Google llc (20250094838). Image Analysis by Prompting of Machine-Learned Models Using Chain of Thought
Image Analysis by Prompting of Machine-Learned Models Using Chain of Thought
Organization Name
Inventor(s)
Jason Weng Wei of Mountain View CA US
Dengyong Zhou of Redmond WA US
Dale Eric Schuurmans of Edmonton CA
Maarten Paul Bosma of Cupertino CA US
Ed Huai-Hsin Chi of Palo Alto CA US
Olivier Jean Andrè Bousquet of Zürich CH
Le Hou of South Setauket NY US
Charles Aloysius Sutton of Santa Clara CA US
[[:Category:Nathanael Martin Sch�rli of Mountain View CA US|Nathanael Martin Sch�rli of Mountain View CA US]][[Category:Nathanael Martin Sch�rli of Mountain View CA US]]
Nathan Kemp Sekiguchi Scales of Mountain View CA US
Augustus Quadrozzi Odena of San Francisco CA US
Sharan Ajit Narang of Mountain View CA US
Guy Gur-ari Krakover of Palo Alto CA US
Aakanksha Chowdhery of Santa Clara CA US
David Martin Dohan of San Francisco CA US
Aitor Lewkowycz of Mountain View CA US
Jacob Austin of New York NY US
Henryk Michalewski of Mountain View CA US
David Luan of Mountain View CA US
David J. Bieber of New York NY US
Anders Johan Andreassen of Princeton NJ US
Maxwell Isaac Nye of Mountain View CA US
Image Analysis by Prompting of Machine-Learned Models Using Chain of Thought
This abstract first appeared for US patent application 20250094838 titled 'Image Analysis by Prompting of Machine-Learned Models Using Chain of Thought
Original Abstract Submitted
an example technique for image analysis is provided. an example image analysis method includes obtaining an instructive sequence descriptive of an instructive query, an instructive response, and an instructive trace of intermediate states from the instructive query to the instructive response. the example image analysis method includes inputting, to a machine-learned model, the instructive sequence and an operative image processing query that comprises image data, wherein the machine-learned model is configured to process the operative query with attention over the instructive sequence. the example method can include generating, using the machine-learned model and responsive to the operative query, an operative image processing response that comprises an analysis of the image data.
- Google llc
- Jason Weng Wei of Mountain View CA US
- Dengyong Zhou of Redmond WA US
- Xuezhi Wang of New York NY US
- Dale Eric Schuurmans of Edmonton CA
- Quoc V. Le of Sunnyvale CA US
- Maarten Paul Bosma of Cupertino CA US
- Ed Huai-Hsin Chi of Palo Alto CA US
- Olivier Jean Andrè Bousquet of Zürich CH
- Le Hou of South Setauket NY US
- Charles Aloysius Sutton of Santa Clara CA US
- Nathan Kemp Sekiguchi Scales of Mountain View CA US
- Augustus Quadrozzi Odena of San Francisco CA US
- Sharan Ajit Narang of Mountain View CA US
- Guy Gur-ari Krakover of Palo Alto CA US
- Aakanksha Chowdhery of Santa Clara CA US
- David Martin Dohan of San Francisco CA US
- Aitor Lewkowycz of Mountain View CA US
- Jacob Austin of New York NY US
- Henryk Michalewski of Mountain View CA US
- David Luan of Mountain View CA US
- David J. Bieber of New York NY US
- Anders Johan Andreassen of Princeton NJ US
- Maxwell Isaac Nye of Mountain View CA US
- G06N5/022
- CPC G06N5/022
