Promoting Cross-Modal Representations to Improve Multimodal Foundation Models for Physiological Signals
Many healthcare applications are inherently multimodal, involving several physiological signals. As sensors for these signals become more common, improving machine learning methods for...
Smart Audit System Empowered by LLM
Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and heavily reliant...
Divide-or-Conquer? Which Part Should You Distill Your LLM?
Recent methods have demonstrated that Large Language Models (LLMs) can solve reasoning tasks better when they are encouraged to solve subtasks of the...
Combining Machine Learning and Homomorphic Encryption in the Apple Ecosystem
At Apple, we believe privacy is a fundamental human right. Our work to protect user privacy is informed by a set of privacy...
Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison
The goal of aligning language models to human preferences requires data that reveal these preferences. Ideally, time and money can be spent carefully...
CtrlSynth: Controllable Image-Text Synthesis for Data-Efficient Multimodal Learning
Pretraining robust vision or multimodal foundation models (e.g., CLIP) relies on large-scale datasets that may be noisy, potentially misaligned, and have long-tail distributions....
MUSCLE: A Model Update Strategy for Compatible LLM Evolution
Large Language Models (LLMs) are regularly updated to enhance performance, typically through changes in data or architecture. Within the update process, developers often...
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
The growing demand for personalized and private on-device applications highlights the importance of source-free unsupervised domain adaptation (SFDA) methods, especially for time-series data,...
4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
*Equal Contributors
Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse...
Scalable Private Search with Wally
This paper presents Wally, a private search system that supports efficient semantic and keyword search queries against
large databases. When sufficiently many clients are...