Comment Comment by Xudong Yes, they are similar. Actually, our initial paper was presented around five months ago (https://arxiv.org/abs/2311.09000). Unfortunately, our paper isn't cited by the DeepMind paper, which you may see this discussion as an example: https://x.com/gregd_nlp/status/1773453723655696431Compared with our initial version, we have mainly focused on its efficiency, with a 10X faster checking process without decreasing accuracy. parent Xudong 2 years ago
Compared with our initial version, we have mainly focused on its efficiency, with a 10X faster checking process without decreasing accuracy.