关注
Davis Yoshida
Davis Yoshida
在 ttic.edu 的电子邮件经过验证
标题
引用次数
引用次数
年份
Convolution based smooth approximations to the absolute value function with application to non-smooth regularization
S Voronin, G Ozkaya, D Yoshida
arXiv preprint arXiv:1408.6795, 2014
212014
Adding recurrence to pretrained transformers for improved efficiency and context size
D Yoshida, A Ettinger, K Gimpel
arXiv preprint arXiv:2008.07027, 2020
62020
NF4 Isn't Information Theoretically Optimal (and that's Good)
D Yoshida
arXiv preprint arXiv:2306.06965, 2023
42023
Using confusion graphs to understand classifier error
D Yoshida, J Boyd-Graber
Proceedings of the Workshop on Human-Computer Question Answering, 48-52, 2016
32016
Reconsidering the past: Optimizing hidden states in language models
D Yoshida, K Gimpel
arXiv preprint arXiv:2112.08653, 2021
22021
Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers
LK Senel, B Fetahu, D Yoshida, Z Chen, G Castellucci, N Vedula, J Choi, ...
arXiv preprint arXiv:2406.05255, 2024
12024
MAP's not dead yet: Uncovering true language model modes by conditioning away degeneracy
D Yoshida, K Goyal, K Gimpel
arXiv preprint arXiv:2311.08817, 2023
12023
Making the Most of your Model: Methods for Finetuning and Applying Pretrained Transformers
D Yoshida
arXiv preprint arXiv:2408.16241, 2024
2024
Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers
L Kerem Senel, B Fetahu, D Yoshida, Z Chen, G Castellucci, N Vedula, ...
arXiv e-prints, arXiv: 2406.05255, 2024
2024
Generative explore-exploit: Training-free optimization of generative recommender systems using LLM optimizers
B Fetahu, Z Chen, D Yoshida, G Castellucci, N Vedula, J Choi, S Malmasi
2024
Domain Adaptation for Factoid Question Answering
D Yoshida
University of Colorado at Boulder, 2017
2017
系统目前无法执行此操作,请稍后再试。
文章 1–11