5 papers
Any-Subgroup Equivariant Networks via Symmetry Breaking
Abhinav Goel, Derek Lim, Hannah Lawrence +2
The inclusion of symmetries as an inductive bias, known as equivariance, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant archit…
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
Guy Bar-Shalom, Fabrizio Frasca, Derek Lim +5
The automated detection of hallucinations and training data contamination is pivotal to the safe deployment of Large Language Models (LLMs). These tasks are particularly challengin…
A Canonicalization Perspective on Invariant and Equivariant Learning
George Ma, Yifei Wang, Derek Lim +2
In many applications, we desire neural networks to exhibit invariance or equivariance to certain groups due to symmetries inherent in the data. Recently, frame-averaging methods em…
Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
Theo Putterman, Derek Lim, Yoav Gelberg +2
Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting p…
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Moe Putterman, Robin Walters +2
Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries -- transformations of neural network parameters that do not change the underly…