Publications

2025

• How Do Vision-Language Models Process Conflicting Information Across Modalities?
  Tianze Hua*, Tian Yun*, Ellie Pavlick
  Under Review
  [paper] [project] [code]

• TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration
  Yanshu Li, Jianjiang Yang, Tian Yun, Pinyuan Feng, Jinfa Huang, Ruixiang Tang
  Under Review

• $100K or 100 days: Trade-offs when Pre-Training with Academic Resources
  Apoorv Khandelwal, Tian Yun, Nihal V. Nayak, Jack Merullo, Stephen H. Bach, Chen Sun, Ellie Pavlick
  COLM 2025
  [paper] [code]

• What is an “Abstract Reasoner”? Revisiting Experiments and Arguments about Large Language Models
  Tian Yun, Ellie Pavlick, Chen Sun
  CONLL 2025
  [paper] [project]

• Pre-trained Vision-Language Models Learn Discoverable Visual Concepts
  Yuan Zang, Tian Yun, Hao Tan, Trung Bui, Chen Sun
  TMLR 2025
  [paper] [project] [code]

2024

• mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? Tianze Hua*, Tian Yun*, Ellie Pavlick
  NAACL 2024
  [paper] [project] [code]

2023

• Emergence of Grounded Representations in Embodied Sequence Modeling
  Tian Yun*, Zilai Zeng*, Kunal Handa, Ashish Thapliyal, Bo Pang, Ellie Pavlick, Chen Sun
  EMNLP 2023
  [paper] [project] [code]

• Improved Inference of Human Intent by Combining Plan Recognition and Language Feedback
  Ifrah Idrees, Tian Yun, Naveen Sharma, Nakul Gopalan, Stefanie Tellex, George Konidaris
  IROS 2023
  [paper]

• Do Vision-Language Pretrained Models Learn Composable Primitive Concepts?
  Tian Yun, Usha Bhalla, Ellie Pavlick, Chen Sun
  TMLR
  [paper] [project] [code]

2021

• Does Vision-and-Language Pretraining Improve Lexical Grounding?
  Tian Yun, Chen Sun, Ellie Pavlick
  Findings of EMNLP 2021
  [paper] [code]

• Mining Biomedical Texts for Pediatric Information
  Tian Yun, Deepti Garg, Natalia Khuri
  14th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOINFORMATICS, 2021
  [paper]

Preprints

• BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
  Teven Scao et al.
  arXiv preprint arXiv:2211.05100 (2022)
  [paper]