← Search

Siyu Zhao

2 accepted papers

2025

Learning Invariant Causal Mechanism from Vision-Language Models

ICML 2025poster

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, but its performance can degrade when fine-tuned in out-of-distribution (OOD) scenarios. We model the prediction process using a Structural Causal Model (SCM) and show that the causal mechanism involving both invariant and…

Cited by 0SourcePDFScholar
2025

Towards the Causal Complete Cause of Multi-Modal Representation Learning

ICML 2025poster

Multi-Modal Learning (MML) aims to learn effective representations across modalities for accurate predictions. Existing methods typically focus on modality consistency and specificity to learn effective representations. However, from a causal perspective, they may lead to representations that contai…

Cited by 0SourcePDFScholar