Jordan Ash
8 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (28) π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4)
π
Academic Marathon
(6)
π
Cross-Pollinator
(6)
π
Renaissance Researcher
(5)
π
Trend Setter
π₯
Unstoppable
(5)
Conferences
NIPS (4)
ICML (2)
ACL (1)
AISTATS (1)
Top co-authors
Keywords
neural network
(2)
large language model
(2)
inductive bia
(2)
active learning
(2)
neural network training
(1)
model selection
(1)
representation learning
(1)
language modeling
(1)
warm starting
(1)
incremental learning
(1)
energy minimization
(1)
maximum likelihood
(1)
fisher information
(1)
experimental design
(1)
label efficiency
(1)
attention mechanism
(1)
parametric optimization
(1)
generalization error bound
(1)
unsupervised representation learning
(1)
margin theory
(1)
Papers
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
ACL 2024
Exposing Attention Glitches with Flip-Flop Language Modeling
NIPS 2023
Understanding Contrastive Learning Requires Incorporating Inductive Biases
ICML 2022
Investigating the Role of Negatives in Contrastive Representation Learning
AISTATS 2022
Gone Fishing: Neural Active Learning with Fisher Embeddings
NIPS 2021
On Warm-Starting Neural Network Training
NIPS 2020
Learning Composable Energy Surrogates for PDE Order Reduction
NIPS 2020
Learning Deep ResNet Blocks Sequentially using Boosting Theory
ICML 2018