← Search

Ye Jun Jian

2 accepted papers

2025

CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models

EMNLP 2025

Large Language Models (LLMs) have achieved remarkable success across various domains. However, a fundamental question remains: Can LLMs effectively utilize causal knowledge for prediction and generation? Through empirical studies, we find that LLMs trained directly on large-scale data often capture

2025

ERICT: Enhancing Robustness by Identifying Concept Tokens in Zero-Shot Vision Language Models

ICML 2025poster

Pre-trained vision-language models (VLMs) have revolutionized the field of machine learning, demonstrating exceptional performance across a wide range of tasks. However, their robustness remains vulnerable to the spurious-correlation problem. Existing works often involve fine-tuning the model with l…

Cited by 0SourcePDFScholar