10 articles aggregated from machinelearning.apple.com — part of DeepTrendLab's coverage of 50 top AI sources.
Apple ML Research is one of the top AI publishers tracked by DeepTrendLab. We aggregate every article from Apple ML Research alongside 49 other leading AI sources — including OpenAI, Anthropic, Google DeepMind, MIT Technology Review, and more — into a single, real-time feed updated every 2 hours.
Below are the most recent Apple ML Research articles in our index. Each is enriched with editorial analysis from DeepTrendLab's team. Browse all sources →
One of the major differentiators unlocked by learned codecs relative to their hard-coded traditional counterparts is their ability to be optimized directly to appeal to…
Image-based Joint-Embedding Predictive Architecture (I-JEPA) offers a promising approach to visual self-supervised learning through masked feature prediction. However with the inherent visual uncertainty at masked…
Mixture-of-Experts (MoE) models enable sparse expert activation, meaning that only a subset of the model’s parameters is used during each inference. However, to translate this…
Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are…
True spatial intelligence for multimodal agents transcends low-level geometric perception, evolving from knowing where things are to understanding what they are for. While existing benchmarks,…
Serving transformer language models with high throughput requires caching Key-Values (KVs) to avoid redundant computation during autoregressive generation. The memory footprint of KV caching is…
Multi-tool-integrated reasoning enables LLM-empowered tool-use agents to solve complex tasks by interleaving natural-language reasoning with calls to external tools. However, training such agents using outcome-only…
This paper was accepted at the Fifth Workshop on Natural Language Generation, Evaluation, and Metrics at ACL 2026. Tool-calling agents are evaluated on tool selection,…
Apple is presenting new research at the annual International Conference on Acoustics, Speech and Signal Processing (ICASSP) , which takes place in person in Barcelona,…
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the…