Reactive Machines

How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore

How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore

Prior authorization is the approval process health plans require before covering certain medical services or medications. It remains one of…
Scaling Categorical Flow Maps – Apple Machine Learning Research

Scaling Categorical Flow Maps – Apple Machine Learning Research

Continuous diffusion and flow matching models could represent a powerful alternative to autoregressive approaches for language modelling (LM), as they…
Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

Arbitrage: Efficient Reasoning via Advantage-Aware Speculation

Modern Large Language Models achieve impressive reasoning capabilities with long Chain of Thoughts, but they incur substantial computational cost during…
Securing AI agents with temporal policies in Amazon Bedrock AgentCore

Securing AI agents with temporal policies in Amazon Bedrock AgentCore

Before AI agents, it was generally sufficient for access controls to treat each action as an independent event. Applications relied…
Configure rate limits for AI traffic on AgentCore gateway

Configure rate limits for AI traffic on AgentCore gateway

Amazon Bedrock AgentCore gateway is a fully managed, serverless AI gateway that provides a single, secure entry point for AI…
Enforcing data residency with single-Region Claude Code on Amazon Bedrock

Enforcing data residency with single-Region Claude Code on Amazon Bedrock

A US-headquartered global organization recently came to us with a deceptively simple data-residency request: let their engineers use Claude Code.…
Locking Pretrained Weights via Deep Low-Rank Residual Distillation

Locking Pretrained Weights via Deep Low-Rank Residual Distillation

The quality of open-weight language models has dramatically improved in recent years. Sharing weights greatly facilitates model adoption by enabling…
DeepAmbigQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness

DeepAmbigQA: Ambiguous Multi-hop Questions for Benchmarking LLM Answer Completeness

Large language models (LLMs) with integrated search tools show strong promise in open-domain question answering (QA), yet they often struggle…
How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock

How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock

Buying a home is one of the biggest financial decisions most people face, and LendingTree built a multi-agent mortgage assistant…
Taming Outlier Tokens in Diffusion Transformers

Taming Outlier Tokens in Diffusion Transformers

We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can…
Back to top button