JT
John Thickstun
cs.LGcs.CLcs.SDcs.AIstat.MLeess.AScs.CRcs.CYcs.MMcs.SE
On Valency
published · living versionsW_fxntxnnu·v1 · currentpublished
PianoBench: Evaluating Musical Perception and Reasoning in Language Models
with Louis Bradshaw, Irmak Bukey, Daniel Chenyu Lin, Chris Donahue
1 version
Preprints & journals
32 papers in the corpus · 2016–2026Spatial Induction Heads: In-Context Learning of Multidimensional Cellular Automata2610.09124v1 · Kimia Kazemian, Menghan Xu, John Thickstun et al.2026 · 0 citationsarXiv
Large Language Continuous Diffusion Models2610.02665v1 · Zhihan Yang, Wei Guo, Jean-Marie Lemercier et al.2026 · 0 citationsarXiv
Unlocking Lossless Speedups in LLMs via Discrete Diffusion2609.04010v1 · Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham et al.2026 · 0 citationsarXiv
From Forensics to Ecosystems: Rethinking Watermarks for Generative AI Oversight2608.07337v1 · Daniel Susser, John Thickstun, Gili Vidan2026 · 0 citationsarXiv
Fidelity-Diversity Metrics for Text2607.04563v1 · Amanda Wang, Tudor Manole, Florentina Bunea et al.2026 · 0 citationsarXiv
Music Transcription with (Almost) No Supervision2605.24193v1 · Saebyeol Shin, Chao Wan, Zhenzhen Liu et al.2026 · 0 citationsarXiv
Continuous Diffusion Scales Competitively with Discrete Diffusion for Language2605.18530v3 · Zhihan Yang, Wei Guo, Shuibai Zhang et al.2026 · 0 citationsarXiv
Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation2604.05150v2 · Geert Trooskens, Aaron Karlsberg, Anmol Sharma et al.2026 · 0 citationsarXiv
Scaling Beyond Masked Diffusion Language Models2602.15014v1 · Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang et al.2026 · 0 citationsarXiv
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms2511.03877v2 · Kimia Kazemian, Zhenzhen Liu, Yangfanyu Yang et al.2025 · 0 citationsarXiv
Esoteric Language Models: A Family of Any-Order Diffusion LLMs2506.01928v5 · Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri et al.2025 · 0 citationsarXiv
Aligning Text-to-Music Evaluation with Human Preferences2503.16669v1 · Yichen Huang, Zachary Novack, Koichi Saito et al.2025 · 1 citationarXiv
Hookpad Aria: A Copilot for Songwriters2502.08122v1 · Chris Donahue, Shih-Lun Wu, Yewon Kim et al.2025 · 0 citationsarXiv
Linearly Constrained Diffusion Implicit Models2411.00359v2 · Vivek Jayaram, Ira Kemelmacher-Shlizerman, Steven M. Seitz et al.2024 · 0 citationsarXiv
Robust Distortion-free Watermarks for Language Models2307.15593v3 · Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto et al.2023 · 23 citationsarXiv
Anticipatory Music Transformer2306.08620v2 · John Thickstun, David Hall, Chris Donahue et al.2023 · 4 citationsarXiv
Backpack Language Models2305.16765v1 · John Hewitt, John Thickstun, Christopher D. Manning et al.2023 · 10 citationsarXiv
MAUVE Scores for Generative Models: Theory and Practice2212.14578v2 · Krishna Pillutla, Lang Liu, John Thickstun et al.2022 · 5 citationsarXiv
Evaluating Human-Language Model Interaction2212.09746v5 · Mina Lee, Megha Srivastava, Amelia Hardy et al.2022 · 61 citationsarXiv
Melody transcription via generative pre-training2212.01884v1 · Chris Donahue, John Thickstun, Percy Liang2022 · 3 citationsarXiv
Reconstruction of visual images from mouse retinal ganglion cell spiking activity using convolutional neural networks10.1101/2022.06.10.482188v1 · Benster, T., Babino, D., Thickstun, J. et al.2022 · 0 citationsbioRxiv
Diffusion-LM Improves Controllable Text Generation2205.14217v1 · Xiang Lisa Li, John Thickstun, Ishaan Gulrajani et al.2022 · 380 citationsarXiv
Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics2105.08164v2 · Vivek Jayaram, John Thickstun2021 · 12 citationsarXiv
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers2102.01454v3 · Krishna Pillutla, Swabha Swayamdipta, Rowan Zellers et al.2021 · 114 citationsarXiv
Faster Policy Learning with Continuous-Time Gradients2012.06684v2 · Samuel Ainsworth, Kendall Lowrey, John Thickstun et al.2020 · 6 citationsL4DC 2021
Rethinking Evaluation Methodology for Audio-to-Score Alignment2009.14374v1 · John Thickstun, Jennifer Brennan, Harsh Verma2020 · 1 citationarXiv
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction2005.00652v3 · Bhargavi Paranjape, Mandar Joshi, John Thickstun et al.2020 · 87 citationsarXiv
Source Separation with Deep Generative Priors2002.07942v2 · Vivek Jayaram, John Thickstun2020 · 19 citationsarXiv
Convolutional Composer Classification1911.11737v1 · Harsh Verma, John Thickstun2019 · 3 citationsarXiv
Coupled Recurrent Models for Polyphonic Music Composition1811.08045v2 · John Thickstun, Zaid Harchaoui, Dean P. Foster et al.2018 · 5 citationsarXiv
Invariances and Data Augmentation for Supervised Music Transcription1711.04845v1 · John Thickstun, Zaid Harchaoui, Dean Foster et al.2017 · 47 citationsarXiv
Learning Features of Music from Scratch1611.09827v2 · John Thickstun, Zaid Harchaoui, Sham Kakade2016 · 143 citationsarXiv
Career total: 39 works. 32 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.