Welcome to M5BMachine 5-Minute Briefing

Code-switching (CS), alternating languages within the same utterance, poses significant challenges for automatic speech recognition (ASR) due to limited CS training data. This paper applies an iterative pseudo-labeling training approach to CS-ASR for the first time, demonstrating its effectiveness i...

Kernel-based optimal transport (OT) estimators offer an alternative, functional estimation procedure to address OT problems from samples. Recent works suggest that these estimators are more statistically efficient than plug-in (linear programming-based) OT estimators when comparing probability measu...

Machine learning techniques in multi-view settings face significant challenges, particularly when integrating heterogeneous data, aligning feature spaces, and managing view-specific biases. These issues are prominent in neuroscience, where data from multiple subjects exposed to the same stimuli are ...

Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for improving the reasoning capabilities of pretrained language models but current studies remain heavily English-centric. We conduct a large-scale empir...

Preference alignment has become a crucial component in enhancing the performance of Large Language Models (LLMs), yet its impact in Multimodal Large Language Models (MLLMs) remains comparatively underexplored. Similar to language models, MLLMs for image understanding tasks encounter challenges like ...

While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally. This graph encodes the data manifold in its original high-dimensional space, before ...

Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded. We introduce LVSum, a human-annotated benchmark for...

We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can be adaptive to the geometry of the underlying scene. We find t...

Suppose Alice has collected a small number of samples from an unknown distribution, and would like to learn about the distribution. Bob, an untrusted data analyst, claims to have run a sophisticated data analysis on the distribution and makes assertions about its properties. When and how is it possi...

A property of functions is called location-invariant (or symmetric) if it can be characterized in terms of the frequencies in which each value occurs in the function, regardless of the locations in which each value occurs. It is known that the (query) complexity of testing location-invariant propert...

Apple Music serves listeners across 150+ storefronts in dozens of languages, with a catalog that grows by hundreds of thousands of new tracks daily. At this scale, search recall on misspelled, transliterated, and cross-lingual queries becomes a dominant driver of session quality, particularly for ta...

On-policy distillation offers dense, per-token supervision for training reasoning models; however, it remains unclear under which conditions this signal is beneficial and under which it is detrimental. Which teacher model should be used, and in the case of self-distillation, which specific context s...

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of expert paths—the sequence of expert selections a token makes across all layers. This perspective reveals that, despite N^L po...

Apple is presenting new research at the annual IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), which takes place in person in Denver at the Colorado Convention Center from June 3 to June 7. We are proud to sponsor the conference, which brings together the scientific and indust...

Streaming vision-language models (VLMs) continuously generate responses given an instruction prompt and an online stream of input frames. This is a core mechanism for real-time visual assistants. Existing VLM frameworks predominantly assess models in offline settings. In contrast, the performance of...

At Apple, we believe privacy is a fundamental human right. As AI capabilities increase and become more integrated into people’s daily lives, advancing research in privacy-preserving techniques is increasingly important to ensure privacy is protected while users enjoy innovative AI experiences. Appl...

We propose HeadsUp, a scalable feed-forward method for reconstructing high-quality 3D Gaussian heads from large-scale multi-camera setups. Our method employs an efficient encoder-decoder architecture that compresses input views into a compact latent representation. This latent representation is then...

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 the human visual system. Despite this potential, a perceptual yet practical image codec is yet to be proposed. In this work, we aim...

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 positions, feature prediction remains challenging and may fail to learn semantic repre...

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 ...

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 8. We are proud to again sponsor the conference, which brings together the scientific and industrial research co...

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 support the broader community. This week, the Fourteenth International Conference on Learning Representations...

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. We are proud to again sponsor the conference, which brings together the scientific and industrial research communiti...

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, from April 13 to 17. We are proud to again sponsor the conference, which brings together the scientific and i...