Research talk: NUWA: Neural visual world creation with multimodal pretraining

Channel:
Microsoft Research
Subscribers:
344,000
Published on ● Video Link: https://www.youtube.com/watch?v=jhmJ5qb-JAU


Duration: 23:23
1,496 views
0

Speakers:
Lei Ji, Senior Researcher, Microsoft Research Asia
Chenfei Wu, Senior Researcher, Microsoft Research Asia

Over the past years, large-scale pretrained models with billions of parameters have improved the state of the art in nearly every natural language processing (NLP) task. These models are fundamentally changing the research and development of NLP and AI in general. Recently, researchers are expanding such models beyond natural language texts to include more modalities, such as structured knowledge bases, images, and videos. With this background, the talks in this session are expected to introduce the latest advances in pretrained models, and also discuss the future of this research frontier. Hear from Lei Ji and Chenfei Wu from Microsoft Research Asia, in the second of three talks on recent advances and applications of language model pertaining.

Learn more about the 2021 Microsoft Research Summit: https://Aka.ms/researchsummit



Other Videos By Microsoft Research


2022-02-08Research talk: Focal Attention: Towards local-global interactions in vision transformers
2022-02-08Research talk: Knowledgeable pre-trained language models
2022-02-08Opening remarks: Deep Learning and Large-Scale AI
2022-02-08Closing remarks: Cloud Intelligence/AIOps
2022-02-08Research talk: Optimizing the cloud supply chain
2022-02-08Research talk: Automating and Optimizing IT Operations Management with AI
2022-02-08Research talk: An intelligent data-driven paradigm towards cloud reliability
2022-02-08Talk: Multidimensional analysis of cloud-native software based on large-scale operation data
2022-02-08Keynote: Cloud Intelligence: Infusing AI into cloud computing systems
2022-02-08Opening remarks: Cloud Intelligence/AIOps
2022-02-08Research talk: NUWA: Neural visual world creation with multimodal pretraining
2022-02-08Research talk: Large-scale, self-supervised pretraining: From language to vision
2022-02-08Roundtable discussion: Efficient and adaptable large-scale AI
2022-02-08Research talk: Prompt tuning: What works and what's next
2022-02-08Closing remarks: Research for Carbon Negative
2022-02-08Research talks: Research partners on innovation for carbon neutralization
2022-02-08Panel: Innovative solutions and frontier technology for carbon neutralization from different angles
2022-02-08Research talk: Nexus between climate change and energy policy: Lessons from California
2022-02-08Research talk: Sustainable energy for all and the role of innovation
2022-02-08Research talk: When climate is everything, all systems must change
2022-02-08Research talk: Getting to net zero safely


Tags:
deep learning
large-scale models
large-scale AI models
AI
artificial intelligence
microsoft research summit