Haoran Xu

X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models