Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the representation the language model reads. Because that model is sparsely activated under Instruction-Following Pruning, only a small subset of its experts occupies DRAM at any …

ML 21846 1

Speaker-labeled transcription with WhisperX on SageMaker AI

Any team working with spoken audio hits the same wall with generic speech-to-text. Think contact-center calls, all-hands meetings, podcasts, depositions, and broadcast media. These workloads need two things that standard transcription gets wrong. First, timestamps land at the utterance level, off by several seconds. Second, there’s no reliable answer to “who said what.” Those gaps …

4 autotradermax 1000x1000 1

Power your agents: Gemini 3.8 Live with Live Avatar is now generally available

Following our announcement of Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking last week, we are thrilled to share that Gemini 3.8 Live with Live Avatar is now generally available in Gemini Enterprise. First previewed at Google Cloud Next 2026, the technology is now officially ready for enterprise production. As enterprise voice AI evolves …

How to Guide Your Language Flow

We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to construct a guidance signal. This works using a similar principle as autoguidance, but eliminates the need for an additional forward pass at inference time and provides a …

ML 21352 1

From portal-hopping to instant answers: HEMA’s journey with MCP and Amazon Bedrock

This post is co-written with Mauro Rallo and Patrick van der Plas from HEMA. When engineers at HEMA needed an answer, they went portal-hopping, navigating disconnected wikis, service catalogs, and IT portals to find it. To turn that friction into instant answers, the 100-year-old Dutch retailer built a knowledge layer on Amazon Bedrock AgentCore. HEMA …

ML 21636 6

Bring more intelligence to everyday work with GPT-6 Sol and GPT-6 Luna on Amazon Bedrock

GPT-6 Sol and GPT-6 Luna are now generally available on Amazon Bedrock, giving you more options to match intelligence and efficiency to each workload. The value of AI at scale depends on two dimensions: what a model can do and how often you can put it to use. Greater intelligence expands the complexity a model …

ML 21784 1

xAI’s Grok 4.6 is now available in Amazon Bedrock

Today, we are announcing that xAI’s Grok 4.6 is available in Amazon Bedrock, adding a frontier model built for long-running agents, coding, and knowledge work to the Bedrock model catalog. Grok 4.6 launched on Bedrock on August 18, 2026. It offers a 500K token context window and supports configurable reasoning effort at four levels: low, …

Dynamically Scaled Activation Steering

Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interventions uniformly across all inputs, degrading model performance when steering is unnecessary. We introduce Dynamically Scaled Activation Steering (DSAS), a method-agnostic steering framework that decouples when to steer …

1AkQlaHO9bwLf dNp Z2HZQ

Leave the Class Path in the Rearview Mirror

Introducing composable, module system native and agent friendly command line tools for modern Java development By Danny Thomas, JVM Ecosystem Team Recent work on the Java language to pave the on-ramp has made it easier than ever to start a Java program and evolve it using the full language and platform. At the end of …

ML 21809 1 1

Amazon SageMaker Inference: 2026 year-to-date launches in review

Generative AI inference is uniquely hard: models are tens to hundreds of gigabytes, latency requirements are measured in tokens per second, cold starts can span multiple minutes as containers and weights transfer, GPU capacity is constrained, and traditional monitoring tools expose none of the token-level signals that matter in production. Amazon SageMaker AI offers customers …