Search Results for author:
Found 3 papers, 1 papers with code
Learning More Generalized Experts by Merging Experts in Mixture-of-Experts
This approach, combined with the subsequent learning of the router's expert selection, allows the model to determine if the most frequently selected experts have learned the same feature differently.
Diverse Feature Learning by Self-distillation and Reset
Our paper addresses the problem of models struggling to learn diverse features, due to either forgetting previously learned features or failing to learn new ones.
Emotional Voice Conversion using Multitask Learning with Text-to-speech
The embedding space of seq2seq-based TTS has abundant information on the text.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
