AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Hyperbolic Hierarchical Alignment Reasoning Network for Text-3D Retrieval

Wenrui Li, Yidan Lu, Yeyu Chai, Rui Zhao, Hengyu Man, Xiaopeng Fan

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 2 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 hierarchical ordering loss (ablation)H2ARN · T3DR-HIT v2Rsum: 229.6 -> 238.5Improved
add contribution-aware hyperbolic aggregation (ablation)H2ARN · T3DR-HIT v2Rsum: 233.5 -> 238.5Improved
add both ordering loss and aggregation (ablation)H2ARN · T3DR-HIT v2Rsum: 222.0 -> 238.5Improved
use contribution-aware aggregation instead of mean pooling in Euclidean space (ablation)Euclidean baseline · T3DR-HIT v2Rsum: 196.3 -> 215.1Improved
move from Euclidean to Lorentz hyperbolic space (with ordering loss) (ablation)Eu + CA · T3DR-HIT v2Rsum: 215.1 -> 238.5Improved
replace CLIP+PointNet with CLIP+DGCNN backbone in RMARNRMARN · T3DR-HIT v2Rsum: 127.3 -> 220.3Improved
vary attention heads and SA layers (ablation)H2ARN · T3DR-HIT v2Rsum: 210.2 to 238.5Mixed
H2ARN vs RMARN with same CLIP+DGCNN backbonesH2ARN · T3DR-HIT v2Rsum: 220.3 -> 238.5Improved

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