@CVPR
, the premier computer vision conference happening now, has an amazing and diverse program with 2719 accepted papers (from 11352 submissions). It selected just two of these for the Best Paper Award, both with authors from @Google
: "Generative Image Dynamics"
All authors
@jeffdean
-
Google Wins Best Paper Awards at CVPR 2026 Conference
By
–
-
Using Gemini 1.5 Pro Long Context for Codebase Analysis
By
–
Nice thread on how to use the long context capabilities of Gemini 1.5 Pro to understand complex code bases. Various approaches like: "draw me an overall diagram of the major modules of the system" "draw me neural net architectures for any sub models used" "give me a list of
-
Gemini 1.5 Enables Interactive Experiences Through Visual Understanding
By
–
Lovely set of examples of how AI models like Gemini 1.5 can help create new interactive experiences because the model can actually understand high-level visual concepts, not just work with pixels. https://t.co/h8erVvvCfh
— Jeff Dean (@JeffDean) 6 juin 2024Lovely set of examples of how AI models like Gemini 1.5 can help create new interactive experiences because the model can actually understand high-level visual concepts, not just work with pixels.
-
Google Optimization Service: Network Design Documentation Link
By
–
https://
developers.google.com/optimization/s
ervice/shipping/network_design
… (linked from the blog post). @orwant as a heads up -
Container Shipping Efficiency Reduces Environmental Impact
By
–
Oh, and delivering 13% more containers with 15% fewer vessels is pretty good for the environment, as well.
-
Google AI Doubles Shipping Profit Via Network Optimization
By
–
Great work by @GoogleResearch
's Operations Research team on shipping logistics. "It is able to double the profit of a container shipper, deliver 13% more containers, and do so with 15% fewer vessels." The Shipping Network Design API for making your shipping ship shape: shipped! -
UW Researchers Develop Sound Isolation Technology Demo
By
–
I got an early demo of this when I visited @uwcse a couple months ago and the ability to isolate sounds in your environment was pretty great. Nice work, @b_veluri, Malek Itani, Tuochao Chen, Takuya Yoshioka, and @ShyamGollakota! https://t.co/dSmrGH90cz
— Jeff Dean (@JeffDean) 26 mai 2024I got an early demo of this when I visited @uwcse a couple months ago and the ability to isolate sounds in your environment was pretty great. Nice work, @b_veluri
, Malek Itani, Tuochao Chen, Takuya Yoshioka, and @ShyamGollakota
! -
Gemini 1.5 Pro and Flash Master Object Detection Tasks
By
–
Did you know Gemini 1.5 Pro and Gemini 1.5 Flash can do a pretty good job of things like "draw a blinding box around the turrets if the castle" or "draw a bounding box around the orange kitten"? You can try things like this yourself thanks to @ashkamath20 's colab! Check it out!
-
Gemini 1.5-Pro ranks second on Reward Bench Leaderboard
By
–
Gemini 1.5-Pro is a pretty good reward model (tops among generative models and second overall in the Reward Bench Leaderboard).
-
Gemini 1.5 Audio Analysis Capabilities Demonstrated at Google IO
By
–
Nice example of some of the audio analysis capabilities of the Gemini 1.5 models, using the video of the Google IO keynote as an example. https://t.co/RLG0DDm8Rm
— Jeff Dean (@JeffDean) 22 mai 2024Nice example of some of the audio analysis capabilities of the Gemini 1.5 models, using the video of the Google IO keynote as an example.