Search Results for author:
Found 5 papers, 1 papers with code
Salient Conditional Diffusion for Defending Against Backdoor Attacks
We propose a novel algorithm, Salient Conditional Diffusion (Sancdifi), a state-of-the-art defense against backdoor attacks.
Learning Geometrically Disentangled Representations of Protein Folding Simulations
Massive molecular simulations of drug-target proteins have been used as a tool to understand disease mechanism and develop therapeutics.
Optimizing Mode Connectivity via Neuron Alignment
Yet, current curve finding algorithms do not consider the influence of symmetry in the loss surface created by model weight permutations.
Unsupervised Geometric Disentanglement for Surfaces via CFAN-VAE
We also successfully detect a level of geometric disentanglement in mesh convolutional autoencoders that encode xyz-coordinates directly by registering its latent space to that of CFAN-VAE.
Optimizing Loss Landscape Connectivity via Neuron Alignment
Empirically, this initialization is critical for efficiently learning a simple, planar, low-loss curve between networks that successfully generalizes.
