Gallery
audio reactive
audio reactive StyleGAN
latent space interpolation
lyric driven music video
prompt driven pixcel art
genetic algorithm
Research Publications
-
ニューラルネットワークの知識蒸留による方程式抽出 / Equation Extraction through Knowledge Distillation of Neural Networks
岡田 領, 横山 諒伍, 松尾 豊
人工知能学会全国大会論文集 JSAI2022, 2022年
深層学習モデルの知識蒸留を用いた方程式抽出に関する研究
-
Construction and Validation of Action-Conditioned VideoGPT
Koudai Tabata, Junnosuke Kamohara, Ryosuke Unno, Makoto Sato, Taiju Watanabe, Taiga Kume, Masahiro Negishi, Ryo Okada, Yusuke Iwasawa, Yutaka Matsuo
37th Annual Conference of JSAI, 2023
World models using action-conditioned video prediction based on VideoGPT
-
Imitation Learning with Mid-Level Representations for Object Rearrangement
Makoto Sato, Ryosuke Unno, Hiroki Furuta, Tatsuya Matsushima, Ryo Okada, Pavel Savkin, Genki Sano, Yutaka Matsuo
36th Annual Conference of JSAI, 2022
Using depth maps as mid-level representations to improve robotic object manipulation through imitation learning
