John Thickstun

According to our database, John Thickstun authored at least 23 papers between 2017 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2025

Esoteric Language Models.

Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri, Johnna Liu, Deepansha Singh, Zhoujun Cheng, Zhengzhong Liu, Eric Xing, John Thickstun, Arash Vahdat

CoRR, June, 2025

Aligning Text-to-Music Evaluation with Human Preferences.

Yichen Huang, Zachary Novack, Koichi Saito, Jiatong Shi, Shinji Watanabe, Yuki Mitsufuji, John Thickstun, Chris Donahue

CoRR, March, 2025

Hookpad Aria: A Copilot for Songwriters.

Chris Donahue, Shih-Lun Wu, Yewon Kim, Dave B. Carlton, Ryan H. Miyakawa, John Thickstun

CoRR, February, 2025

2024

Anticipatory Music Transformer.

John Thickstun, David Leo Wright Hall, Chris Donahue, Percy Liang

Trans. Mach. Learn. Res., 2024

Robust Distortion-free Watermarks for Language Models.

Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang

Trans. Mach. Learn. Res., 2024

Constrained Diffusion Implicit Models.

Vivek Jayaram, Ira Kemelmacher-Shlizerman, Steven M. Seitz, John Thickstun

CoRR, 2024

2023

Evaluating Human-Language Model Interaction.

Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang Lisa Li, Faisal Ladhak, Frieda Rong, Rose E. Wang, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee, Rishi Bommasani, Michael S. Bernstein, Percy Liang

Trans. Mach. Learn. Res., 2023

MAUVE Scores for Generative Models: Theory and Practice.

Krishna Pillutla, Lang Liu, John Thickstun, Sean Welleck, Swabha Swayamdipta, Rowan Zellers, Sewoong Oh, Yejin Choi, Zaïd Harchaoui

J. Mach. Learn. Res., 2023

Backpack Language Models.

John Hewitt, John Thickstun, Christopher D. Manning, Percy Liang

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022

Diffusion-LM Improves Controllable Text Generation.

Xiang Lisa Li, John Thickstun, Ishaan Gulrajani, Percy Liang, Tatsunori B. Hashimoto

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Melody transcription via generative pre-training.

Chris Donahue, John Thickstun, Percy Liang

Proceedings of the 23rd International Society for Music Information Retrieval Conference, 2022

2021

Leveraging Generative Models for Music and Signal Processing.

John Thickstun

PhD thesis, 2021

MAUVE: Human-Machine Divergence Curves for Evaluating Open-Ended Text Generation.

Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Yejin Choi, Zaïd Harchaoui

CoRR, 2021

MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers.

Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers, John Thickstun, Sean Welleck, Yejin Choi, Zaïd Harchaoui

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Faster Policy Learning with Continuous-Time Gradients.

Samuel K. Ainsworth, Kendall Lowrey, John Thickstun, Zaïd Harchaoui, Siddhartha S. Srinivasa

Proceedings of the 3rd Annual Conference on Learning for Dynamics and Control, 2021

Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics.

Vivek Jayaram, John Thickstun

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

Rethinking Evaluation Methodology for Audio-to-Score Alignment.

John Thickstun, Jennifer Brennan, Harsh Verma

CoRR, 2020

Source Separation with Deep Generative Priors.

Vivek Jayaram, John Thickstun

Proceedings of the 37th International Conference on Machine Learning, 2020

An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction.

Bhargavi Paranjape, Mandar Joshi, John Thickstun, Hannaneh Hajishirzi, Luke Zettlemoyer

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020

2019

Convolutional Composer Classification.

Harsh Verma, John Thickstun

Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019

Coupled Recurrent Models for Polyphonic Music Composition.

John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade

Proceedings of the 20th International Society for Music Information Retrieval Conference, 2019

2018

Invariances and Data Augmentation for Supervised Music Transcription.

John Thickstun, Zaïd Harchaoui, Dean P. Foster, Sham M. Kakade

Proceedings of the 2018 IEEE International Conference on Acoustics, 2018

2017

Learning Features of Music From Scratch.

John Thickstun, Zaïd Harchaoui, Sham M. Kakade

Proceedings of the 5th International Conference on Learning Representations, 2017