Alexa

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.

Digital assistants developed by competing teams helped users perform cooking and home-improvement tasks.

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.

Reducing false positives for rare events, adapting Echo hardware to ultrasound sensing, and enabling concurrent ultrasound sensing and music playback are just a few challenges Amazon researchers addressed.