On the Second Half of Machine Translation
Published:
Many think that machine translation (MT) is a solved problem, but is it really? While significant progress has been made with models like GPT-4 and other large language models, challenges remain.
Thoughts
Besides writing research papers, I also enjoy sharing my thoughts and experiences. These posts are not formal academic articles, but rather personal reflections on various topics related to my research and interests, so I will not rigorously acknowledge all the sources. I hope you find them interesting and thought-provoking!
When Test-Time Scaling Works
Published:
Test-time scaling (TTS) involves investing more computational resources during inference to enhance model performance on complex tasks, especially reasoning. There are various TTS methods, such as chain-of-thought reasoning, self-consistency, and majority voting. As long as the method involves additional computation during inference, it can be considered a TTS method.