cd/sources/apple-ml-research· home› sources› Apple ML Research
cat /sources/apple-ml-research.feed | wc -l → 81

Apple ML Research

articles 81 domain machinelearning.apple.com → page 1/5 feed RSS
00:00
2026-11-16
machinelearning.apple.com
computer-vision

Split-and-Scale Latent 3D Representations

Researchers Dorian Chan, Muhammed Kocabas, Xiaoming Zhao, Oncel Tuzel and Jen-Hao Rick Chang published a paper on split-and-scale, an inference-time method that expands the latent capacity of 3D repre…

00:00
2026-11-12
machinelearning.apple.com
ai-research

Theoretical Limits of Language Model Alignment

A November 2026 paper by Lucas Monteiro Paes, Natalie Mackraz, Barry-John Theobald and Federico Danieli derives a closed-form expression for the maximum achievable expected reward gain under a fixed K…

00:00
2026-11-10
machinelearning.apple.com
machine-learning

Weighted State Souping for Efficient Long-Context Retrieval

Researchers William L. Tong, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Cengiz Pehlevan and Eran Malach proposed weighted state souping, a method that learns query-dependent weights for composing cache…

00:00
2026-11-10
machinelearning.apple.com
artificial-intelligence

Understanding Private Evolution as Learning-Augmented Clustering

Apple researchers Audra McMillan, Kunal Talwar and Felix Zhou published a paper in November 2026 recasting Private Evolution (PE), a differentially private synthetic data generation algorithm, as gene…

00:00
2026-11-10
machinelearning.apple.com
machine-learning

Toward a Theory of Evaluability

A new research paper, "Toward a Theory of Evaluability," formalizes how black-box machine learning models can be evaluated when test samples may have been used during training, dropping the classical …

00:00
2026-11-05
machinelearning.apple.com
artificial-intelligence

Faster Retrieval for Better, More Efficient RAG

Researchers from Apple presented a paper at ICML 2026, "Amortizing Maximum Inner Product Search with Learned Support Functions," that trains small neural networks offline for a fixed database of keys …

00:00
2026-10-14
machinelearning.apple.com
artificial-intelligence

The Design Space of Tri-Modal Masked Diffusion Models

Researchers from the University of Cambridge, MIT, Google DeepMind and Apple introduced the first tri-modal Masked Diffusion Models pretrained from scratch on text, image-text and audio-text data, pre…

00:00
2026-10-12
machinelearning.apple.com
ai-agents

Self-Compacting Language Model Agents

Johns Hopkins University researchers Tianjian Li, Jingyu Zhang, William Jurayj, Xi Wang, Chuanyang Jin, Mehrdad Farajtabar, Eric Nalisnick and Daniel Khashabi published SELFCOMPACT in October 2026, a …

00:00
2026-10-08
machinelearning.apple.com
artificial-intelligence

Normalizing Trajectory Models

Apple researchers Jiatao Gu, Tianrong Chen, Ying Shen, David Berthelot, Shuangfei Zhai and Josh Susskind published Normalizing Trajectory Models (NTM) in October 2026, a generative modeling method tha…

00:00
2026-10-02
machinelearning.apple.com
artificial-intelligence

Limits of Confidence in Diffusion

Apple researchers Russ Webb, Amitis Shidani, Alice Bizeul and Dan Busbridge published an October 2026 paper showing that discrete diffusion samplers — including remasking and uniform-state samplers — …

00:00
2026-10-01
machinelearning.apple.com
machine-learning

RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback

A new method called RLTL;DR lets a Qwen 3.5 9B Thinking policy break through a learning barrier on tool-calling and coding datasets filtered to Pass@128 = 0, reaching a Pass@1 of 14–31% with insights …

page 1 / 5 next →