AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

IVQ: Structured and Lightweight Vector Quantization via Binary Hierarchical Composition Inspired by $\textit{IChing}$

Heda Zuo, Junxian Wu, Fengjie Lu, Pei Chen, Lingyun Sun, Weitao You

ICML 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment

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 hierarchical design (ablation)IVQ · Visual reconstructionPSNR: 20.93 -> 21.20Improved
add structured (relational) design (ablation)IVQ · Visual reconstructionFID: 4.86 -> 4.33Improved
add IVQ in place of plain quantizer (ablation)bottom-up IVQ · Visual reconstructionPSNR: 19.68 -> 21.20Improved
add hierarchical design (ablation)Yin-Yang IVQ · Audio reconstructionKLD: 0.89 -> 0.68Improved
add structured (relational) design (ablation)Yin-Yang IVQ · Audio reconstructionKLD: 0.76 -> 0.68Improved
use IVQ 4x2 instead of 4x64 RVQ (ablation)Encodec · Audio reconstructionKLD: 0.79 -> 0.68Improved
share subspace codebook across pieces (ablation)IVQ · Audio reconstructionKLD: 0.86 -> 0.68Improved
use bottom-up instead of Yin-Yang-only layers (ablation)IVQ · Visual reconstructionPSNR: 13.40 -> 21.20Improved
use 4-line hexagrams (16 codes) vs 16-code RVQ (ablation)IVQ · Audio reconstructionKLD: 0.87 -> 0.82Improved
replace VQVAE with IVQVQVAE · ImageNet-1k reconstructionFID: 12.26 -> 8.84Improved
replace VQ with IVQ in ViT-VQVAEViT-VQVAE · ImageNet-1k reconstructionFID: 2.95 -> 2.77Improved
add IVQ to EncodecEncodec · MTG music reconstructionFAD: 1.60 -> 2.56Hurt

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