https://machinelearning.apple.com Apple machine learning teams are engaged in state of the art research in machine learning and artificial intelligence. Learn about the latest advancements. en Thu, 09 Apr 2026 00:00:00 GMT neighbor https://machinelearning.apple.com/research/neighbor This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embedding space. A probabilistic interpretation of the distances between embeddings is proposed, based on a general quantitative definition of phonetic similarity between words. This provides us a framework for understanding and applying the embeddings in a principled manner. Theoretical and empirical evidence to support an approximation of uniform cluster-wise isotropy are shown, which allows us to… Thu, 09 Apr 2026 00:00:00 GMT lacy https://machinelearning.apple.com/research/lacy This paper was accepted at the Workshop on Memory for LLM-Based Agentic Systems at ICLR. Language models have consistently grown to compress more world knowledge into their parameters, but the knowledge that can be pretrained into them is upper-bounded by their parameter size. Especially the capacity of Small Language Models (SLMs) is limited, leading to factually incorrect generations. This problem is often mitigated by giving the SLM access to an outside source: the ability to query a larger model, documents, or a database. Under this setting, we study the fundamental question of which… Thu, 09 Apr 2026 00:00:00 GMT governance-aware-agent-telemetry https://machinelearning.apple.com/research/governance-aware-agent-telemetry Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Langfuse collect telemetry but treat governance as a downstream analytics concern, not a real-time enforcement target. The result is an “observe-but-do-not-act” gap where policy violations are detected only after damage is done. We present Governance-Aware Agent Telemetry (GAAT), a reference architecture that closes the loop between telemetry collection and automated policy enforcement for multi-agent… Wed, 08 Apr 2026 00:00:00 GMT squire https://machinelearning.apple.com/research/squire Frontend developers create UI prototypes to evaluate alternatives, which is a time-consuming process of repeated iteration and refinement. Generative AI code assistants enable rapid prototyping simply by prompting through a chat interface rather than writing code. However, while this interaction gives developers flexibility since they can write any prompt they wish, it makes it challenging to control what is generated. First, natural language on its own can be ambiguous, making it difficult for developers to precisely communicate their intentions. Second, the model may respond unpredictably… Mon, 06 Apr 2026 00:00:00 GMT personalized-group https://machinelearning.apple.com/research/personalized-group Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF), optimize for a single, global objective. While Group Relative Policy Optimization (GRPO) is a widely adopted on-policy reinforcement learning framework, its group-based normalization implicitly assumes that all samples are exchangeable, inheriting this limitation in personalized settings. This assumption conflates distinct user reward distributions and… Thu, 02 Apr 2026 00:00:00 GMT protext-gender-bias-benchmark https://machinelearning.apple.com/research/protext-gender-bias-benchmark We introduce ProText, a dataset for measuring gendering and misgendering in stylistically diverse long-form English texts. ProText spans three dimensions: Theme nouns (names, occupations, titles, kinship terms), Theme category (stereotypically male, stereotypically female, gender-neutral/non-gendered), and Pronoun category (masculine, feminine, gender-neutral, none). The dataset is designed to probe (mis)gendering in text transformations such as summarization and rewrites using state-of-the-art Large Language Models, extending beyond traditional pronoun resolution benchmarks and beyond the… Tue, 31 Mar 2026 00:00:00 GMT entropy-preserving-reinforcement-learning https://machinelearning.apple.com/research/entropy-preserving-reinforcement-learning Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative solutions. As we show in this paper, many policy gradient algorithms naturally reduce the entropy—and thus the diversity of explored trajectories—as part of training, yielding a policy increasingly limited in its ability to explore. In this paper, we argue that entropy should be actively monitored and controlled throughout training. We formally analyze the… Mon, 30 Mar 2026 00:00:00 GMT beyond-real-data https://machinelearning.apple.com/research/beyond-real-data Synthetic data can improve generalization when real data is scarce, but excessive reliance may introduce distributional mismatches that degrade performance. In this paper, we present a learning-theoretic framework to quantify the trade-off between synthetic and real data. Our approach leverages algorithmic stability to derive generalization error bounds, characterizing the optimal synthetic-to-real data ratio that minimizes expected test error as a function of the Wasserstein distance between the real and synthetic distributions. We motivate our framework in the setting of kernel ridge… Mon, 30 Mar 2026 00:00:00 GMT less-gaussians-texture-more https://machinelearning.apple.com/research/less-gaussians-texture-more Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM (Less Gaussians, Texture More), a feed-forward framework that overcomes this resolution scaling barrier. By predicting compact Gaussian primitives coupled with per-primitive textures, LGTM decouples geometric complexity from rendering resolution. This approach enables high-fidelity 4K novel view synthesis without… Sat, 28 Mar 2026 00:00:00 GMT athena https://machinelearning.apple.com/research/athena It is challenging to generate the code for a complete user interface using a Large Language Model (LLM). User interfaces are complex and their implementations often consist of multiple, inter-related files that together specify the contents of each screen, the navigation flows between the screens, and the data model used throughout the application. It is challenging to craft a single prompt for an LLM that contains enough detail to generate a complete user interface, and even then the result is frequently a single large and difficult to understand file that contains all of the generated… Fri, 27 Mar 2026 00:00:00 GMT