TensorFlow

Guiding Frozen Language Models with Learned Soft Prompts http://ai.googleblog.com/2022/02/guiding-frozen-language-models-with.html @tensorflowblog

Nested Hierarchical Transformer: Towards Accurate, Data-Efficient, and Interpretable Visual Understanding http://ai.googleblog.com/2022/02/nested-hierarchical-transformer-towards.html @tensorflowblog

https://blog.tensorflow.org/2022/02/tfrt-progress-update.html @tensorflowblog

Robot See, Robot Do http://ai.googleblog.com/2022/02/robot-see-robot-do.html @tensorflowblog

Unlocking the Full Potential of Datacenter ML Accelerators with Platform-Aware Neural Architecture Search http://ai.googleblog.com/2022/02/unlocking-full-potential-of-datacenter.html @tensorflowblog

Can Robots Follow Instructions for New Tasks? http://ai.googleblog.com/2022/02/can-robots-follow-instructions-for-new.html @tensorflowblog

Applying Differential Privacy to Large Scale Image Classification http://ai.googleblog.com/2022/02/applying-differential-privacy-to-large.html @tensorflowblog

https://blog.tensorflow.org/2022/01/body-segmentation.html @tensorflowblog

Controlling Neural Networks with Rule Representations http://ai.googleblog.com/2022/01/controlling-neural-networks-with-rule.html @tensorflowblog

Does Your Medical Image Classifier Know What It Doesn’t Know? http://ai.googleblog.com/2022/01/does-your-medical-image-classifier-know.html @tensorflowblog

Resolving High-Energy Impacts on Quantum Processors http://ai.googleblog.com/2022/01/resolving-high-energy-impacts-on.html @tensorflowblog

Accurate Alpha Matting for Portrait Mode Selfies on Pixel 6 http://ai.googleblog.com/2022/01/accurate-alpha-matting-for-portrait.html @tensorflowblog

Separating Birdsong in the Wild for Classification http://ai.googleblog.com/2022/01/separating-birdsong-in-wild-for.html @tensorflowblog

LaMDA: Towards Safe, Grounded, and High-Quality Dialog Models for Everything http://ai.googleblog.com/2022/01/lamda-towards-safe-grounded-and-high.html @tensorflowblog

https://blog.tensorflow.org/2022/01/improved-tensorflow-27-operations-for.html @tensorflowblog

December 22, 2021 Introducing TorchVision’s New Multi-Weight Support API TorchVision has a new backwards compatible API for building models with multi-weight support. The new API allows loading different pre-trained weights on the same model variant, keeps track of vital meta-data such as the classification labels and includes the preprocessing transforms necessary for using the models. In this blog post, we plan to review the prototype API, show-case its features and highlight key differences with the existing one. https://pytorch.org//blog/introducing-torchvision-new-multi-weight-support-api/ @pytorch

LaMDA: Towards Safe, Grounded, and High-Quality Dialog Models for Everything http://ai.googleblog.com/2022/01/lamda-towards-safe-grounded-and-high.html @tensorflowblog

https://blog.tensorflow.org/2022/01/improved-tensorflow-27-operations-for.html @tensorflowblog

Introducing StylEx: A New Approach for Visual Explanation of Classifiers http://ai.googleblog.com/2022/01/introducing-stylex-new-approach-for.html @tensorflowblog

https://blog.tensorflow.org/2022/01/on-device-one-shot-learning-for-image.html @tensorflowblog