Jordan T. Ash

Computer Science · Physical Sciences

12h-index812citations41works0.52yr avg
OpenAlex↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Machine Learning and Data Classification(12), Machine Learning and Algorithms(9), Topic Modeling(8), Natural Language Processing Techniques(6), Domain Adaptation and Few-Shot Learning(6)

Publications41 total

The Coverage Principle: How Pre-Training Enables Post-Training
arXiv (Cornell University)·2025Open Access
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
arXiv (Cornell University)·2025Open Access
On the Query Complexity of Verifier-Assisted Language Generation
arXiv (Cornell University)·2025Open Access
Self-Improvement in Language Models: The Sharpening Mechanism
arXiv (Cornell University)·2024· 1 citedOpen Access
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
arXiv (Cornell University)·2024· 1 citedOpen Access
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
arXiv (Cornell University)·2024Open Access
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
2024
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
2024· 2 citedOpen Access
The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
arXiv (Cornell University)·2023· 8 citedOpen Access
Current infra-red developments within Leonardo
2023
Understanding and Improving Neural Active Learning on Heteroskedastic Distributions
Frontiers in artificial intelligence and applications·2023Open Access
Exposing Attention Glitches with Flip-Flop Language Modeling
arXiv (Cornell University)·2023· 8 citedOpen Access
Streaming Active Learning with Deep Neural Networks
arXiv (Cornell University)·2023· 2 citedOpen Access
Neural Active Learning on Heteroskedastic Distributions
arXiv (Cornell University)·2022Open Access
Eigen Memory Trees
arXiv (Cornell University)·2022Open Access
Transformers Learn Shortcuts to Automata
arXiv (Cornell University)·2022· 11 citedOpen Access
Understanding Contrastive Learning Requires Incorporating Inductive Biases
arXiv (Cornell University)·2022· 15 citedOpen Access
Anti-Concentrated Confidence Bonuses for Scalable Exploration
arXiv (Cornell University)·2021Open Access
Investigating the Role of Negatives in Contrastive Representation Learning
arXiv (Cornell University)·2021· 11 citedOpen Access
Gone Fishing: Neural Active Learning with Fisher Embeddings
arXiv (Cornell University)·2021· 16 citedOpen Access
page 1 of 3Next →

Frequent Co-authors

Akshay Krishnamurthy(12), Cyril Zhang(7), Surbhi Goel(6), John Langford(5), Ryan P. Adams(5), Barbara E. Engelhardt(4), Tianju Xue(3), Alex Beatson(3), Geoffrey Roeder(3), Robert E. Schapire(3), Sham M. Kakade(3), Dipendra Misra(3), Dylan J. Foster(3), Chicheng Zhang(2), Alekh Agarwal(2), Gregory Darnell(2), Daniel Munro(2), Robert Langlois(2), Jesper Pallesen(2), Joachim Frank(2)