Stefanie Jegelka

11

Papers

57

Total Citations

Papers (11)

On the Emergence of Position Bias in Transformers

On the hardness of learning under symmetries

Learning Diffusion Models with Flexible Representation Guidance

NeurIPS 2025arXiv

Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness

Learning Linear Attention in Polynomial Time

Geometric Algorithms for Neural Combinatorial Optimization with Constraints

NeurIPS 2025arXiv

Simplicity Bias via Global Convergence of Sharpness Minimization

A Universal Class of Sharpness-Aware Minimization Algorithms

Sample Complexity Bounds for Estimating Probability Divergences under Invariances

Position: Future Directions in the Theory of Graph Machine Learning

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?