News

Google News
machinelearning.apple.com > research > personalized-group

Google News

1+ day, 17+ hour ago  (12+ words) Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment'Apple Machine Learning Research...

machinelearning.apple.com
machinelearning.apple.com > research > athena

Athena: Intermediate Representations for Iterative Scaffolded App Generation with an LLM

1+ week, 17+ hour ago  (92+ words) AuthorsJazbo Beason, Ruijia Cheng, Eldon Schoop, Jeffrey Nichols This paper was accepted at IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) 2024. Programmers frequently engage with machine learning tutorials in computational notebooks and have been adopting code generation technologies…...

machinelearning.apple.com
machinelearning.apple.com > research > scaling-synthetic-task

Scaling Synthetic Task Generation for Agents via Exploration

1+ week, 3+ day ago  (128+ words) Scaling Synthetic Task Generation for Agents via Exploration'Apple Machine Learning Research Scaling Synthetic Task Generation for Agents via Exploration Related readings and updates. AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding February 24, 2026research area Computer Vision, research area Methods…...

machinelearning.apple.com
machinelearning.apple.com > research > depyf-open

depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers

1+ mon, 1+ week ago  (59+ words) View source code (GitHub) UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback Deploying Transformers on the Apple Neural Engine June 6, 2022research area Computer Vision, research area Speech and Natural Language Processing Our research in machine learning…...

machinelearning.apple.com
machinelearning.apple.com > research > amuse

AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding

1+ mon, 1+ week ago  (348+ words) AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding'Apple Machine Learning Research AMUSE: Audio-Visual Benchmark and Alignment Framework for Agentic Multi-Speaker Understanding Recent multimodal large language models (MLLMs) such as GPT-4o and Qwen3-Omni show strong perception but struggle in…...

machinelearning.apple.com
machinelearning.apple.com > updates > reasoning-workshop-2025

Apple Workshop on Reasoning and Planning 2025

1+ mon, 1+ week ago  (914+ words) Apple ML researcher Iman Mirzadeh presenting at the workshop. Last year, Apple hosted the Workshop on Reasoning and Planning, bringing together Apple researchers and members of the broader research community for a two-day event focused on advancing the state of…...

machinelearning.apple.com
machinelearning.apple.com > research > ferret-ui

Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents

1+ mon, 2+ week ago  (319+ words) Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents'Apple Machine Learning Research Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents AuthorsZhen Yang, Zi-Yi Dou, Di Feng, Forrest Huang, Anh Nguyen, Keen You, Omar Attia, Yuhao Yang, Michael Feng, Haotian…...

machinelearning.apple.com
machinelearning.apple.com > research > semantic-caching

Asynchronous Verified Semantic Caching for Tiered LLM Architectures

1+ mon, 2+ week ago  (354+ words) Asynchronous Verified Semantic Caching for Tiered LLM Architectures'Apple Machine Learning Research Asynchronous Verified Semantic Caching for Tiered LLM Architectures AuthorsAsmit Kumar Singh, Haozhe Wang, Laxmi Naga Santosh Attaluri, Tak Chiam, Weihua Zhu Large language models (LLMs) now sit in the…...

machinelearning.apple.com
machinelearning.apple.com > research > mapping

Mapping the Design Space of User Experience for Computer Use Agents

1+ mon, 2+ week ago  (337+ words) Mapping the Design Space of User Experience for Computer Use Agents'Apple Machine Learning Research Mapping the Design Space of User Experience for Computer Use Agents AuthorsRuijia Cheng, Jenny T. Liang, Eldon Schoop, Jeffrey Nichols Large language model (LLM)-based computer use agents…...