Daniel Soudry

5

Papers

12

Total Citations

Papers (5)

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets

Optimal Rates in Continual Linear Regression via Increasing Regularization

NeurIPS 2025arXiv

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

NeurIPS 2025arXiv

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers