AI Paper Atlas

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

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization

Jiehui Luo, Yuguo Yin, Yuxin Xie, Jinghan Ru, Xianwei Zhuang, Minghua He, Aofan Liu, Zihan Xiong, Dongchao Yang

ICLR 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 bidirectional DynamicSVR regularizerInfoNCE · AudioCaps (monolingual)T2A R@1: 41.87 -> 44.16Improved
add bidirectional DynamicSVR regularizerSigLIP · AudioCaps (monolingual)T2A R@1: 36.74 -> 43.09Improved
add bi-DynamicSVRInfoNCE · ESC-50 zero-shottop-1 accuracy: 89.6 -> 92.1Improved
use dynamic radius predictor instead of static learnable radius (ablation)bi-SVR on InfoNCE · AudioCaps (monolingual)A2T R@1: 57.77 -> 59.66Improved
make SVR bidirectional instead of text-to-audio only (ablation)DynamicSVR · AudioCaps (monolingual)A2T R@1: 58.51 -> 59.66Improved
add constraint term L_cons to radius predictor (ablation)bi-DynamicSVR · AudioCaps (monolingual)T2A R@1: 44.01 -> 44.16Improved
add constraint term L_cons to radius predictor (ablation)uni-DynamicSVR · AudioCaps (monolingual)A2T R@1: 57.67 -> 58.51Improved
replace SVR with learnable scaling of positive probability (Simple Reweight) (ablation)InfoNCE · AudioCaps (monolingual)A2T R@1: 56.72 -> 51.26Hurt
add bi-DynamicSVR trained on AudioCaps, tested on ClothoInfoNCE · AudioCaps -> ClothoA2T R@1: 18.1643 -> 20.1932Improved
add bi-DynamicSVR on large-scale WavCapsInfoNCE · WavCapsT2A R@1: 7.76 -> 8.30Improved
use InfoNCE rather than SigLIP loss as base (ablation)contrastive loss · AudioCaps (monolingual)T2A R@1: 36.74 -> 41.87Improved
add bi-DynamicSVR to ATRI-CACL on multilingualATRI-CACL · AudioCaps (multilingual)T2A R@1: 39.44 -> 43.61Improved

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