Education

Selected Awards

IBM Ph.D. Fellowship, 2018

Best student paper runner-up, International Joint Conference on Artificial Intelligence (IJCAI), 2017

First Places, Track 1 and Track 2 of KDD Cup 2013

First Places, Track 1 and Track 2 of KDD Cup 2011

Publications (* denotes equal contribution)

• 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
  In Advances in Neural Information Processing Systems (NeurIPS), 2024
• Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
  Hadi Pouransari, Chun-Liang Li, Jen-Hao Rick Chang, Pavan Kumar Anasosalu Vasu, Cem Koc, Vaishaal Shankar, Oncel Tuzel
  In Advances in Neural Information Processing Systems (NeurIPS), 2024
• MUSCLE: A Model Update Strategy for Compatible LLM Evolution
  Jessica Echterhoff, Fartash Faghri, Raviteja Vemulapalli, Ting-Yao Hu, Chun-Liang Li, Oncel Tuzel, Hadi Pouransari
  In Empirical Methods in Natural Language Processing (EMNLP), 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 T. Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister
  In Annual Meeting of the Association for Computational Linguistics (ACL), 2024
• CodecLM: Aligning Language Models with Tailored Synthetic Data
  Zifeng Wang, Chun-Liang Li, Vincent Perot, Long T. Le, Jin Miao, Zizhao Zhang, Chen-Yu Lee, Tomas Pfister
  In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2024
• Chain-of-table: Evolving tables in the reasoning chain for table understanding
  Zilong Wang, Hao Zhang, Chun-Liang Li, Julian Martin Eisenschlos, Vincent Perot, Zifeng Wang, Lesly Miculicich, Yasuhisa Fujii, Jingbo Shang, Chen-Yu Lee, Tomas Pfister
  In International Conference on Learning Representations (ICLR), 2024
• 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 and Tomas Pfister
  In Annual Meeting of the Association for Computational Linguistics (ACL), 2023 (Google ACL 2023 Spotlight) [code]
• FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
  Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolai Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua and Tomas Pfister
  In Annual Meeting of the Association for Computational Linguistics (ACL), 2023
• Pic2word: Mapping pictures to words for zero-shot composed image retrieval
  Kuniaki Saito, Kihyuk Sohn, Xiang Zhang, Chun-Liang Li, Chen-Yu Lee, Kate Saenko and Tomas Pfister
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [code]
• Prefix conditioning unifies language and label supervision
  Kuniaki Saito, Kihyuk Sohn, Xiang Zhang, Chun-Liang Li, Chen-Yu Lee, Kate Saenko and Tomas Pfister
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023
• Hyperbolic contrastive learning for visual representations beyond objects
  Songwei Ge, Shlok Mishra, Simon Kornblith, Chun-Liang Li and David Jacobs
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 [code]
• Learning Instance-Specific Adaptation for Cross-Domain Segmentation
  Yuliang Zou, Zizhao Zhang, Chun-Liang Li, Han Zhang, Tomas Pfister and Jia-Bin Huang
  In European Conference on Computer Vision (ECCV), 2022 [code]
• FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
  Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii and Tomas Pfister
  In Annual Meeting of the Association for Computational Linguistics (ACL), 2022 [blog]
• Decoupling Local and Global Representations of Time Series
  Sana Tonekaboni, Chun-Liang Li, Sercan Arik, Anna Goldenberg and Tomas Pfister
  In International Conference on Artificial Intelligence and Statistic (AISTATS), 2022 [code]
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
  Asma Ghandeharioun, Been Kim, Chun-Liang Li, Brendan Jou, Brian Eoff, and Rosalind W. Picard
  In International Conference on Learning Representations (ICLR), 2022 [code]
• A Unified View of cGANs with and without Classifiers
  Si-An Chen, Chun-Liang Li and Hsuan-Tien Lin
  In Advances in Neural Information Processing Systems (NeurIPS), 2021 [code]
• Robust Contrastive Learning Using Negative Samples with Diminished Semantics
  Songwei Ge, Shlok Mishra, Haohan Wang, Chun-Liang Li and David Jacobs
  In Advances in Neural Information Processing Systems (NeurIPS), 2021 [code]
• Object-aware Contrastive Learning for Debiased Scene Representation
  Sangwoo Mo, Hyunwoo Kang, Kihyuk Sohn, Chun-Liang Li and Jinwoo Shin
  In Advances in Neural Information Processing Systems (NeurIPS), 2021 [code]
• ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
  Chen-Yu Lee, Chun-Liang Li, Chu Wang, Renshen Wang, Yasuhisa Fujii, Siyang Qin, Ashok Popat and Tomas Pfister
  In Annual Meeting of the Association for Computational Linguistics (ACL), 2021 (Oral)
• Unsupervised Program Synthesis for Images using Tree-Structured LSTM
  Chenghui Zou, Chun-Liang Li and Barnabás Póczos
  In Uncertainty in Artificial Intelligence (UAI), 2021
• Deep Generative Models for Galaxy Image Simulations
  François Lanusse, Rachel Mandelbaum, Siamak Ravanbakhsh, Chun-Liang Li, Peter Freeman and Barnabás Póczos
  In Monthly Notices of the Royal Astronomical Society (MNRAS), 2021. [code]
• CutPaste: Self-Supervised Learning for Anomaly Detection and Localization
  Chun-Liang Li*, Kihyuk Sohn*, Jinsung Yoon, and Tomas Pfister
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [blog]
• Learning and Evaluating Representations for Deep One-class Classification
