6 papers
Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech
Siqi Ouyang, Shuoyang Ding, Oleksii Hrinchuk +4
Simultaneous speech translation (SST) generates translations while receiving partial speech input. Recent advances show that large language models (LLMs) can substantially improve…
Efficient Document Parsing via Parallel Token Prediction
Lei Li, Ze Zhao, Meng Li +6
Document parsing, as a fundamental yet crucial vision task, is being revolutionized by vision-language models (VLMs). However, the autoregressive (AR) decoding inherent to VLMs cre…
Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translation
Yifeng Liu, Siqi Ouyang, Yatish Hosmane Revanasiddappa +1
Large Language Models (LLMs) have demonstrated remarkable capability in machine translation on high-resource language pairs, yet their performance on low-resource translation still…
CMU's IWSLT 2025 Simultaneous Speech Translation System
Siqi Ouyang, Xi Xu, Lei Li
This paper presents CMU's submission to the IWSLT 2025 Simultaneous Speech Translation (SST) task for translating unsegmented English speech into Chinese and German text in a strea…
InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Model
Siqi Ouyang, Xi Xu, Lei Li
Simultaneous translation of unbounded streaming speech remains a challenging problem due to the need for effectively processing the history speech context and past translations so…
Anticipating Future with Large Language Model for Simultaneous Machine Translation
Siqi Ouyang, Oleksii Hrinchuk, Zhehuai Chen +4
Simultaneous machine translation (SMT) takes streaming input utterances and incrementally produces target text. Existing SMT methods mainly use the partial utterance that has alrea…