Yasaman Bahri
8 papers · 2017–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (3) π Academic Marathon (8) π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π₯
Mega-Team
(30)
π
Conference Pioneer
Conferences
ICLR (4)
ICML (3)
NIPS (1)
Top co-authors
Keywords
neural tangent kernel
(1)
mean field theory
(1)
attention mechanism
(1)
neural network optimization
(1)
neural network theory
(1)
gaussian process
(1)
gradient descent
(1)
random matrix theory
(1)
convolutional neural network
(1)
hessian eigenvalue
(1)
positional encoding
(1)
linear model
(1)
orthogonal transformation
(1)
critical point
(1)
dynamical isometry
(1)
infinite width
(1)
loss surface
(1)
spectral distribution
(1)
infinite width limit
(1)
vanishing gradient
(1)
Papers
CURIE: Evaluating LLMs on Multitask Scientific Long-Context Understanding and Reasoning
ICLR 2025
Infinite attention: NNGP and NTK for deep attention networks
ICML 2020
Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
ICLR 2019
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent
NIPS 2019
Sensitivity and Generalization in Neural Networks: an Empirical Study
ICLR 2018
Deep Neural Networks as Gaussian Processes
ICLR 2018
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
ICML 2018
Geometry of Neural Network Loss Surfaces via Random Matrix Theory
ICML 2017