World Congress 2025 Aug 20, 2025 Session details

Mobile AI Just Got Faster: What’s Coming for Developers on Arm

Gian Marco Iodice

Run heavy generative AI entirely on-device without rewriting your code. Arm's KleidiAI integrates natively into standard frameworks, unlocking a 6x speedup for seamless, offline mobile execution.

Pause
Mute Enter Fullscreen
#1 about 3 min

Generative AI use cases on mobile devices

How on-device generative AI works without internet access for tasks like group chat summarization.

#2 about 2 min

Running audio generation locally on smartphones

Overcoming cloud latency by generating high-quality stereophonic audio directly on a mobile CPU using AudioGen.

#3 about 4 min

Scalability, security, and performance of Arm processors

The primary benefits of deploying AI workloads on mobile CPUs including optimization scaling and security.

#4 about 3 min

Open-source community and machine learning frameworks

Leveraging open-source frameworks like ExecuTorch and ONNX Runtime for diverse AI model deployments.

#5 about 3 min

Optimizing AI routines with the KleidiAI library

Integrating a lightweight C-based micro-kernel library into popular frameworks to accelerate neural networks.

#6 about 4 min

AudioGen pipelines and mixed memory data types

How on-device generative AI reduces cloud latency for iterative audio production using flexible floating-point operations.

#7 about 3 min

Building private smart assistants without cloud dependencies

Running speech-to-text, large language models, and text-to-speech stages securely on-device without internet connectivity.

#8 about 4 min

Matrix multiplication with SME2 architecture instructions

Using the Scalable Vector Extension 2 and Matrix Outer Product Accumulate to speed up heavy computations.

#9 about 3 min

Performance benchmarks and Android developer adoption

Unlocking significant performance speedups on key AI models and preparing Android applications for automatic hardware acceleration.

Matching moments

1:15 min

Debunking common biases about limited mobile AI capabilities

Sasha Denisov Sasha Denisov · WWC Europe 2026

3:42 min

Accelerating machine learning workloads using KleidiAI libraries

Andrew Wafaa Andrew Wafaa · WWC 2024

3:21 min

Reducing cloud dependency with on-device edge AI models

Precious Osaro Precious Osaro · WWC Europe 2026

48 sec

Shifting artificial intelligence models to local smartphone hardware

Chris Heilmann +1 · LIVE

1:41 min

Addressing mobile energy limits and AI processing tradeoffs

Precious Osaro Precious Osaro · WWC Europe 2026

3:38 min

The convergence of mobile engineering and machine learning

Sasha Denisov Sasha Denisov · WWC Europe 2026

Upcoming sessions on this topic

Open session

World Congress 2026 North America

Building Stuff with GenAI - The Open Minded Workshop beyond OpenAI

Andreas Erben

CTO for Applied AI and Metaverse at daenet

Andreas Erben
Open session

World Congress 2026 North America

From Software Agents to Physical Devices: Inside the Agentic Hardware Stack

Michael Yuan, Vivian Hu

Michael Yuan
Vivian Hu
Open session

World Congress 2026 North America

Compute for your AI model: GPUs, LPUs, TPUs and beyond..

Kushaagra Goyal

Tech Lead at Rubrik, ex-CTO at Gan.AI, ex-Databricks

Kushaagra Goyal
Open session

World Congress 2026 North America

The Things Your AI Isn't Telling You

Desmond Lamptey

Lead Software Engineer @ Capital One

Desmond Lamptey
Open session

World Congress 2026 North America

No Single Model to Rule Them All: Building Resilient AI Agents Across Open & Closed LLMs

Emmanuel Acheampong

Senior Manager Developer Relations at Crusoe AI

Emmanuel Acheampong
Open session

World Congress 2026 North America

You Can’t Re-Run Sunlight: Designing ML Data Architectures for Physical AI

An Phan

Senior Data Infrastructure Engineer @ Hippo Harvest

An Phan