Alexa

AI models that generate stories, place objects in a visual scene, and assemble music on the fly customize content to children’s specifications.

Self-supervised training, distributed training, and knowledge distillation have delivered remarkable results, but they’re just the tip of the iceberg.

With an encoder-decoder architecture — rather than decoder only — the Alexa Teacher Model excels other large language models on few-shot tasks such as summarization and machine translation.

To become the interface for the Internet of things, conversational agents will need to learn on their own. Alexa has already started down that path.

Co-mingling industry experience and academic teaching.

From Josh Miele's passion for making the world more accessible to improving forecasting by learning quantile functions, these stories resonated with our audience.

Rohit Prasad on the pathway to generalizable intelligence and what excites him most about his re:MARS keynote.

Papers focus on learning previously unseen intents and personalization, both generally and in the specific case of recipe recommendation.

Knowledge distillation and discriminative training enable efficient use of a BERT-based model to rescore automatic-speech-recognition hypotheses.