Reactive Machines
How Cohere Health digitizes clinical policies using Amazon Bedrock AgentCore
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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
3 weeks ago
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…