Pre-Trained Foundation Model Representations to Uncover Breathing Patterns in Speech
The process of human speech production involves coordinated respiratory action to elicit acoustic speech signals. Typically, speech is produced when air is forced...
Apple Intelligence Foundation Language Models
We present foundation language models developed to power Apple Intelligence features, including a ∼3 billion parameter model designed to run efficiently on devices...
Federated Learning With Differential Privacy for End-to-End Speech Recognition
*Equal Contributors
While federated learning (FL) has recently emerged as a promising approach to train machine learning models, it is limited to only preliminary...
Ferretv2: An Improved Baseline for Referring and Grounding
While Ferret seamlessly integrates regional understanding into the Large Language Model (LLM) to facilitate its referring and grounding capability, it poses certain limitations:...
Samplable Anonymous Aggregation for Private Federated Data Analytics
We revisit the problem of designing scalable protocols for private statistics and private federated learning when each device holds its private data. Locally...
Whispering Experts: Toxicity Mitigation in Pre-trained Language Models by Dampening Expert Neurons
An important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the...
International Conference on Machine Learning (ICML) 2024
International Conference on Machine Learning (ICML) 2024
Source link
PINE: Efficient Norm-Bound Verification for Secret-Shared Vectors
Secure aggregation of high-dimensional vectors is a fundamental primitive in federated statistics and learning. A two-server system such as PRIO allows for scalable...
Projected Language Models: A Large Model Pre-Segmented Into Smaller Ones
This paper has been accepted at the Foundation Models in the Wild workshop at ICML 2024.
Large language models are versatile tools but are...
Improving GFlowNets for Text-to-Image Diffusion Alignment
This paper was accepted at the Foundation Models in the Wild workshop at ICML 2024.
Diffusion models have become the de-facto approach for generating...
