VASA-1 - Microsoft Research
www.microsoft.com/en-us/research/project/vasa-1
What Jamie wrote
The example videos in this research writeup are incredible. If you look really, really close you can see some errors. But the fact that these videos of talking heads were created with just a single still image is mind blowing. We need to assume that anything being said by anyone in a video could be generated.
Same host · 8 links from microsoft.com
- LAMBDA: The ultimate Excel worksheet function - Microsoft Research
- Phi-2: The surprising power of small language models - Microsoft Research
- GraphRAG: Unlocking LLM discovery on narrative private data - Microsoft Research
- AI at Work Is Here. Now Comes the Hard Part
- Introducing KBLaM: Bringing plug-and-play external knowledge to LLMs - Microsoft Research
Saved the same week · 14 links that week
- Why the Short-Lived Calvin and Hobbes Is Still One of the Most Beloved & Influential Comic Strips | Open Culture
- Mental Health in Software Engineering
- My 25-Year Engineering Career Retrospective
- US Air Force says AI-controlled F-16 has fought humans • The Register
- Valkey is Rapidly Overtaking Redis - DevOps.com