Pascal Frossard

28

Papers

526

Total Citations

Papers (28)

Robustness of classifiers: from adversarial to random noise

NeurIPS 2016arXiv

IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

DeFoG: Discrete Flow Matching for Graph Generation

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

NeurIPS 2025arXiv

Empirical Study of the Topology and Geometry of Deep Networks

Geometric Robustness of Deep Networks: Analysis and Improvement

Robustness via Curvature Regularization, and Vice Versa

SparseFool: A Few Pixels Make a Big Difference

GeoDA: A Geometric Framework for Black-Box Adversarial Attacks

Joint Graph-Based Depth Refinement and Normal Estimation

A Structured Dictionary Perspective on Implicit Neural Representations

A Geometry-Inspired Decision-Based Attack

U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture Search

PRIME: A Few Primitives Can Boost Robustness to Common Corruptions

Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises

Pi-DUAL: Using privileged information to distinguish clean from noisy labels

Localizing Task Information for Improved Model Merging and Compression

DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks

Universal Adversarial Perturbations

GOT: An Optimal Transport framework for Graph comparison

Hold me tight! Influence of discriminative features on deep network boundaries

Building powerful and equivariant graph neural networks with structural message-passing

Neural Anisotropy Directions

What can linearized neural networks actually say about generalization?

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

Graph-based Isometry Invariant Representation Learning

Geometry Aware Convolutional Filters for Omnidirectional Images Representation