
Daiki Chijiwa
@dchiji_en
Researcher at NTT / Interests: neural networks, loss landscape, learning theory
ID: 1400455668553818124
https://dchiji.github.io/ 03-06-2021 14:13:55
70 Tweet
119 Takipçi
197 Takip Edilen

Our "Portable Reward Tuning" paper has been accepted to #ICML2025, which proposes a new fine-tuning framework based on KL-regularized reward maximization, jointly with Taku Hasegawa🔥 We also have one more accepted paper on DP-ICL, which will be available soon.
