talk-data.com talk-data.com

YouTube 2025-12-07 at 07:13

AWS re:Invent 2025 - Unlock Advanced Model Training: Reinforcement Fine-tuning on Bedrock (AIM3327)

Description

Organizations struggle to customize AI models for complex tasks due to the extensive human annotation required for traditional fine-tuning approaches. Learn how Amazon Bedrock's new Reinforcement Fine Tuning (RFT) capabilities enable developers to train models using custom evaluators instead of large labeled datasets. Discover how to implement RFT with Amazon Nova and open-source models using techniques like RLVR for code generation and RLAIF for AI feedback. We'll demonstrate how these RL-based customization methods improve model accuracy, safety, and adaptability for enterprise applications while reducing the burden of data annotation.

Learn more: More AWS events: https://go.aws/3kss9CP

Subscribe: More AWS videos: http://bit.ly/2O3zS75 More AWS events videos: http://bit.ly/316g9t4

ABOUT AWS: Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts. AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

AWSreInvent #AWSreInvent2025 #AWS