Bobby He
10 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (18) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (5)
π
Cross-Pollinator
(11)
π
Triple Crown
π
Century Club
(10)
π₯
Unstoppable
(6)
Conferences
ICLR (4)
NIPS (3)
ICML (2)
AISTATS (1)
Top co-authors
Keywords
model compression
(1)
transformer architecture
(1)
model quantization
(1)
representation learning
(1)
neural tangent kernel
(1)
ensemble learning
(1)
uncertainty quantification
(1)
self-supervised learning
(1)
attention mechanism
(1)
neural network optimization
(1)
gaussian process
(1)
covariance matrix
(1)
eigenvalue decay
(1)
posterior predictive
(1)
deep neural network
(1)
stochastic differential equation
(1)
feature collapse
(1)
transformer training
(1)
outlier feature
(1)
activation normalization
(1)
Papers
The Directionality of Optimization Trajectories in Neural Networks
ICLR 2025
Simplifying Transformer Blocks
ICLR 2024
Understanding and Minimising Outlier Features in Transformer Training
NIPS 2024
Recurrent Distance Filtering for Graph Representation Learning
ICML 2024
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
ICLR 2023
The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit
NIPS 2023
Feature Kernel Distillation
ICLR 2022
Exploring the Gap between Collapsed & Whitened Features in Self-Supervised Learning
ICML 2022
Stable ResNet
AISTATS 2021
Bayesian Deep Ensembles via the Neural Tangent Kernel
NIPS 2020