← Search

Zhang Keli

2 accepted papers

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
2024

Learning Causal Relations from Subsampled Time Series with Two Time-Slices

ICML 2024spotlight

This paper studies the causal relations from subsampled time series, in which measurements are sparse and sampled at a coarser timescale than the causal timescale of the underlying system. In such data, because there are numerous missing time-slices (i.e., cross-sections at each time point) between…

Cited by 0SourcePDFScholar