9 papers
SPRI: SVD-Partitioned Residual Initialization for Data-Constrained MoE Upcycling
Weiqiao Shan, Ruixiang Mao, Yuang Li +10
Mixture-of-Experts (MoE) models enable efficient scaling, but training them from scratch remains prohibitively expensive. MoE upcycling mitigates this cost by converting pretrained…
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
Yingfeng Luo, Hongyu Liu, Dingyang Lin +6
Large Language Models (LLMs) have achieved remarkable performance in Machine Translation (MT), but deploying them at scale remains prohibitively expensive. A widely adopted remedy…
NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs
Yingfeng Luo, Ziqiang Xu, Yuxuan Ouyang +9
Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains chall…
APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards
Kaiyan Chang, Chenwei Zhu, Yingfeng Luo +7
Test-Time Scaling (TTS) has significantly enhanced the capabilities of Large Reasoning Models (LRMs) but introduces a critical side-effect known as Overthinking. We conduct a preli…
Scale-Aware Curriculum Learning for Ddata-Efficient Lung Nodule Detection with YOLOv11
Yi Luo, Yike Guo, Hamed Hooshangnejad +1
Lung nodule detection in chest CT is crucial for early lung cancer diagnosis, yet existing deep learning approaches face challenges when deployed in clinical settings with limited…
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
Weiqiao Shan, Yuang Li, Yuhao Zhang +9
Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captio…