Gregor Bachmann
17 papers
· 2020–2025
· 6 conferences
· across top CS/AI conferences
Achievements
π
Cross-Pollinator
(11)
π£
Hot Topic Early Bird
πΊοΈ
Taxonomy Completionist
(27)
π
Interdisciplinary Bridge
π§
Keyword Pioneer
π
Renaissance Researcher
(5)
π
Conference Polyglot
(6)
π
Academic Marathon
(5)
π€
Dynamic Duo
(12)
π
Triple Crown
π₯
Unstoppable
(6)
π
Century Club
(17)
β
The Questioner
ποΈ
Keyword Collector
(54)
Conferences
ICML (7)
NIPS (4)
ICLR (3)
ACL (1)
AISTATS (1)
CVPR (1)
Top co-authors
Keywords
bayesian neural network
(3)
knowledge distillation
(2)
cold posterior effect
(2)
data augmentation
(2)
computer vision
(1)
video generation
(1)
neural tangent kernel
(1)
model architecture
(1)
network architecture
(1)
neural network optimization
(1)
loss landscape
(1)
efficient computing
(1)
uniform convergence
(1)
gaussian priors
(1)
generative model
(1)
second-order optimization
(1)
hessian matrix
(1)
generalization bound
(1)
inductive bia
(1)
image generation
(1)
Papers
Tokenisation is NP-Complete
ACL 2025
How Good is a Single Basin?
AISTATS 2024
The Pitfalls of Next-Token Prediction
ICML 2024
The Curious Case of Benign Memorization
ICLR 2023
Scaling MLPs: A Tale of Inductive Bias
NIPS 2023
Random Teachers are Good Teachers
ICML 2023