Reactive Machines

Omnichannel ordering with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic

Omnichannel ordering with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic

Introduction Building a voice-enabled ordering system that works across mobile apps, websites, and voice interfaces (an omnichannel approach) presents real…
What Does Your Text Know? (The Answer May Surprise You!)

What Does Your Text Know? (The Answer May Surprise You!)

Recent work has shown that experimental internal models can reveal a wealth of information that is not apparent in model…
Introducing granular cost attribution for Amazon Bedrock

Introducing granular cost attribution for Amazon Bedrock

As AI inference grows into a significant share of cloud spend, understanding who and what are driving costs is essential…
Optimize video semantic search intent with Amazon Nova Model Distillation on Amazon Bedrock

Optimize video semantic search intent with Amazon Nova Model Distillation on Amazon Bedrock

Developing video semantic search models requires measurement accuracy, cost, and latency. Fast, small models lack routing intelligence, while large, intuitive…
Nova Forge SDK series part 2: Practical guide to fine-tune Nova models using data mixing capabilities

Nova Forge SDK series part 2: Practical guide to fine-tune Nova models using data mixing capabilities

This hands-on guide walks through every step of fine-tuning an Amazon Nova model with the Amazon Nova Forge SDK, from…
International Conference on Learning Representations (ICLR) 2026

International Conference on Learning Representations (ICLR) 2026

Apple is presenting new research at the annual International Conference on Learning Representations (ICLR), which takes place in person in…
Cost-efficient custom text-to-SQL using Amazon Nova Micro and Amazon Bedrock on-demand inference

Cost-efficient custom text-to-SQL using Amazon Nova Micro and Amazon Bedrock on-demand inference

Text-to-SQL generation remains a persistent challenge in enterprise AI applications, particularly when working with custom SQL dialects or domain-specific database…
MixAtlas: Development of Uncertainty Data Integration for Multimodal LLM Midtraining

MixAtlas: Development of Uncertainty Data Integration for Multimodal LLM Midtraining

This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models (NADPFM) at ICLR 2026.…
Dala amathiphu acebile, wangokwezifiso ku-Amazon Quick Sight

Dala amathiphu acebile, wangokwezifiso ku-Amazon Quick Sight

I-Amazon Quick Sight, ikhono lebhizinisi lobuhlakani (BI) le-Amazon Quick, iyisevisi ye-BI ehlangene. Ihlinzeka ngamadeshibhodi esimanje asebenzisanayo, imibuzo yolimi lwemvelo, imibiko…
Navigating the generative AI journey: The Path-to-Value framework from AWS

Navigating the generative AI journey: The Path-to-Value framework from AWS

Generative AI is reshaping how organizations approach productivity, customer experiences, and operational capabilities. Across industries, teams are experimenting with generative…
Back to top button