Industry
Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors
BERT, and GPT models show GRACE's state-of-the-art performance in making
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
Based on our definitions, we identify and analyze six real-world benchmarks spanning from homophilic to heterophilic link prediction settings, with graphs containing up to 30M edges.
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design.
Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
As a result, it tractably draws samples even when the matrices forming the Khatri-Rao product have tens of millions of rows each.
Multi-task Representation Learning for Pure Exploration in Bilinear Bandits
Bilinear bandits (Jun et al., 2019; Lu et al., 2021; Kang et al., 2022) are an important class of
