Yingshan Chang

Greetings! I am a 5th year PhD student at the Language Technology Institute of Carnegie Mellon University. I am very fortunate to be advised by Professor Yonatan Bisk. I received my Bachelor's degree in Computer Science & Mathematics with first class honors from Hong Kong University of Science and Technology. I love trees and nature documentaries. I get along with people who write or will write good books.
Curriculum Vitae

Big questions that puzzle me:

  1. What are hard to learn?
  2. Why are they hard? (quantify their complexity)
  3. To what extent "learning = computation" is true?
  4. To what extent "cognition = computation" is true?

My research, in broad terms, engages with concepts that defy easy definition but embody the shared struggle of these large communities: Computation, Learning, and Cognition.

Examples of "elusive concepts" include: Generalization, Abstraction, and Reasoning. The research landscape on the nature of these concepts tends to be tightly interwoven. What further complicates the picture is the learning component: generalization, abstraction and reasoning are not enough. I tend to focus on learning to generalize, learning to abstract, and learning to reason. The challenge lies in that building the computational foundation of each one of them depends on one another. Because we are living in a nascent stage of this field, substantial effort on formalization, quantification, categorization and unification is needed. This is why I'm so intellectually invested in these areas and want to dedicate a career to them ✨.

Current Research

My PhD work studies generalization to unseen domains in deep learning, where an unseen domain is a collection of instances systematically unsupported by training data. I contribute to an expanding collection of insights on this subject from multiple angles: categorization, formalization, and identification of performance indicators. My work is structured around three concepts: Composition, Cardinality, and Frame. A series of investigations uncovered three factors that shape generalization in deep learning: data, architectural bias, and the learning paradigm.

Publications

Yingshan Chang and Yonatan Bisk. "Model Successor Functions" arXiv:2502.00197 Under review
Yingshan Chang and Yonatan Bisk. "Language Models Need Inductive Biases to Count Inductively" ICLR 2025
Jimin Sun, So Yeon Min, Yingshan Chang, Yonatan Bisk "Tools Fail: Detecting Silent Errors in Faulty Tools" EMNLP 2024
Shaurya Dewan, Rushikesh Zawar, Prakanshul Saxena, Yingshan Chang, Andrew Luo, Yonatan Bisk. "DiffusionPID: Interpreting Diffusion via Partial Information Decomposition" Neurips 2024
Yingshan Chang, Yasi Zhang, Zhiyuan Fang, Yingnian Wu, Yonatan Bisk, Feng Gao. "Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation" European Conference on Computer Vision (ECCV) 2024.
Akter, Syeda Nahida, Sangwu Lee, Yingshan Chang, Yonatan Bisk and Eric Nyberg. “VISREAS: Complex Visual Reasoning with Unanswerable Questions” In Findings of the Association for Computational Linguistics: ACL 2024.
Liangke Gui, Yingshan Chang, Qiuyuan Huang, Subhojit Som, Alexander G Hauptmann, Jianfeng Gao and Yonatan Bisk. “Training Vision-Language Transformers from Captions” In Transactions on Machine Learning Research, pp. 2835-8856. 2023.
Yingshan Chang, Mridu Narang, Hisami Suzuki, Guihong Cao, Jianfeng Gao, and Yonatan Bisk. “Webqa: Multihop and Multimodal QA” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 16495-16504. 2022. Oral.
Yingshan Chang, and Yonatan Bisk. “WebQA: A Multimodal Multihop NeurIPS Challenge” In NeurIPS 2021 Competitions and Demonstrations Track, pp. 232-245. PMLR, 2022.

Writings and Photography

🌟Thoughts🌲Gallery🏔Journal

Education

Carnegie Mellon University

PhD in Language Technologies  2022 -

Carnegie Mellon University

MS in Language Technologies  2020 - 2022

Hong Kong University of Science and Technology

BS in Computer Science & Mathematics  2016 - 2020

Georgia Institute of Technology

Exchange  Spring 2019

Peking University

AEARU Summer Camp  Summer 2018

Old Projects

Neuro-Concepts

CMU 85707  Spring 2022

  • Read more

Conlanging

CMU 11823  Spring 2022

  • Read more

Sociolinguistics

CMU 11724  Fall 2021

  • Read more

Low-Light Video Enhancement Using Deep Learning

  • Read more

2019-2020

Internet Computing

HKUST COMP4021  Fall 2019

  • Read more

Event-to-Sentence Using BERT in Automated Story Generation

  • Read more

Summer 2019

Machine Learning

Georgia Tech CS4641  Spring 2019

  • Read more

Information Visualization

Georgia Tech CS4460  Spring 2019

  • Read more

Language Modelling

HKUST COMP4901K  Fall 2018

  • Read more

Customer Revenue Prediction with Spark

HKUST COMP4651  Fall 2018

  • Read more

A Blockchain and Smart Contract Application

  • Read more

Fall 2018