HeyJaredApple ML
- Indexed articles, last 90 days
- 17
- Latest publication
- Aug 3, 2026
- Outlet visibility, for Apple Machine Learning
- Top 5M sites
- Earliest in this view
- Jul 6, 2026
Latest articles
Understanding Alignment in Multimodal LLMs: A Comprehensive Study (opens the original)
Read excerpt
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 hallucination. In MLLMs, hallucination can occur not only by stating incorrect facts but also by producing responses that are inconsistent with the image content. A primary objective of alignment for
Dimensionality Reduction Meets Network Science: Sensemaking on UMAP’s kNN Graph (opens the original)
Read excerpt
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 the distortion that UMAP’s 2D projection introduces. We demonstrate the untapped potential of this internal representation, showing how standard graph algorithms applied to this graph enhance data sen
MoMo: Dial Motion Mode in Robot Manipulation with Spatiotemporal Action Tokenization (opens the original)
Read excerpt
To operate effectively across diverse contexts, robots must not only perform manipulation tasks accurately but also adapt how their actions unfold to the task, object, and interaction setting. We ask whether this execution-level variation can be learned as a reusable behavioral factor shared across tasks. We present MoMo, a two-stage imitation-learning framework consisting of a spatiotemporal action tokenizer and a behavior-cloning transformer that takes task and a continuous motion-mode conditi
Memory Efficient Audio Synthesis with Decoupled Temporal Depth Diffusion Transformers (opens the original)
Read excerpt
Siri Expressive Voices synthesize rich, configurable speech in real time and entirely on device, powered by AFM 3 Core Advanced, Apple’s most powerful on-device foundation model. This work presents the memory-efficient audio synthesis architecture behind that capability: a detokenizer that converts the semantic audio tokens emitted by the foundation model into high-fidelity audio within the tight compute and memory budget of the Apple Matrix Coprocessor (AMX). We convert semantic audio tokens to
GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks (opens the original)
Read excerpt
Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Existing slice discovery approaches largely model slices as clusters in representation space or combinations of predefined attributes. While effective for image-level classification, such formulations are insufficient for instance-level tasks such as object detection and segmentation, where failures often arise from contextual relational and spatially gro
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
Top 5M sites
For Apple Machine Learning, the outlet · Measured Aug 1, 2026
Website popularity band, not a count of readers or article views.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.