Author

Falong Tan

h-index 5 View on Semantic Scholar

We have 1 of 21 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

A Unified Framework for In-Context Learning with Causal and Masked Language Models

Experiments on controlled function-learning tasks show that the Masked Pair Encoder can achieve performance comparable to GPT-2-style causal Transformers, suggesting that ICL behavior is not specific to causal language models.

Chenrui Liu, Chuanlong Xie, Falong Tan et al. · 0 citations