Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models.
Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu
Browse the full AAAI paper archive.
Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu
Browse the full AAAI paper archive.