Showing 2024Show all
2 papers · 1 filter
cs.CL2024
Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning
Sungjin Park, Xiao Liu, Yeyun Gong +1
Despite recent advances in large language models, open-source models often struggle to consistently perform well on complex reasoning tasks. Existing ensemble methods, whether appl…
cs.LG2024
Multimodal Transformer With a Low-Computational-Cost Guarantee
Sungjin Park, Edward Choi
Transformer-based models have significantly improved performance across a range of multimodal understanding tasks, such as visual question answering and action recognition. However…