Stanislav Fort
9 papers · 2019–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (12) π Conference Polyglot (4) π Academic Marathon (6) π§ Keyword Pioneer
π
Conference Polyglot
(4)
π
Academic Marathon
(6)
π
Grand Slam
π
Keyword Champion
(4)
π
Triple Crown
π
Conference Pioneer
Conferences
ICLR (4)
NIPS (3)
AAAI (1)
ICML (1)
Top co-authors
Keywords
loss landscape
(4)
neural network optimization
(3)
vision transformer
(1)
feature learning
(1)
few-shot learning
(1)
kernel learning
(1)
differential geometry
(1)
high dimensional optimization
(1)
convolutional neural network
(1)
deep neural network
(1)
hessian eigenvalue
(1)
out-of-distribution detection
(1)
training dynamics
(1)
mode connectivity
(1)
parameter space
(1)
network initialization
(1)
parameter trajectory
(1)
outlier exposure
(1)
network training
(1)
linear interpolation
(1)
Papers
Scaling Laws for Adversarial Attacks on Language Model Activations and Tokens
ICLR 2025
How many degrees of freedom do we need to train deep networks: a loss landscape perspective
ICLR 2022
Training independent subnetworks for robust prediction
ICLR 2021
Exploring the Limits of Out-of-Distribution Detection
NIPS 2021
On Monotonic Linear Interpolation of Neural Network Parameters
ICML 2021
The Break-Even Point on Optimization Trajectories of Deep Neural Networks
ICLR 2020
Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernel
NIPS 2020
Large Scale Structure of Neural Network Loss Landscapes
NIPS 2019
The Goldilocks Zone: Towards Better Understanding of Neural Network Loss Landscapes
AAAI 2019