Reactive Machines

Advanced fine-tuning techniques for multi-agent orchestration: Patterns from Amazon at scale

Advanced fine-tuning techniques for multi-agent orchestration: Patterns from Amazon at scale

[ad_1] Our work with large enterprise customers and Amazon teams has revealed that high stakes use cases continue to benefit…
The Data-Quality Illusion: Rethinking Quality-Based Filtering for LLM Pretraining

The Data-Quality Illusion: Rethinking Quality-Based Filtering for LLM Pretraining

[ad_1] Large models are pre-trained on large datasets that appear on the web that contain documents of mixed quality, making…
How the Amazon AMET Payments team accelerates test case generation with Strands Agents

How the Amazon AMET Payments team accelerates test case generation with Strands Agents

[ad_1] At Amazon.ae, we serve approximately 10 million customers monthly across five countries in the Middle East and North Africa…
How AutoScout24 built a Bot Factory to standardize AI agent development with Amazon Bedrock

How AutoScout24 built a Bot Factory to standardize AI agent development with Amazon Bedrock

[ad_1] AutoScout24 is Europe’s leading automotive marketplace platform that connects buyers and sellers of new and used cars, motorcycles, and…
Securing Amazon Bedrock cross-Region inference: Geographic and global

Securing Amazon Bedrock cross-Region inference: Geographic and global

[ad_1] The adoption and implementation of generative AI inference has increased with organizations building more operational workloads that use AI…
Getting Started with XGBoost: A Beginner-Friendly Tutorial

Getting Started with XGBoost: A Beginner-Friendly Tutorial

[ad_1] Among all the tools that a data scientist has, it is difficult to find one that has received a…
How Omada Health scaled patient care by fine-tuning Llama models on Amazon SageMaker AI

How Omada Health scaled patient care by fine-tuning Llama models on Amazon SageMaker AI

[ad_1] This post is co-written with Sunaina Kavi, AI/ML Product Manager at Omada Health. Omada Health, a longtime innovator in…
DeepMMSearch-R1: Enabling Multimodal LLMs in Multimodal Web Search

DeepMMSearch-R1: Enabling Multimodal LLMs in Multimodal Web Search

[ad_1] Multimodal Large Language Models (MLLMs) in real-world applications need access to external information sources and must constantly respond to…
Multivariate Conformal Prediction using Optimal Transport

Multivariate Conformal Prediction using Optimal Transport

[ad_1] Conformal prediction (CP) quantifies the uncertainty of machine learning models by constructing sets of observable outputs. These sets are…
MANZANO: A Simple and Sharp Multimodal Integrated Model with Hybrid Vision Tokenizer

MANZANO: A Simple and Sharp Multimodal Integrated Model with Hybrid Vision Tokenizer

[ad_1] Large-scale Linguistic Models (LLMs) capable of understanding and generating visual content hold great potential. However, existing open source models…
Back to top button

Enjoy this blog? Please spread the word :)