About Me

At Pinterest, I have led a variety of large-scale machine learning projects and published research on representation learning and recommender systems.

I earned my B.S./M.S. in Computer Science from Stanford. I worked with Fei-Fei Li and Serena Yeung on privacy-preserving computer vision.

I moonlighted as a Ph.D. flâneur in the Yale Applied Cryptography Lab, working with Ben Fisch. My research focused on recursive zero-knowledge proofs, which have powerful applications in decentralized systems and verifiable machine learning.

I was the co-founder and CTO of Reveal, a venture-backed startup that developed one of the first social networking apps with cryptocurrency incentive mechanisms.

Selected Publications

For a complete list of publications, please visit my Google Scholar profile here.

• PinCLIP: Large-scale Foundational Multimodal Representation at Pinterest
  Josh Beal, Eric Kim, Jinfeng Rao, Rex Wu, Dmitry Kislyuk, Charles Rosenberg. arXiv 2026.
• Mira: Efficient Folding for Pairing-Based Arguments
  Josh Beal, Ben Fisch. ePrint 2024.
• Derecho: Privacy Pools with Proof-Carrying Disclosures
  Josh Beal, Ben Fisch. CCS 2024.
• Billion-Scale Pretraining with Vision Transformers for Multi-Task Visual Representations
  Josh Beal, Hao-Yu Wu, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk. WACV 2022.
• Toward Transformer-Based Object Detection
  Josh Beal, Eric Kim, Eric Tzeng, Dong Huk Park, Andrew Zhai, Dmitry Kislyuk. arXiv 2020.
• Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference
  Josh Beal, Edward Chou, Daniel Levy, Serena Yeung, Albert Haque, Li Fei-Fei. arXiv 2018.