Yuntian Deng Ph.D. Student Harvard University [CV] [Google Scholar] [Email]

My research aims at enabling ubiquitous long-form text generation, where anyone can produce a document on any topic with just a few clicks. To achieve this goal, my research focuses on the following three directions, utilizing advances in deep learning combined with probabilistic modeling:

• Long-Form Coherence to generate coherent documents with self-consistency and clear transitions.
• Transparent Generation to enable users to understand, debug, and control document generation.
• Efficient Systems to handle the scale and real-time requirements of long-form text generation.

I also work on open-source projects such as OpenNMT, Im2LaTeX, LaTeX2Im, and Steganography to make my research efforts more readily available for developers and researchers.

Statements

Selected Papers

	Markup-to-Image Diffusion Models with Scheduled Sampling Yuntian Deng, Noriyuki Kojima, Alexander M. Rush. ICLR 2023
	Model Criticism for Long-Form Text Generation Yuntian Deng, Volodymyr Kuleshov, Alexander M Rush. EMNLP 2022
	Cascaded Text Generation with Markov Transformers Yuntian Deng, Alexander M. Rush. NeurIPS 2020
	Residual Energy-Based Models for Text Generation Yuntian Deng, Anton Bakhtin, Myle Ott, Arthur Szlam, Marc'Aurelio Ranzato. ICLR 2020
	Latent Alignment and Variational Attention Yuntian Deng*, Yoon Kim*, Justin Chiu, Demi Guo, Alexander M. Rush. NIPS 2018
	Image-to-Markup Generation with Coarse-to-Fine Attention Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, and Alexander M. Rush. ICML 2017
	Neural Linguistic Steganography Zachary Ziegler*, Yuntian Deng*, Alexander Rush. EMNLP 2019 (Oral)
	OpenNMT: Open-Source Toolkit for Neural Machine Translation Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, Alexander M. Rush. ACL Demo 2017 (Best Demo Runner-up)

Contact