  Kihyuk Sohn*, Chun-Liang Li*, Jinsung Yoon, Minho Jin, and Tomas Pfister
  In International Conference on Learning Representations (ICLR), 2021 [code]
• PseudoSeg: Designing Pseudo Labels for Semantic Segmentation
  Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, and Tomas Pfister
  In International Conference on Learning Representations (ICLR), 2021 [code]
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
  Kibok Lee, Yian Zhu, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin, and Honglak Lee
  In International Conference on Learning Representations (ICLR), 2021 [code]
• Interpretable Sequence Learning for Covid-19 Forecasting
  Sercan Arik, Chun-Liang Li, Jinsung Yoon, Rajarishi Sinha, Arkady Epshteyn, Long Le, Vikas Menon, Shashank Singh, Leyou Zhang, Nate Yoder, Martin Nikoltchev, Yash Sonthalia, Hootan Nakhost, Elli Kanal and Tomas Pfister
  In Advances in Neural Information Processing Systems (NeurIPS), 2020 (Spotlight)
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
  Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang and Colin Raffel
  In Advances in Neural Information Processing Systems (NeurIPS), 2020
• On Completeness-aware Concept-Based Explanations in Deep Neural Networks
  Chih-Kuan Yeh, Been Kim, Sercan Arik, Chun-Liang Li, Tomas Pfister and Pradeep Ravikumar
  In Advances in Neural Information Processing Systems (NeurIPS), 2020
• Learning Generative Models using Transformations
  Chun-Liang Li
  PhD Thesis, Carnegie Mellon University, 2019
• LBS Autoencoder: Self-supervised Fitting of Articulated Meshes to Point Clouds
  Chun-Liang Li, Tomas Simon, Jason Saragih, Barnabás Póczos and Yaser Sheikh
  In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [video]
• Implicit Kernel Learning
  Chun-Liang Li, Wei-Chen Chang, Youssef Mroueh, Yiming Yang and Barnabás Póczos
  In International Conference on Artificial Intelligence and Statistic (AISTATS), 2019
• Kernel Change-Point Detection with Auxiliary Deep Generative Models
  Wei-Chen Chang, Chun-Liang Li, Yiming Yang and Barnabás Póczos
  In International Conference on Learning Representations (ICLR), 2019 [code]
• Beyond Pixel Norm-Balls: Parametric Adversaries using an Analytically Differentiable Renderer
  Hsueh-Ti Liu, Michael Tao, Chun-Liang Li, Derek Nowrouzezahrai and Alec Jacobson
  In International Conference on Learning Representations (ICLR), 2019
• Point Cloud GAN
  Chun-Liang Li, Manzil Zaheer, Yang Zhang, Barnabás Póczos and Ruslan Salakhutdinov
  In ICLR Workshop on Deep Generative Models for Highly Structured Data, 2019 [code]
• Nonparametric Density Estimation with Adversarial Losses
  Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer and Barnabás Póczos
  In Advances in Neural Information Processing Systems (NIPS), 2018
• Classifier Two-Sample Test for Video Anomaly Detections
  Yusha Liu*, Chun-Liang Li*, and Barnabás Póczos
  In British Machine Vision Conference (BMVC), 2018 [code]
• Sobolev GAN
  Youssef Mroueh, Chun-Liang Li*, Tom Sercu*, Anant Raj*, and Yu Cheng
  In International Conference on Learning Representations (ICLR), 2018 [code]
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
  Francois Lanusse, Quanbin Ma, Nan Li, Thomas E. Collett, Chun-Liang Li, Siamak Ravanbakhsh, Rachel Mandelbaum and Barnabás Póczos
  In Monthly Notices of the Royal Astronomical Society (MNRAS), 2018. [code]
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
  Chun-Liang Li*, Wei-Chen Chang*, Yu Cheng, Yiming Yang and Barnabás Póczos
  In Advances in Neural Information Processing Systems (NIPS), 2017 [code]
• One Network to Solve Them All — Solving Linear Inverse Problems using Deep Projection Models
  J. H. Rick Chang, Chun-Liang Li, Barnabás Póczos, B. V. K. Vijaya Kumar and Aswin C. Sankaranarayanan
  In International Conference on Computer Vision (ICCV), 2017 (Oral) [code]
• Data-driven Random Fourier Feature using Stein Effect
  Wei-Chen Chang, Chun-Liang Li, Yiming Yang and Barnabás Póczos
  In International Joint Conference on Artificial Intelligence (IJCAI), 2017
  (Best student paper runner-up)
• Polynomial Optimization Methods for Matrix Factorization
  Po-Wei Wang, Chun-Liang Li, and J. Zico Kolter
  In AAAI Conference on Artificial Intelligence (AAAI), 2017
• Utilize Old Coordinates: Faster Doubly Stochastic Gradients for Kernel Methods
  Chun-Liang Li and Barnabás Póczos
  In Uncertainty in Artificial Intelligence (UAI), 2016
• High Dimensional Bayesian Optimization via Restricted Projection Pursuit Models
  Chun-Liang Li, Kirthevasan Kandasamy, Barnabás Póczos and Jeff Schneider
  In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
• Rivalry of Two Families of Algorithms for Memory-Restricted Streaming PCA
  Chun-Liang Li, Hsuan-Tien Lin and Chi-Jen Lu
  In International Conference on Artificial Intelligence and Statistics (AISTATS), 2016
• Active Learning with Hint Information
  Chun-Liang Li, Chun-Sung Ferng, and Hsuan-Tien Lin
  In Neural Computation, 2015
• Condensed Filter Tree for Cost-Sensitive Multi-Label Classification
  Chun-Liang Li and Hsuan-Tien Lin
  In International Conference on Machine Learning (ICML), 2014 [slide]
• Active Learning with Hinted Support Vector Machine
  Chun-Liang Li, Chun-Sung Ferng, and Hsuan-Tien Lin
  In Asian Conference on Machine Learning (ACML), 2012 [slide]