Mingda Chen

Hello! I am a research scientist at FAIR NYC. I'm interested in natural language processing and more recently multimodal understanding and generation.

Email: chenmda gmail com
Curriculum Vitae (outdated)

Papers

For a complete list of papers, see my google scholar profile.

2025

• 😈ImpRAG: Retrieval-Augmented Generation with Implicit Queries
  Wenzheng Zhang, Victoria Lin, Karl Stratos, Scott Wen-tau Yih, Mingda Chen
  arXiv Preprint, 2025
  arXiv

• Improving Factuality with Explicit Working Memory
  Mingda Chen, Yang Li, Karthik Padthe, Rulin Shao, Alicia Sun, Jacob Kahn, Luke Zettlemoyer, Gargi Ghosh, Scott Wen-tau Yih
  Proceedings of ACL, 2025
  arXiv

• Characterizing and Efficiently Accelerating Multimodal Generation Model Inference
  Lee et al.
  IEEE Micro, 2025
  arXiv

2024

• Chameleon: Mixed-Modal Early-Fusion Foundation Models
  FAIR Chameleon Team
  arXiv Preprint, 2024
  arXiv

• Few-Shot Data Synthesis for Open-Domain Multi-Hop Question Answering
  Mingda Chen, Xilun Chen, Scott Wen-tau Yih
  Proceedings of EACL, 2024 (oral)
  arXiv / BibTex

2023

• RA-DIT: Retrieval-Augmented Dual Instruction Tuning
  Victoria Lin*, Xilun Chen*, Mingda Chen*, Weijia Shi, Maria Lomeli, Rich James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, Scott Wen-tau Yih
  Proceedings of ICLR, 2023
  arXiv / BibTex

• Findings of the IWSLT 2023 Evaluation Campaign
  Agarwal et al.
  Proceedings of IWSLT, 2023
  PDF / BibTex

• BLASER: A Text-Free Speech-to-Speech Translation Evaluation Metric
  Mingda Chen, Paul-Ambroise Duquenne, Pierre Andrews, Justine Kao, Alexandre Mourachko, Holger Schwenk, Marta R. Costa-jussà
  Proceedings of ACL, 2023
  arXiv / BibTex

• xSIM++: An Improved Proxy to Bitext Mining Performance for Low-Resource Languages
  Mingda Chen*, Kevin Heffernan*, Onur Çelebi, Alexandre Mourachko, Holger Schwenk
  Proceedings of ACL, 2023 (oral)
  arXiv / BibTex

2022

• Leveraging Natural Supervision for Language Representation Learning and Generation
  Mingda Chen
  PhD Thesis, 2022
  arXiv / BibTex

• Improving In-Context Few-Shot Learning via Self-Supervised Training
  Mingda Chen, Jingfei Du, Ramakanth Pasunuru, Todor Mihaylov, Srini Iyer, Veselin Stoyanov, Zornitsa Kozareva
  Proceedings of NAACL, 2022
  arXiv / Poster / Slides / BibTex

• SummScreen: A Dataset for Abstractive Screenplay Summarization
  Mingda Chen, Zewei Chu, Sam Wiseman, Kevin Gimpel
  Proceedings of ACL, 2022 (oral)
  arXiv / Poster / Slides / Data / BibTex

2021

• TVRecap: A Dataset for Generating Stories with Character Descriptions
  Mingda Chen, Kevin Gimpel
  arXiv Preprint, 2021
  arXiv / Data / BibTex

• WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections
  Mingda Chen, Sam Wiseman, Kevin Gimpel
  Findings of ACL, 2021
  arXiv / Code / BibTex

2020

• Exemplar-Controllable Paraphrasing and Translation using Bitext
  Mingda Chen, Sam Wiseman, Kevin Gimpel
  arXiv Preprint, 2020
  arXiv / Data / BibTex

• Mining Knowledge for Natural Language Inference from Wikipedia Categories
  Mingda Chen*, Zewei Chu*, Karl Stratos, Kevin Gimpel
  Findings of EMNLP, 2020
  arXiv / Code / BibTex

• Learning Probabilistic Sentence Representations from Paraphrases
  Mingda Chen, Kevin Gimpel
  Proceedings of RepL4NLP at ACL, 2020
  arXiv / Slides / BibTex

• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
  Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut
  Proceedings of ICLR, 2020
  arXiv / Code / BibTex

• How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions
  Zewei Chu, Mingda Chen*, Jing Chen*, Miaosen Wang*, Kevin Gimpel, Manaal Faruqui, Xiance Si
  Proceedings of AAAI, 2020 (oral)
  arXiv / Data / BibTex

2019

• EntEval: A Holistic Evaluation Benchmark for Entity Representations
  Mingda Chen*, Zewei Chu*, Yang Chen, Karl Stratos, Kevin Gimpel
  Proceedings of EMNLP, 2019
  arXiv / Poster / Code / BibTex

• Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations
  Mingda Chen*, Zewei Chu*, Kevin Gimpel
  Proceedings of EMNLP, 2019 (oral)
  arXiv / Slides / Code / BibTex

• Controllable Paraphrase Generation with a Syntactic Exemplar
  Mingda Chen, Qingming Tang, Sam Wiseman, Kevin Gimpel
  Proceedings of ACL, 2019
  arXiv / Poster / Code / Train and Eval Data / BibTex

• A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
  Mingda Chen, Qingming Tang, Sam Wiseman, Kevin Gimpel
  Proceedings of NAACL-HLT, 2019
  arXiv / Poster / 1-Minute Slides / Code / Train Data / Eval Data / BibTex

2018

• Variational Sequential Labelers for Semi-Supervised Learning
  Mingda Chen, Qingming Tang, Karen Livescu, Kevin Gimpel
  Proceedings of EMNLP, 2018 (oral)
  PDF / Appendix / Slides / Code / BibTex

• Smaller Text Classifiers with Discriminative Cluster Embeddings
  Mingda Chen, Kevin Gimpel
  Proceedings of NAACL-HLT, 2018
  PDF / Poster / Code / BibTex