Posts in category: Apple

Scaling the capacity of language models has consistently proven to be a reliable approach for
improving performance and unlocking new capabilities. Capacity can be primarily defined by
two dimensions: the number of model parameters and the compute per example. While scaling
typically involves increasing both, the precise interplay between these factors and their combined contribution to overall capacity remains not fully understood. We explore this relationship
in the context of sparse Mixture-of-Experts (MoEs) , which allow scaling the number of parameters without proportionally increasing…Apple Machine Learning Research

We give a principled method for decomposing the predictive uncertainty of a model into aleatoric and epistemic components with explicit semantics relating them to the real-world data distribution. While many works in the literature have proposed such decompositions, they lack the type of formal guarantees we provide. Our method is based on the new notion of higher-order calibration, which generalizes ordinary calibration to the setting of higher-order predictors that predict mixtures over label distributions at every point. We show how to measure as well as achieve higher-order calibration…Apple Machine Learning Research

Nonverbal behaviors such as posture, gestures, and gaze are essential for conveying internal states, both consciously and unconsciously, in human interaction. For robots to interact more naturally with humans, robot movement design should likewise integrate expressive qualities—such as intention, attention, and emotions—alongside traditional functional considerations like task fulfillment, spatial constraints, and time efficiency. In this paper, we present the design and prototyping of a lamp-like robot that explores the interplay between functional and expressive objectives in movement…Apple Machine Learning Research

This paper introduces a framework, called EMOTION, for generating expressive motion sequences in humanoid robots, enhancing their ability to engage in human-like non-verbal communication. Non-verbal cues such as facial expressions, gestures, and body movements play a crucial role in effective interpersonal interactions. Despite the advancements in robotic behaviors, existing methods often fall short in mimicking the diversity and subtlety of human non-verbal communication. To address this gap, our approach leverages the in-context learning capability of large language models (LLMs) to…Apple Machine Learning Research

Single-cell genomics technologies enable multimodal profiling of millions of cells across temporal and spatial dimensions. Experimental limitations prevent the measurement of all-encompassing cellular states in their native temporal dynamics or spatial tissue niche. Optimal transport theory has emerged as a powerful tool to overcome such constraints, enabling the recovery of the original cellular context. However, most algorithmic implementations currently available have not kept up the pace with increasing dataset complexity, so that current methods are unable to incorporate multimodal…Apple Machine Learning Research

This paper presents an efficient decoding approach for end-to-end automatic speech recognition (E2E-ASR) with large language models (LLMs). Although shallow fusion is the most common approach to incorporate language models into E2E-ASR decoding, we face two practical problems with LLMs. (1) LLM inference is computationally costly. (2) There may be a vocabulary mismatch between the ASR model and the LLM. To resolve this mismatch, we need to retrain the ASR model and/or the LLM, which is at best time-consuming and in many cases not feasible. We propose “delayed fusion,” which applies LLM scores…Apple Machine Learning Research

Generating high-quality 3D content requires models capable of learning robust distributions of complex scenes and the real-world objects within them. Recent Gaussian-based 3D reconstruction techniques have achieved impressive results in recovering high-fidelity 3D assets from sparse input images by predicting 3D Gaussians in a feed-forward manner. However, these techniques often lack the extensive priors and expressiveness offered by Diffusion Models. On the other hand, 2D Diffusion Models, which have been successfully applied to denoise multiview images, show potential for generating a wide…Apple Machine Learning Research

Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. In this paper, we investigate the capabilities of Large Language Models (LLMs) for reinforcement learning (RL) across a diversity of interactive domains. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly, by first generating reward models to train an agent with RL. Our results show that, even without…Apple Machine Learning Research

What distinguishes robust models from non-robust ones? While for ImageNet distribution shifts it has been shown that such differences in robustness can be traced back predominantly to differences in training data, so far it is not known what that translates to in terms of what the model has learned. In this work, we bridge this gap by probing the representation spaces of 16 robust zero-shot CLIP vision encoders with various backbones (ResNets and ViTs) and pretraining sets (OpenAI, LAION-400M, LAION-2B, YFCC15M, CC12M and DataComp), and comparing them to the representation spaces of less…Apple Machine Learning Research

The increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, recent works have proposed to control model generation by steering model activations in order to effectively induce or prevent the emergence of concepts or behaviours in the generated output. In this paper we introduce Activation Transport (AcT), a general framework to steer activations guided by optimal transport theory that generalizes many previous activation-steering works. AcT is…Apple Machine Learning Research