Andrew McCallum

13

Papers

391

Total Citations

Papers (13)

Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples

NeurIPS 2017arXiv

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise

NeurIPS 2025arXiv

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Fast, Scalable, Warm-Start Semidefinite Programming with Spectral Bundling and Sketching

Modeling Transitivity and Cyclicity in Directed Graphs via Binary Code Box Embeddings

Structured Energy Network As a Loss

Structured Prediction Energy Networks

End-to-End Learning for Structured Prediction Energy Networks

Compact Representation of Uncertainty in Clustering

Search-Guided, Lightly-Supervised Training of Structured Prediction Energy Networks

Improving Local Identifiability in Probabilistic Box Embeddings

Capacity and Bias of Learned Geometric Embeddings for Directed Graphs