AI Paper Atlas

Research map / Architectures and efficiency / Quantization

ProQuant: Progressive Quantization-aware Training for Edge MLLMs

Yufei Xue, Yushi Huang, Jiawei Shao, Pingcheng Dong, Yonghao Tan, Shiyao Li, Kwang-Ting Cheng, Jun Zhang

NeurIPS 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of LLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes ProQuant, a progressive quantization-aware training approach for compressing multi-modal LLMs for edge deployment.

Problem

Multi-modal LLMs have heavy compute and memory requirements that hinder deployment on resource-constrained edge devices; post-training quantization is one route, but the abstract is truncated before its limitations are stated.

Approach

Uses progressive quantization-aware training for MLLMs, as the title indicates; the specific mechanism is not described in the available abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add self-relabeling (SRL) to naive QAT (ablation)naive QAT · Qwen3-VL-2B W4A8 / W4A4average accuracy: +1.00 (W4A8), +3.36 (W4A4)Improved
add progressive block activation (PBA) to naive QAT (ablation)naive QAT · Qwen3-VL-2B W4A8 / W4A4average accuracy: +0.67 (W4A8), +3.02 (W4A4)Improved
combine SRL and PBA (ablation)naive QAT · Qwen3-VL-2B W4A8 / W4A4average accuracy: +1.44 (W4A8), +6.07 (W4A4)Improved
prioritize vision-sensitive blocks (high tau) instead of low tau (ablation)ProQuant · Qwen3-VL-2B W4A8average accuracy: 72.03 -> 72.54Improved
use tau instead of weight gradient norm as activation metric (ablation)ProQuant · Qwen3-VL-2B W4A8average accuracy: 72.19 -> 72.54Improved
use logarithmic instead of linear scheduler (ablation)ProQuant · Qwen3-VL-2B W4A8average accuracy: 71.00 -> 72.54Improved
treat each decoding layer as unit vs two layers (ablation)ProQuant · Qwen3-VL-2B W4A8average accuracy: 70.28 -> 72.54Improved
split decoding layer into attn and ffn units (finer granularity) (ablation)ProQuant · Qwen3-VL-2B W4A8average accuracy: 72.54 -> 72.15Hurt
use self labels instead of GPT-4 labels (ablation)ProQuant · Qwen3-VL-2B W4A4average accuracy: 56.78 -> 59.83Improved
use self labels instead of 8B homogeneous labels (ablation)ProQuant · Qwen3-VL-2B W4A4average accuracy: 59.04 -> 59.83Improved
keep down_proj activations at 8-bitW4A4 ProQuant · three Qwen VL backbonesaverage accuracy: +1.44, +9.39, +3.21Improved
use ProQuant QAT instead of MBQ PTQW8A8 quantization · Qwen3-VL-2B W8A8average accuracy: 73.95 (MBQ) vs 72.88 (ProQuant)No clear effect

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