I am a final-year Ph.D. student in Computer Science & Engineering at the University of Washington, working with Ranjay Krishna and Alex Ratner on tackling challenges in today's large-scale machine learning environment. I am grateful to be supported by the Google PhD Fellowship.

Previously, I recevied my B.S. and M.S. from National Taiwan University, where I was fortunate to work with Hsuan-Tien Lin. Prior to joining UW, I spent wonderful time visiting Carnegie Mellon University and Univeristy of California, Los Angeles, where I worked with Pradeep Ravikumar and Cho-Jui Hsieh.

I am on the job market this year. Please feel free to reach out to discuss potential opportunities!

Research Interests

My research goal is to democratize AI development by making both data and model scaling more efficient and effective in today’s large-scale environment, based on four complementary areas of work tackling different aspects of data and model scaling challenges. On data side, I study (1) how to efficiently curate large datasets, and (2) how to effectively align model behavior through data. On model side, I tackle (3) how to efficiently deploy large models, and (4) how to effectively adapt large models to downstream applications.

Preprints

• Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions. 2024.
  Yu-Guan Hsieh*, Cheng-Yu Hsieh*, Shih-Ying Yeh, Louis Béthune, Hadi Pour Ansari, Pavan Kumar Anasosalu Vasu, Chun-Liang Li, Ranjay Krishna, Oncel Tuzel, Marco Cuturi

Publications

• The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better.
  Scott Geng, Cheng-Yu Hsieh, Vivek Ramanujan, Matthew Wallingford, Chun-Liang Li, Pang Wei Koh, Ranjay Krishna.
  NeurIPS 2024.

• DataComp-LM: In search of the next generation of training sets for language models.
  DataComp-LM Team.
  NeurIPS 2024.

• Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps.
  Yung-Sung Chuang, Linlu Qiu, Cheng-Yu Hsieh, Ranjay Krishna, Yoon Kim, James Glass
  EMNLP 2024.

• Is C4 Dataset Enough for Pruning? An Investigation of Calibration Data for LLM Pruning.
  Abhinav Bandari, Lu Yin, Cheng-Yu Hsieh, Ajay Jaiswal, Tianlong Chen, Li Shen, Ranjay Krishna, Shiwei Liu
  EMNLP 2024.

• The Hard Positive Truth about Vision-Language Compositionality.
  Amita Kamath, Cheng-Yu Hsieh, Kai-Wei Chang, Ranjay Krishna.
  ECCV 2024.

• Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization.
  Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James R. Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna*, Tomas Pfister*.
  ACL Findings 2024.

• Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity.
  Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Gen Li, Ajay Jaiswal, Mykola Pechenizkiy, Yi Liang, Michael Bendersky, Zhangyang Wang, Shiwei Liu.
  ICML 2024.

• SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality.
  Cheng-Yu Hsieh*, Jieyu Zhang*, Zixian Ma, Aniruddha Kembhavi, Ranjay Krishna.
  NeurIPS 2023.

• Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models.
  Cheng-Yu Hsieh, Si-An Chen, Chun-Liang Li, Yasuhisa Fujii, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister.
  Technical Report. 2023.

• Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes.
  Cheng-Yu Hsieh, Chun-Liang Li, Chih-Kuan Yeh, Hootan Nakhost, Yasuhisa Fujii, Alexander Ratner, Ranjay Krishna, Chen-Yu Lee, Tomas Pfister.
  ACL Findings 2023.

• Nemo: Guiding and Contextualizing Weak Supervision for Interactive Data Programming.
  Cheng-Yu Hsieh, Jieyu Zhang, and Alexander Ratner.
  VLDB 2023.

• A Survey on Programmatic Weak Supervision.
  Jieyu Zhang*, Cheng-Yu Hsieh*, Yue Yu*, Chao Zhang, and Alexander Ratner.
  Technical Report. 2022.

• Understanding Programmatic Weak Supervision via Source-aware Influence Function.
  Jieyu Zhang*, Haonan Wang*, Cheng-Yu Hsieh, and Alexander Ratner.
  NeurIPS 2022.

• Evaluations and Methods for Explanation through Robustness Analysis.
  Cheng-Yu Hsieh, Chih-Kuan Yeh, Xuanqing Liu, Pradeep Ravikumar, Seungyeon Kim, Sanjiv Kumar, and Cho-Jui Hsieh.
  ICLR 2021.

• On the (In)fidelity and Sensitivity of Explanations.
  Chih-Kuan Yeh, Cheng-Yu Hsieh, Arun Sai Suggala, David Inouye, and Pradeep Ravikumar.
  NeurIPS 2019.

• A Pseudo- Label Method for Coarse-to-Fine Multi-Label Learning with Limited Supervision.
  Cheng-Yu Hsieh, Miao Xu, Gang Niu, Hsuan-Tien Lin, and Masashi Sugiyama.
  Learning from Limited Labeled Data @ ICLR 2019.

• A Deep Model with Local Surrogate Loss for General Cost-sensitive Multi-label Learning.
  Cheng-Yu Hsieh, Yi-An Lin, and Hsuan-Tien Lin.
  AAAI 2018.

• Automatic Bridge Bidding using Deep Reinforcement Learning.
  Chih-Kuan Yeh, Cheng-Yu Hsieh, and Hsuan-Tien Lin.
  IEEE Transactions on Games 2018.

Professional Experience

Research Intern, Apple Machine Learning Research
Mentor: Hadi Pouransari and Pavan Kumar Anasosalu Vasu
Spring 2024 - Present

Student Researcher, Google Cloud AI Research
Mentor: Chen-Yu Lee and Chun-Liang Li
Summer 2022 - Winter 2024

Research Intern, RIKEN AIP
Mentor: Masashi Sugiyama
April 2018 - July 2018