITF (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 83.76 -> 32.19Improved
add SSR instead of no reordering (ablation)PT2-LLM on LLaMA-2-7B · 7 zero-shot tasksavg accuracy: 41.37 -> 43.33Improved
add SSR instead of no reordering (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 112.83 -> 32.19Improved
use SSR instead of Hessian-based reordering (ablation)PT2-LLM on LLaMA-2-7B · 7 zero-shot tasksavg accuracy: 39.15 -> 43.33Improved
use random reordering instead of none (ablation)PT2-LLM on LLaMA-2-7B · 7 zero-shot tasksavg accuracy: 41.37 -> 40.86No clear effect
use Hessian-based reordering instead of none (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 112.83 -> 35.86Improved
increase calibration set from 64 to 128 samples (ablation)PT2-LLM on LLaMA-3-8B · WikiText2perplexity: 38.90 -> 32.19Improved
increase calibration set from 128 to 256 samples (ablation)PT2-LLM on LLaMA-2-7B · 7 zero-shot tasksavg accuracy: 43.33 -> 43.55No clear effect

Later papers that compared with this method

1 later accepted paper reports PT2-LLM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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