Pradeep Kumar Ravikumar

Learning from weak labelers as constraints

Contextures: Representations from Contexts

Identifying Representations for Intervention Extrapolation

Spectrally Transformed Kernel Regression

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

From Causal to Concept-Based Representation Learning

Do LLMs dream of elephants (when told not to)? Latent concept association and associative memory in transformers

Markov Equivalence and Consistency in Differentiable Structure Learning

Identifying General Mechanism Shifts in Linear Causal Representations

LLMSelect: Knowledge-based Feature Selection with Large Language Models