Vikas K Garg

Frozen Priors, Fluid Forecasts: Prequential Uncertainty for Low-Data Deployment with Pretrained Generative Models

The Spacetime of Diffusion Models: An Information Geometry Perspective

Composition of Pretrained Diffusion Models: A Logic-Based Calculus

Contraction and Hourglass Persistence for Learning on Graphs, Simplices, and Cells

The Logical Expressiveness of Topological Neural Networks

Heat Kernel Goes Topological

AD-NODE: Adaptive Dynamics Learning with Neural ODEs for Mobile Robots Control

DIVIDE-AND-DENOISE: A GAME THEORETIC METHOD FOR FAIRLY COMPOSING DIFFUSION MODELS

Beyond Search: Direct Model Guidance for Steerable Synthesis Planning

Let Physics Guide Your Protein Flows: Topology-aware Unfolding and Generation

On topological descriptors for graph products

Graph Persistence goes Spectral

Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models

Positional Encoding meets Persistent Homology on Graphs