David Wipf

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond

TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning

Chain-of-Thought Provably Enables Learning the (Otherwise) Unlearnable

Sparse Autoencoders, Again?

MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy

Explicit Preference Optimization: No Need for an Implicit Reward Model

Griffin: Towards a Graph-Centric Relational Database Foundation Model