Sony's Research Minds is an interview program where we invite individuals conducting outstanding research to delve into the allure of their work.
This time, we discuss the accepted paper "CTM" at ICLR 2024.
Kim, Dongjun and Lai, Chieh-Hsin and Liao, Wei-Hsiang and Murata, Naoki and Takida, Yuhta and Uesaka, Toshimitsu and He, Yutong and Mitsufuji, Yuki and Ermon, Stefano,
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
project page: consistencytra...
code: github.com/son...
- VIDEO -
Creative Direction & Cinematographer: Yuki Asukabe
1st Assistant Camera: Katsuya Sakoyama
Special Thanks: Backcasters
日本語字幕: Hiromichi Kamata
--
We have launched a video channel introducing information related to Sony's open-source deep learning framework software, Neural Network Libraries (nnabla.org/, github.com/son.... In addition to tutorials and tips on Neural Network Libraries, we will also share cutting-edge deep learning technology information (lectures, introductions to state-of-the-art papers). Please subscribe to our channel and support us ( / nnabla .
Similarly, the very popular KZitem channel ( / @neuralnetworkconsole ) by Sony's intuitive GUI-based deep learning development environment, Neural Network Console (dl.sony.com/), also publishes numerous deep learning technical courses and tool tutorials. Please subscribe to and support this channel as well.
#ai #diffusion_ai #stablediffusion #generativemodels #neuralnetworks #deeplearning
Негізгі бет [AI paper] CTM: Advanced Single-Step DIffusion Model for Fast and High-Quality Sampling (日本語字幕付)
Пікірлер