FeedSources
⌘K
AM

Apple Machine Learning Research Publications

75 articles total

Go to source

Explore advancements in state of the art machine learning research in speech and natural language, privacy, computer vision, health, and more.

Go to source
  •  REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
  •  Agent Seer: Synthesizing Scenarios from Specification Understanding
  •  LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic Beliefs
  •  From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
  •  IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining
  •  Luce: Relightable Gaussians for 3D Asset Generation
  •  PROOF-Gen: From Optimized Data to Better Distillation
  •  STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
  •  Beyond Visual CoT: Internalized Visual Thinking for Proactive Video Reasoning
  •  Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
  •  Progressive Refinement: An Iterative Pseudo-Labeling Approach for Mandarin-English Code-Switching ASR
  •  Scaling Laws for Mixture Pretraining Under Data Constraints
  •  Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts
  •  The P-Completeness of Inverted Index Traversal: On the Complexity of Evaluating Boolean Query DAGs
  •  A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport
  •  GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
  •  MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations
  •  When Unlearning Is Free: Leveraging Low Influence Points to Reduce Computational Costs
  •  Arbitrage: Efficient Reasoning via Advantage-Aware Speculation
  •  Beyond Next-Token Prediction: A Performance Characterization of Diffusion versus Autoregressive Language Models