Richard E. Turner

Graph Random Features for Scalable Gaussian Processes

Fresh in memory: Training-order recency is linearly encoded in language model activations

Wavelet-Induced Rotary Encodings: RoPE Meets Graphs

Warm Starts Accelerate Conditional Diffusion

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner

Influence Functions for Scalable Data Attribution in Diffusion Models

Distributional Training Data Attribution: What do Influence Functions Sample?

Gridded Transformer Neural Processes for Spatio-Temporal Data

Linear Transformer Topological Masking with Graph Random Features

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Variance-Reducing Couplings for Random Features

Gridded Transformer Neural Processes for Large Unstructured Spatio-Temporal Data

Fast Fractional Natural Gradient Descent using Learnable Spectral Factorizations

Adaptive Vision Encoders: Balancing Efficiency and Robustness in Vision-Language Models

Benchmarking Survival Models: Treatment Effects, Bias, and Equity