content type videopublished August 29, 2024
Apple Workshop on Privacy-Preserving Machine Learning: Flocks of Stochastic Parrots: Differentially Private Prompt Learning for LLMs
AuthorsNicolas Papernot (University of Toronto, Vector Institute)
Related readings and updates.
What Matters in Practical Learned Image Compression
May 7, 2026research area Computer Visionconference CVPR
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 to close this gap. We conduct a comprehensive study of the key modeling choices that govern the design of a practical learned image codec, jointly…
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
May 7, 2026research area Computer Vision, research area Methods and Algorithmsconference ICML
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 representations. In this work, we propose Text-Conditional JEPA (TC-JEPA) that uses image captions to reduce the prediction uncertainty. Specifically, we…
Discover opportunities in Machine Learning.
Our research in machine learning breaks new ground every day.