Semantic-aware Contrastive Learning via Multi-prompt Alignment

Feb 6, 2025·
Zhuoran Zhao
Equal contribution
秦皓
秦皓
Equal contribution
,
Ming Kong
,
Luyuan Chen
,
Di Xie
,
Jiang Zhu
,
Qiang Zhu
· 1 min read
Abstract
This work studies semantic-aware positive sample generation for contrastive learning through multi-source and multi-modal prompt alignment. It uses large multimodal model capabilities to improve semantic consistency and sample diversity.
Type
Publication
Machine Learning
publications

The paper investigates how semantic consistency in generated positive samples affects representation learning.

Contrastive Learning Self-Supervised Learning Multimodal Learning
秦皓
Authors
秦皓
Ph.D. Student at Zhejiang University

I am a Ph.D. student in the College of Computer Science and Technology at Zhejiang University. My research focuses on spatial intelligence, 3D-AIGC, multi-agent systems, latent reasoning for VLMs, and contrastive learning, with a broader interest in building intelligent systems that connect perception, reasoning, and controllable creation in the world.

Email: haoqin@zju.edu.cn