AI Paper Atlas

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

Hyperbolic Gramian Volumes for Multimodal Alignment

Saiyang Na, Feng Jiang, Qifeng Zhou, Wenliang Zhong, Thao M. Dang, Yuzhi Guo, Hehuan Ma, Chunyuan Li, Weizhi An, Junzhou Huang

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer

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
replace Euclidean Gramian volume with hybrid Euclidean-hyperbolic volumeGRAM on VAST backbone · MSR-VTT zero-shotT2V Recall@1: 54.8 -> 56.6Improved
use pure hyperbolic volume (alpha = 0) instead of Euclidean GRAM (ablation)GRAM · MSR-VTT zero-shotT2V Recall@1: 54.8 -> 54.8No clear effect
use pure hyperbolic volume instead of Euclidean GRAM (ablation)GRAM · DiDeMo and VATEX zero-shotT2V Recall@1: DiDeMo 49.8 -> 49.1; VATEX 77.0 -> 76.7Hurt
use pure hyperbolic volume instead of Euclidean GRAM (ablation)GRAM · ActivityNet zero-shotT2V Recall@1: 56.2 -> 57.0Improved
add learnable hybrid mixing (alpha = 0.5148) over pure hyperbolic (ablation)HyperGRAM · MSR-VTT zero-shotT2V Recall@1: 0.548 -> 0.566Improved
switch from Euclidean volume to hyperbolic Lorentzian volume: variance of volumesGramian volume · MSR-VTT volume statisticsvolume std: 0.005 -> 0.12Improved
set curvature c = 1.0 versus near-Euclidean c = 0.05 (ablation)HyperGRAM · MSR-VTT zero-shotT2V Recall@1: 0.551 -> 0.566Improved
raise curvature to c = 9.0 (ablation)HyperGRAM · MSR-VTT zero-shotT2V Recall@1: 0.566 -> 0.564No clear effect
add audio modality to hybrid volume (ablation)HyperGRAM · MSR-VTT zero-shotT2V Recall@1: 0.532 -> 0.548Improved
add subtitle modality (TVAS vs TVA) (ablation)HyperGRAM · MSR-VTT zero-shotT2V Recall@1: 0.548 -> 0.566Improved
vary alpha across [0.3, 0.7] around the learned value (ablation)HyperGRAM · four video-text benchmarksT2V Recall@1No clear effect
use hybrid geometry instead of either pure space (ablation)HyperGRAM · MSR-VTTT2V Recall@1: +1.3-1.8%Improved

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