Ash, Jordan T.

13 publications

ICML 2025 On the Query Complexity of Verifier-Assisted Language Generation Edoardo Botta, Yuchen Li, Aashay Mehta, Jordan T. Ash, Cyril Zhang, Andrej Risteski

ICLRW 2025 On the Query Complexity of Verifier-Assisted Language Generation Edoardo Botta, Yuchen Li, Aashay Mehta, Jordan T. Ash, Cyril Zhang, Andrej Risteski

ICLR 2025 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

NeurIPS 2024 A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning Arthur Juliani, Jordan T. Ash

NeurIPSW 2024 Self-Improvement in Language Models: The Sharpening Mechanism Audrey Huang, Adam Block, Dylan J Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

ICLR 2024 The Truth Is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction Pratyusha Sharma, Jordan T. Ash, Dipendra Misra

ICMLW 2023 Exposing Attention Glitches with Flip-Flop Language Modeling Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang

ICML 2023 Streaming Active Learning with Deep Neural Networks Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan T. Ash

ICLR 2023 Transformers Learn Shortcuts to Automata Bingbin Liu, Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang

ICLR 2022 Anti-Concentrated Confidence Bonuses for Scalable Exploration Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade

NeurIPSW 2021 Catastrophic Failures of Neural Active Learning on Heteroskedastic Distributions Savya Khosla, Alex Lamb, Jordan T. Ash, Cyril Zhang, Kenji Kawaguchi

ICLR 2020 Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal

UAI 2019 End-to-End Training of Deep Probabilistic CCA on Paired Biomedical Observations Gregory Gundersen, Bianca Dumitrascu, Jordan T. Ash, Barbara E. Engelhardt