2 papers
q-bio.GN2025
DNAMotifTokenizer: Towards Biologically Informed Tokenization of Genomic Sequences
Xiaoxiao Zhou, Zihan Wang, Jingbo Shang +1
DNA language models have advanced genomics, but their downstream performance varies widely due to differences in tokenization, pretraining data, and architecture. We argue that a m…
cs.CL2025
Order Matters: Rethinking Prompt Construction in In-Context Learning
Warren Li, Yiqian Wang, Zihan Wang +1
In-context learning (ICL) enables large language models to perform new tasks by conditioning on a sequence of examples. Most prior work reasonably and intuitively assumes that whic…