AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Bi-VLM: Binary Post-Training Quantization for Vision-Language Models

Xijun Wang, Rayyan Abdalla, Junyun Huang, Chengyuan Zhang, Ruiqi Xian, Dinesh Manocha

AAAI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Attention-based visual token pruning · 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 Bi-VLM, a binary post-training quantization method for vision-language models aimed at ultra-low-bit weight precision.

Problem

The computational demands of vision-language models clash with the need for ultra-low-bit weight precision (bitwidth-level compression) for deployment.

Approach

Binary post-training quantization of VLM weights, targeting ultra-low-bit (near 1-bit) weight precision without retraining. Details beyond the abstract are not available.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hybrid precision quantization (2-bit salient weights) to fixed binary (ablation)Bi-VLM · ScienceQA-IMG ablation (Llama 3.2-Vision-11B)accuracy: 6.33 -> 13.74Improved
add adaptive saliency search (ablation)Bi-VLM · ScienceQA-IMG ablation (Llama 3.2-Vision-11B)accuracy: 13.74 -> 49.51Improved
add multiple unsalient search (ablation)Bi-VLM · ScienceQA-IMG ablation (Llama 3.2-Vision-11B)accuracy: 49.51 -> 58.35Improved
quantize only the language model vs only the vision model (ablation)Bi-VLM · ScienceQA-IMG, component quantized (Llama 3.2-Vision-11B)accuracy: 85.23 -> 58.75Hurt
quantize adaptor/projector only (ablation)Bi-VLM · ScienceQA-IMG, component quantized (Llama 3.2-Vision-11B)accuracy: 85.82 -> 85.86No clear effect
use Bi-VLM instead of BiLLM for whole-VLM binarizationLlama 3.2-Vision-11B · ScienceQA-IMG (Llama 3.2-Vision-11B)accuracy: 17.4 -> 58.35Improved
use Bi-VLM instead of BiLLM for quantization procedureLlama 3.2-Vision-11B · ScienceQA-IMG (Llama 3.2-Vision-11B)quantization time: 139.8 Mins -> 9.6 MinsImproved
use Bi-VLM instead of BiLLM on MME CognitionLlama 3.2-Vision-11B · MME Cognition (whole VLM quantized, 1-1.1 bit)score: 222.85 -> 196.07Hurt
use Bi-VLM instead of BiLLM on MME PerceptionQwen2.5-VL-7B-Instruct · MME Perception (whole VLM quantized, 1-1.1 bit)score: 828.54 -> 1458.70Improved
use Bi-VLM instead of BiLLM on MMMULLaVA-OneVision-7B · MMMU (whole VLM quantized, 1-1.1 bit)score: 28.78 -> 39.12Improved

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