27 citations · 49 across the 12 of their papers we have counts for
12 papers
Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled Diffusion
Pengcheng Jiang, Judith Yue Li, Moonkyung Ryu +8
Many modern retrieval problems are set-valued: given a broad intent, the system must return a collection of results that optimizes higher-order properties (e.g., diversity, coverag…
Efficient Hyperparameter Search for Non-Stationary Model Training
Berivan Isik, Matthew Fahrbach, Dima Kuzmin +4
Online learning is the cornerstone of applications like recommendation and advertising systems, where models continuously adapt to shifting data distributions. Model training for s…
Successive Halving with Learning Curve Prediction via Latent Kronecker Gaussian Processes
Jihao Andreas Lin, Nicolas Mayoraz, Steffen Rendle +3
Successive Halving is a popular algorithm for hyperparameter optimization which allocates exponentially more resources to promising candidates. However, the algorithm typically rel…
Diff4Steer: Steerable Diffusion Prior for Generative Music Retrieval with Semantic Guidance
Xuchan Bao, Judith Yue Li, Zhong Yi Wan +5
Modern music retrieval systems often rely on fixed representations of user preferences, limiting their ability to capture users' diverse and uncertain retrieval needs. To address t…
PERSOMA: PERsonalized SOft ProMpt Adapter Architecture for Personalized Language Prompting
Liam Hebert, Krishna Sayana, Ambarish Jash +5
Understanding the nuances of a user's extensive interaction history is key to building accurate and personalized natural language systems that can adapt to evolving user preference…
User Embedding Model for Personalized Language Prompting
Sumanth Doddapaneni, Krishna Sayana, Ambarish Jash +2
Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recomm…