Apple Machine Learning Research

apple.com Imported from official source

Apple Machine Learning Research — publications from its own official source.

Publications 45

  1. Split-and-Scale Latent 3D Representations

    Latent 3D representations have significantly expanded the capabilities of modern shape modeling, enabling compact encoding of 3D scenes and supporting powerful 3D generative models. Despite this pr...

    AI
  2. Theoretical Limits of Language Model Alignment

    Language model (LM) alignment improves model outputs to reflect human preferences while preserving the capabilities of the base model. The most common alignment approaches are (i) reinforcement lea...

    AI
  3. Toward a Theory of Evaluability

    Machine learning models, particularly large foundation models, are increasingly evaluated along multiple axes that are relevant for their usage. In addition to accuracy measures appropriate for the...

    AI
  4. Understanding Private Evolution as Learning-Augmented Clustering

    Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm, it performs much better in practice than wors...

    AI
  5. Weighted State Souping for Efficient Long-Context Retrieval

    This paper was accepted at the Workshop on Personalized, Aligned, Long-term Memory for AI Systems (PALM) at NeurIPS 2026. State space models (SSMs) combine fast inference and fixed state size with ...

    AI
  6. On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models

    State Space Models (SSMs) have emerged as a compelling alternative to Transformers, enabling sequence modeling with constant memory and linear compute. …

    AI
  7. Evaluating the Evaluators: Investigating LLM Judges for Personalized Writing Style Assessment

    This paper was accepted at the Can We Trust AI Evaluation? Workshop at NeurIPS 2026. We evaluate how good large language model (LLM) judges are for personalized writing tasks. This is important whe...

    AI
  8. Faster Retrieval for Better, More Efficient RAG

    Maximum inner product search (MIPS) sits at the core of recommendation systems, search, and retrieval-augmented generation (RAG). Given a query vector, MIPS systems search within a database of mill...

    AI
  9. Attention to Mamba: A Recipe for Cross-Architecture Distillation

    State Space Models (SSMs) such as Mamba have become a popular alternative to Transformer models, due to their reduced memory consumption and higher throughput at generation compared to their Attent...

    AI
  10. Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live iOS Apps

    While frontier vision-language models demonstrate strong capabilities in user interface (UI) navigation, their high inference costs prohibit everyday use. Conversely, smaller models trained via sup...

    AI
  11. GHARP: Real-Time Gaussian Head Animation from Large-Scale Reconstruction Prior

    We present GHARP (Real-time Gaussian Head Animation from Large-scale Reconstruction Prior), a method that animates 3D human heads in real time from a few input images of a subject and a driving exp...

    AI
  12. Pixels to Tokens: Token Space Efficient Active Learning for Low-Budget Semantic Segmentation

    While foundation models and vision transformers (ViTs) have redefined visual representations, current active learning (AL) strategies for these backbones largely operate at the patch or region leve...

    AI
  13. Plan or Retrieve First? A Scale Study of Tool Discovery Architectures

    Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The domina...

    AI
  14. Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents

    Multimodal agents commonly generate freeform reasoning before each action. For small models, limited model capacity can result in lengthy reasoning that provides little useful guidance for action g...

    AI
  15. Local and Distributed Large LLM Inference with MLX and RDMA on Mac Studio

    MLX on Mac with Apple silicon lets AI researchers and developers experiment locally with the latest models and methods in a private environment. The open-source array framework leverages the unifie...

    AI 2 versions
  16. Code-Switching Detection via Language-Selective Dimensions in Speech Foundation Models

    Code-switching (CS), the alternation between languages within an utterance, is common in multilingual speech but underrepresented in pretraining corpora. Increasing CS coverage requires finding rel...

    AI
  17. The Design Space of Tri-Modal Masked Diffusion Models

    Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and finetuning a base unimodal model for bi-modal generation. Divergin...

    AI
  18. Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings

    For most languages of the world, language model pre-training operates in a data-constrained regime where models must repeat their training data many times, degrading generalization. Two remedies ex...

    AI
  19. Self-Compacting Language Model Agents

    Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it...

    AI
  20. Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices

    The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost, limited elasticity, and long wait times under r...

    AI
  21. Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged

    Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation. With MT evaluation spanning a large numb...

    AI
  22. Normalizing Trajectory Models

    Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step metho...

    AI
  23. RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation

    Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. …

    AI
  24. Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems

    Designed artifacts are ontological, shaping, and at times limiting, what becomes possible or imaginable. One path toward mitigating such foreclosures is giving people power over how systems are des...

    AI
  25. Limits of Confidence in Diffusion

    Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing whic...

    AI
  26. Language Discrimination Improves Linguistic Learning in Multilingual Speech Models

    Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. …

    AI
  27. RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback

    The common paradigm of reinforcement learning with verifiable rewards (RLVR) is to let agents make multiple attempts at a task, and optimize towards the successful ones. This becomes problematic in...

    AI
  28. How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?

    Recent autonomous machine learning engineering (MLE) agents have made significant progress on public leaderboards. Often motivated by progress stagnation over long-horizon cycles and limited Large ...

    AI
  29. SCLATE: A Substrate for Continual-Learning Agent Training and Evaluation

    Continual-learning agents are systems of models, harnesses, and memory operating over long multi-session horizons. Evaluating and training them requires interleaving tasks with agent-side events su...

    AI
  30. On the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study

    Controlling the output of Large Language Models (LLMs) is a central challenge for their reliable deployment, yet a clear understanding of the involved trade-offs remains elusive. Current approaches...

    AI
  31. The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models

    When language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural language. How much tree-structured compositional content surv...

    AI
  32. Faster Rates for Federated Variational Inequalities

    In this paper, we study federated optimization for solving stochastic variational inequalities (VIs), a problem that has attracted growing attention in recent years. Despite substantial progress, a...

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

    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 Recog...

    AI
  34. Compressing Streaming Neural Audio Encoders via Latent-Space Distillation

    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 t...

    AI
  35. How to Guide Your Language Flow

    We introduce a new method to guide flow matching models. Our approach, which we call probe guidance, uses the frozen internal states of an existing diffusion model to construct a guidance signal. …

    AI
  36. Dynamically Scaled Activation Steering

    Activation steering has emerged as a powerful method for guiding the behavior of generative models towards desired outcomes such as toxicity mitigation. However, most existing methods apply interve...

    AI
  37. REVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff

    A central goal of autonomous reinforcement learning is continuous policy training without external resets. However, existing paradigms largely depend on underlying environmental reversibility, a pr...

    AI
  38. How Value Induction Reshapes LLM Behaviour

    Conversational Large Language Models are post-trained on language that expresses specific behavioural traits, such as curiosity, open-mindedness, and empathy, and values, such as helpfulness, harml...

    AI
  39. Trajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation

    Discrete flow matching generates text by iteratively transforming noise tokens into coherent language, but may require hundreds of forward passes. Distillation uses the multi-step trajectory to tra...

    AI
  40. DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models

    Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely on biased, high-...

    AI
  41. Glyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs

    Enterprise data lakes accumulate tables faster than human stewards can document or classify them, leaving columns with missing descriptions and unassigned governance labels. This documentation debt...

    AI
  42. Shared Selective Persistent Memory for Agentic LLM Systems

    Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data ...

    AI
  43. SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign

    Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative ...

    AI
  44. Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering

    Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This p...

    AI
  45. DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation

    Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a compu...

    AI

Officially records where a publication came from, not whether it is true. Imported records are reproduced from an organization's own official source.