Vikas Garg

When do GFlowNets learn the right distribution?

E(3)-equivariant models cannot learn chirality: Field-based molecular generation

Diffusion Models as Cartoonists: The Curious Case of High Density Regions

Generalization and Distributed Learning of GFlowNets

Robust Simulation-Based Inference under Missing Data via Neural Processes

Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models

Topological Data Analysis on Graphs: Euler characteristics, Persistent Homology, or Spectrum?

Train once and generalize: Zero-shot quantum state preparation with RL

Topological Positional Encoding

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

Algebraic Positional Encodings

What do Graph Neural Networks learn? Insights from Tropical Geometry

Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond

How well does Persistent Homology generalize on graphs?

Diffusion Twigs with Loop Guidance for Conditional Graph Generation

Molecule Generation by Heterophilious Triple Flows

Twinned Interventional Flows

Meta Compression: Learning to compress Deep Neural Networks

Streamlining Generative Models for Structure-Based Drug Design

Forked Diffusion for Conditional Graph Generation