Generating user intent from a sequence of user interface (UI) actions is a core challenge in comprehensive UI understanding. Recent advancements in multimodal large language models (MLLMs) have led to substantial progress in this area, but their demands for extensive model parameters, computing power, and high latency makes them impractical for scenarios requiring lightweight, on-device solutions with low latency or heightened privacy. Additionally, the lack of high-quality datasets has hindered the development of such lightweight models. To address these challenges, we propose UI-JEPA, a…Apple Machine Learning Research
Optimizing Byte-level Representation for End-to-End ASR
This paper was accepted at the IEEE Spoken Language Technology Workshop (SLT) 2024.
In this paper, we propose an algorithm to optimize a byte-level representation for end-to-end (E2E) automatic speech recognition (ASR). Byte-level representation is often used by large scale multilingual ASR systems when the character set of the supported languages is large. The compactness and universality of byte-level representation allow the ASR models to use smaller output and therefore, provides more flexibility. UTF-8 is the most commonly used byte-level representation and has been successfully applied…Apple Machine Learning Research
Apple Workshop on Privacy-Preserving Machine Learning 2024
At Apple, we believe privacy is a fundamental human right. It’s also one of our core values, influencing both our research and the design of Apple’s products and services.
Understanding how people use their devices often helps in improving the user experience. However, accessing the data that provides such insights — for example, what users type on their keyboards and the websites they visit — can compromise user privacy. We develop system architectures that enable learning at scale by leveraging advances in machine learning (ML), such as private federated learning (PFL), combined with…Apple Machine Learning Research
Positional Description for Numerical Normalization
We present a Positional Description Scheme (PDS) tailored for digit sequences, integrating placeholder value information for each digit. Given the structural limitations of subword tokenization algorithms, language models encounter critical Text Normalization (TN) challenges when handling numerical tasks. Our schema addresses this challenge through straightforward pre-processing, preserving the model architecture while significantly simplifying number normalization, rendering the problem tractable. This simplifies the task and facilitates more compact production-ready models capable of…Apple Machine Learning Research
Classifier-Free Guidance Is a Predictor-Corrector
We investigate the unreasonable effectiveness of classifier-free guidance (CFG).
CFG is the dominant method of conditional sampling for text-to-image diffusion models, yet
unlike other aspects of diffusion, it remains on shaky theoretical footing. In this paper, we disprove common misconceptions, by showing that CFG interacts differently with DDPM and DDIM, and neither sampler with CFG generates the gamma-powered distribution.
Then, we clarify the behavior of CFG by showing that it is a kind of Predictor-Corrector (PC) method that alternates between denoising and sharpening, which we call…Apple Machine Learning Research
On the Benefits of Pixel-Based Hierarchical Policies for Task Generalization
Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional complexity associated with implementing a hierarchy. However, by introducing multiple decision-making levels, hierarchical policies can compose lower-level policies to more effectively generalize between tasks, highlighting the need for multi-task evaluations. We analyze the benefits of hierarchy through simulated multi-task robotic control experiments from pixels…Apple Machine Learning Research
Can You Remove the Downstream Model for Speaker Recognition with Self-Supervised Speech Features?
Self-supervised features are typically used in place of filter-bank features in speaker verification models. However, these models were originally designed to ingest filter-banks as inputs, and thus, training them on self-supervised features assumes that both feature types require the same amount of learning for the task. In this work, we observe that pre-trained self-supervised speech features inherently include information required for a downstream speaker verification task, and therefore, we can simplify the downstream model without sacrificing performance. To this end, we revisit the…Apple Machine Learning Research
RepCNN: Micro-Sized, Mighty Models for Wakeword Detection
Always-on machine learning models require a very low memory and compute footprint. Their restricted parameter count limits the model’s capacity to learn, and the effectiveness of the usual training algorithms to find the best parameters. Here we show that a small convolutional model can be better trained by first refactoring its computation into a larger redundant multi-branched architecture. Then, for inference, we algebraically re-parameterize the trained model into the single-branched form with fewer parameters for a lower memory footprint and compute cost. Using this technique, we show…Apple Machine Learning Research
Novel-View Acoustic Synthesis From 3D Reconstructed Rooms
We investigate the benefit of combining blind audio recordings with 3D scene information for novel-view acoustic synthesis. Given audio recordings from 2-4 microphones and the 3D geometry and material of a scene containing multiple unknown sound sources, we estimate the sound anywhere in the scene. We identify the main challenges of novel-view acoustic synthesis as sound source localization, separation, and dereverberation. While naively training an end-to-end network fails to produce high-quality results, we show that incorporating room impulse responses (RIRs) derived from 3D reconstructed…Apple Machine Learning Research
ReALM: Reference Resolution as Language Modeling
Reference resolution is an important problem, one that is essential to understand and successfully handle contexts of different kinds. This context includes both previous turns and context that pertains to non-conversational entities, such as entities on the user’s screen or those running in the background. While LLMs have been shown to be extremely powerful for a variety of tasks, their use in reference resolution, particularly for non-conversational entities, remains underutilized. This paper demonstrates how LLMs can be used to create an effective system to resolve references of various…Apple Machine Learning Research