Picture for Jordan T. Ash

Jordan T. Ash

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning

May 29, 2024
Viaarxiv icon

An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models

Jan 12, 2024
Viaarxiv icon

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

Add code
Dec 21, 2023
Viaarxiv icon

Exposing Attention Glitches with Flip-Flop Language Modeling

Add code
Jun 01, 2023
Figure 1 for Exposing Attention Glitches with Flip-Flop Language Modeling
Figure 2 for Exposing Attention Glitches with Flip-Flop Language Modeling
Figure 3 for Exposing Attention Glitches with Flip-Flop Language Modeling
Figure 4 for Exposing Attention Glitches with Flip-Flop Language Modeling
Viaarxiv icon

Streaming Active Learning with Deep Neural Networks

Add code
Mar 05, 2023
Figure 1 for Streaming Active Learning with Deep Neural Networks
Figure 2 for Streaming Active Learning with Deep Neural Networks
Figure 3 for Streaming Active Learning with Deep Neural Networks
Figure 4 for Streaming Active Learning with Deep Neural Networks
Viaarxiv icon

Neural Active Learning on Heteroskedastic Distributions

Add code
Nov 02, 2022
Figure 1 for Neural Active Learning on Heteroskedastic Distributions
Figure 2 for Neural Active Learning on Heteroskedastic Distributions
Figure 3 for Neural Active Learning on Heteroskedastic Distributions
Figure 4 for Neural Active Learning on Heteroskedastic Distributions
Viaarxiv icon

Eigen Memory Trees

Add code
Oct 31, 2022
Figure 1 for Eigen Memory Trees
Figure 2 for Eigen Memory Trees
Figure 3 for Eigen Memory Trees
Figure 4 for Eigen Memory Trees
Viaarxiv icon

Transformers Learn Shortcuts to Automata

Add code
Oct 19, 2022
Viaarxiv icon

Anti-Concentrated Confidence Bonuses for Scalable Exploration

Add code
Oct 21, 2021
Figure 1 for Anti-Concentrated Confidence Bonuses for Scalable Exploration
Figure 2 for Anti-Concentrated Confidence Bonuses for Scalable Exploration
Figure 3 for Anti-Concentrated Confidence Bonuses for Scalable Exploration
Figure 4 for Anti-Concentrated Confidence Bonuses for Scalable Exploration
Viaarxiv icon

Investigating the Role of Negatives in Contrastive Representation Learning

Jun 18, 2021
Figure 1 for Investigating the Role of Negatives in Contrastive Representation Learning
Figure 2 for Investigating the Role of Negatives in Contrastive Representation Learning
Figure 3 for Investigating the Role of Negatives in Contrastive Representation Learning
Figure 4 for Investigating the Role of Negatives in Contrastive Representation Learning
Viaarxiv icon