Mohammad Pezeshki
10 papers · 2016–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (20)
π§
Keyword Pioneer
π
Century Club Β· Bronze
π
Conference Pioneer
Top co-authors
Research topics
Keywords
feature learning
(2)
out-of-distribution generalization
(2)
distribution shift
(2)
semi-supervised learning
(1)
game theory
(1)
sequence labeling
(1)
domain adaptation
(1)
denoising autoencoder
(1)
compositional generalization
(1)
gradient descent
(1)
generalization error
(1)
connectionist temporal classification
(1)
dynamical system
(1)
neural network dynamics
(1)
robust learning
(1)
acoustic modeling
(1)
sample efficiency
(1)
convolutional neural network
(1)
recurrent neural network
(1)
double descent
(1)
Papers
Compositional Risk Minimization
ICML 2025
Improving the Scaling Laws of Synthetic Data with Deliberate Practice
ICML 2025
The Pitfalls of Memorization: When Memorization Hurts Generalization
ICLR 2025
Discovering Environments with XRM
ICML 2024
Multi-scale Feature Learning Dynamics: Insights for Double Descent
ICML 2022
Simple data balancing achieves competitive worst-group-accuracy
CLeaR 2022
Gradient Starvation: A Learning Proclivity in Neural Networks
NeurIPS 2021
Negative Momentum for Improved Game Dynamics
AISTATS 2019
Deconstructing the Ladder Network Architecture
ICML 2016
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Interspeech 2016