AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models

Tianao Zhang, Zhiteng Li, Xianglong Yan, Haotong Qin, Yong Guo, 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 Masked Calibration Simulation (ablation)Quant-dLLM · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 52.10 -> 56.87Improved
add Masked Calibration Simulation (ablation)Quant-dLLM · MMLU 5-shot, Dream-7B-Baseaccuracy: 37.81 -> 40.22Improved
add ABMP with 5% reallocation (ablation)Quant-dLLM · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 54.32 -> 56.87Improved
add ABMP with 10% reallocation (ablation)Quant-dLLM · MMLU 5-shot, Dream-7B-Baseaccuracy: 32.75 -> 40.22Improved
raise ABMP reallocation ratio from 5% to 15% (ablation)Quant-dLLM · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 56.87 -> 53.01Hurt
raise ABMP reallocation ratio from 10% to 15% (ablation)Quant-dLLM · MMLU 5-shot, Dream-7B-Baseaccuracy: 40.22 -> 31.11Hurt
add RSR (without data-aware objective) to baseline quantizer (ablation)DAQ · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 39.26 -> 48.32Improved
add data-aware objective (DOR) on top of RSR (ablation)DAQ · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 48.32 -> 56.87Improved
add RSR and DOR to baseline quantizer (ablation)DAQ · MMLU 5-shot, Dream-7B-Baseaccuracy: 27.84 -> 40.22Improved
increase calibration samples from 128 to 256 (ablation)Quant-dLLM · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 56.87 -> 55.59No clear effect
increase calibration samples from 64 to 128 (ablation)Quant-dLLM · MMLU 5-shot, LLaDA-8B-Baseaccuracy: 54.49 -> 56.87Improved
use Quant-dLLM instead of Slim-LLM2-bit PTQ · 7 general tasks avg, LLaDA-8B-Baseaverage accuracy: 42.39 -> 54.06Improved

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