AP
Apple Research Blog
0 stories this week · 10 topics · machinelearning.apple.com
Apple's machine learning research blog: papers and on-device AI work.
Latest from Apple Research Blog
- Machine LearningPlan or Retrieve First? A Scale Study of Tool Discovery Architectures
- Machine LearningSelection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
- Machine LearningLocal and Distributed Large LLM Inference with MLX and RDMA on Mac Studio
- Machine LearningThe Design Space of Tri-Modal Masked Diffusion Models
- Machine LearningCode-Switching Detection via Language-Selective Dimensions in Speech Foundation Models
- Machine LearningMix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings
- Machine LearningMinions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
- LLM & Text GenerationSelf-Compacting Language Model Agents
- Machine LearningLarge Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged
- Image GenerationNormalizing Trajectory Models
- Machine LearningRISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
- AI ResearchNegotiating Ontological Boundaries in User-Authored Personal Sensing Systems
- AI ResearchLimits of Confidence in Diffusion
- Machine LearningLanguage Discrimination Improves Linguistic Learning in Multilingual Speech Models
- Machine LearningRLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback
- Machine LearningHow Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?
- Machine LearningSCLATE: A Substrate for Continual-Learning Agent Training and Evaluation
- LLM & Text GenerationOn the Effectiveness-Fluency Trade-Off in LLM Conditioning: A Systematic Study
- LLM & Text GenerationThe Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
- Machine LearningFaster Rates for Federated Variational Inequalities
- Machine LearningA Practical Recipe for Semi-Supervised Federated ASR: Online Pseudo-Labels with Server Update Stabilization
- Machine LearningCompressing Streaming Neural Audio Encoders via Latent-Space Distillation
- LLM & Text GenerationHow to Guide Your Language Flow
- Machine LearningDynamically Scaled Activation Steering
- Machine LearningREVERSAL-BENCH: A Reversibility Axis and Reset Oracle for Measuring the Reset-Free RL Cliff
- LLM & Text GenerationTrajectory as the Teacher: Few-Step Discrete Flow Matching via Energy-Navigated Distillation
- Business & EnterpriseGlyph: A Multi-Strategy Agentic System for Column Description and Sensitivity-Ontology Tagging of Enterprise Data Catalogs
- Machine LearningShared Selective Persistent Memory for Agentic LLM Systems
- LLM & Text GenerationHow Value Induction Reshapes LLM Behaviour
- Machine LearningDACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models