141 citations · 291 across the 6 of their papers we have counts for
6 papers
PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest
Josh Beal, Eric Kim, Jinfeng Rao +3
While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems rema…
Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
Josh Beal, Hao-Yu Wu, Dong Huk Park +2
Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at ext…
Toward Transformer-Based Object Detection
Josh Beal, Eric Kim, Eric Tzeng +3
Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific t…
Bootstrapping Complete The Look at Pinterest
Eileen Li, Eric Kim, Andrew Zhai +2
Putting together an ideal outfit is a process that involves creativity and style intuition. This makes it a particularly difficult task to automate. Existing styling products gener…
Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
Edward Chou, Josh Beal, Daniel Levy +3
Homomorphic encryption enables arbitrary computation over data while it remains encrypted. This privacy-preserving feature is attractive for machine learning, but requires signific…
A Fully Private Pipeline for Deep Learning on Electronic Health Records
Edward Chou, Thao Nguyen, Josh Beal +2
We introduce an end-to-end private deep learning framework, applied to the task of predicting 30-day readmission from electronic health records. By using differential privacy durin…