content type videopublished August 12, 2025

Apple Workshop on Privacy-Preserving Machine Learning 2025: Local Pan-Privacy for Federated Analytics

AuthorsGuy Rothblum (Apple)

Related readings and updates.

Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

September 24, 2026research area Methods and Algorithms, research area Speech and Natural Language Processing

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 time, so the always-on tokenizer competes for the same memory, and its…

Read more

A Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization

September 24, 2026research area Methods and Algorithms, research area Speech and Natural Language Processing

Semi-supervised federated learning (SSFL) trains models on clients’ unlabeled data using a teacher to generate pseudo-labels, with a small labeled seed dataset on the server. Automatic Speech Recognition (ASR) is particularly fragile here: pseudo-label errors compound across the output sequence and across training rounds into divergence, leaving a large gap to fully-supervised FL. We show that closing this gap turns on two coupled design axes—the…

Read more