Title |
|---|
 Compute-Optimal LLMs Provably Generalize Better With ScaleInternational Conference on Learning Representations (ICLR), 2025 |
 Diffusing Differentiable RepresentationsNeural Information Processing Systems (NeurIPS), 2024 |
 Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects ModelsNeural Information Processing Systems (NeurIPS), 2024 |
 Searching for Efficient Linear Layers over a Continuous Space of
Structured MatricesNeural Information Processing Systems (NeurIPS), 2024 |
 Any-dimensional equivariant neural networksInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023 |
