All articles from Apple ML Research aggregated on DeepTrendLab — AI news, research, and announcements in one place.
Apple ML Research
24 articles
🍎 AI Labs
Apple ML Research
2 min read
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 sparsity into practical performance, an expert caching mechanism is required. Previous works have proposed hardware-centric caching policies, but how these various caching policies interact with each other and different hardware specification remains poorly understood. To…
🍎 AI Labs
Apple ML Research
1 min read
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 capable of achieving promising performance…
🍎 AI Labs
Apple ML Research
2 min read
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, such as VSI-Bench, effectively evaluate…
🍎 AI Labs
Apple ML Research
2 min read
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 significant and heavily impacts serving…
🍎 AI Labs
Apple ML Research
2 min read
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 rewards suffers from credit-assignment ambiguity,…
🍎 AI Labs
Apple ML Research
2 min read
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, parameter accuracy, and scope recognition,…
🍎 AI Labs
Apple ML Research
2 min read
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 video generation domain, where spatiotemporal…
🍎 AI Labs
Apple ML Research
2 min read
AI-driven sign language interpretation is limited by a lack of high-quality annotated data. New datasets including ASL STEM Wiki and FLEURS-ASL contain professional interpreters and 100s of hours of data…
🍎 AI Labs
Apple ML Research
1 min read
Apple is presenting new research at the annual International Conference on Acoustics, Speech and Signal Processing (ICASSP) , which takes place in person in Barcelona, Spain, from May 4 to…
🍎 AI Labs
Apple ML Research
2 min read
Recent advances in large language models (LLMs) test-time computing have introduced the capability to perform intermediate chain-of-thought (CoT) reasoning (thinking) before generating answers. While increasing the thinking budget yields smooth…
🍎 AI Labs
Apple ML Research
2 min read
Generative models are often deployed to make decisions on behalf of users, such as vision-language models (VLMs) identifying which person in a room is a doctor to help visually impaired…
🍎 AI Labs
Apple ML Research
2 min read
Conditional diffusion models appear capable of compositional generalization, i.e., generating convincing samples for out-of-distribution combinations of conditioners, but the mechanisms underlying this ability remain unclear. To make this concrete, we…
🍎 AI Labs
Apple ML Research
2 min read
We present StereoFoley, a video-to-audio generation framework that produces semantically aligned, temporally synchronized, and spatially accurate stereo sound at 48 kHz. While recent generative video-to-audio models achieve strong semantic and…
🍎 AI Labs
Apple ML Research
1 min read
Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM’s autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner,…
🍎 AI Labs
Apple ML Research
1 min read
Understanding and predicting motion is a fundamental component of visual intelligence. Although modern video models exhibit strong comprehension of scene dynamics, exploring multiple possible futures through full video synthesis remains…
🍎 AI Labs
Apple ML Research
10 min read
Recurrent Neural Networks (RNNs) are naturally suited to efficient inference, requiring far less memory and compute than attention-based architectures, but the sequential nature of their computation has historically made it…
🍎 AI Labs
Apple ML Research
7 min read
Apple is advancing AI and ML with fundamental research, much of which is shared through publications and engagement at conferences in order to accelerate progress in this important field and…
🍎 AI Labs
Apple ML Research
2 min read
Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of…
🍎 AI Labs
Apple ML Research
1 min read
Recent work has shown that probing model internals can reveal a wealth of information not apparent from the model generations. This poses the risk of unintentional or malicious information leakage,…
🍎 AI Labs
Apple ML Research
12 min read
Apple is presenting new research at the annual International Conference on Learning Representations (ICLR) , which takes place in person in Rio de Janeiro, Brazil, from April 23 to 27.…
🍎 AI Labs
Apple ML Research
2 min read
This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models (NADPFM) at ICLR 2026. Principled domain reweighting can substantially improve sample efficiency and downstream…
🍎 AI Labs
Apple ML Research
2 min read
This paper was accepted at the Workshop on Navigating and Addressing Data Problems for Foundation Models at ICLR 2026. Large language models (LLMs) can struggle to memorize factual knowledge in…
🍎 AI Labs
Apple ML Research
2 min read
We consider the privacy amplification properties of a sampling scheme in which a user’s data is used in k steps chosen randomly and uniformly from a sequence (or set) of…
🍎 AI Labs
Apple ML Research
2 min read
Apple is presenting new research at the annual ACM (Association of Computing Machinery) CHI Conference on Human Factors in Computing Systems , which takes place in person in Barcelona, Spain,…