See my Google Scholar Page or Microsoft Homepage​ for the most updated list of publications.
   * : equal contribution, **: alphabetical order

1.  Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles. 
   Shuquan Ye, Yujia Xie, Dongdong Chen, Yichong Xu, Lu Yuan, Chenguang Zhu, Jing Liao. To appear at CVPR 2023. Highlight Paper (10% of accepted papers, 2.5% of submissions).
   Document: [arXiv]

2. APOLLO: A Simple Approach for Adaptive Pretraining of Language Models for Logical Reasoning
   Soumya Sanyal, Yichong Xu, Shuohang Wang, Ziyi Yang, Reid Pryzant, Wenhao Yu, Chenguang Zhu, Xiang Ren. arXiv preprint: arXiv 2212.09282, 2022.
   Document: [arXiv]

3. Generate rather than Retrieve: Large Language Models are Strong Context Generators. 
   Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, Meng Jiang. To appear at ICLR 2023.
   Document: [arXiv]

4. i-Code: An Integrative and Composable Multimodal Learning Framework
   Ziyi Yang, Yuwei Fang, Chenguang Zhu, Reid Pryzant, Dongdong Chen, Yu Shi, Yichong Xu, Yao Qian, Mei Gao, Yi-Ling Chen, Liyang Lu, Yujia Xie, Robert Gmyr, Noel Codella, Naoyuki Kanda, Bin Xiao, Yuan Lu, Takuya Yoshioka, Michael Zeng, Xuedong Huang. AAAI 2023.
   Document: [arXiv]

5. Empowering Language Models with Knowledge Graph Reasoning for Open-Domain Question Answering
   Ziniu Hu, Yichong Xu, Wenhao Yu, Shuohang Wang, Ziyi Yang, Chenguang Zhu, Kai-Wei Chang, Yizhou Sun. EMNLP 2022. Best Paper Award at SoCal NLP Symposium 2022.
   ​Document: [arXiv]

6. Automatic Rule Induction for Efficient Semi-Supervised Learning
   Reid Pryzant, Ziyi Yang, Yichong Xu, Chenguang Zhu, Michael Zeng. EMNLP 2022.
   Document: [arXiv]

7. Task Compass: Scaling Multi-task Pre-training with Task Prefix
   Zhuosheng Zhang, Shuohang Wang, Yichong Xu, Yuwei Fang, Wenhao Yu, Yang Liu, Hai Zhao, Chenguang Zhu, Michael Zeng. Findings of EMNLP 2022.
   Document: [arXiv]

8. Unsupervised Summarization with Customized Granularities
   Ming Zhong, Yang Liu, Suyu Ge, Yuning Mao, Yizhu Jiao, Xingxing Zhang, Yichong Xu, Chenguang Zhu, Michael Zeng, Jiawei Han. Findings of EMNLP 2022.
   Document: [arXiv]

9. REVIVE: Regional Visual Representation Matters in Knowledge-Based Visual Question Answering
   Yuanze Lin, Yujia Xie, Dongdong Chen, Yichong Xu, Chenguang Zhu, Lu Yuan. NeurIPS 2022.
   Document: [arXiv]

10. Integrating Rankings into Quantized Scores in Peer Review
    Yusha Liu, Yichong Xu, Nihar B. Shah, Aarti Singh. Transactions on Machine Learning Research (TMLR).
    Short version in Workshop on ML Evaluation Standards at ICLR 2022. Outstanding + People's Choice Award.
    Document: [arXiv]

11. Human Parity on CommonsenseQA: Augmenting Self-Attention with External Attention
    Yichong Xu, Chenguang Zhu, Shuohang Wang, Siqi Sun, Hao Cheng, Xiaodong Liu, Jianfeng Gao, Pengcheng He, Michael Zeng, Xuedong Huang. IJCAI 2022. Long oral.
    Document: [arXiv][Blog][video][code]

12. An Empirical Study of Training End-to-End Vision-and-Language Transformers
    Zi-Yi Dou, Yichong Xu, Zhe Gan, Jianfeng Wang, Shuohang Wang, Lijuan Wang, Chenguang Zhu, Nanyun (Violet) Peng, Zicheng Liu and Michael Zeng. CVPR 2022.
    Document: [arXiv]

13. Training Data is More Valuable than You Think: A Simple and Effective Method by Retrieving from Training Data
    Shuohang Wang, Yichong Xu, Yuwei Fang, Yang Liu, Siqi Sun, Ruochen Xu, Chenguang Zhu, Michael Zeng. ACL 2022 (Main conference).
    Document: [arXiv]

14. Leveraging Knowledge in Multilingual Commonsense Reasoning
    Yuwei Fang, Shuohang Wang, Yichong Xu, Ruochen Xu, Siqi Sun, Chenguang Zhu, Michael Zeng. Findings of ACL 2022.
    Document: [arXiv]

15. DICT-BERT: Enhancing Language Model Pre-Training with Dictionary
    Wenhao Yu, Chenguang Zhu, Yuwei Fang, Donghan Yu, Shuohang Wang, Yichong Xu, Michael Zeng, Meng Jiang. Findings of ACL 2022.
    Document: [arXiv]

16. KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering
    Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng. ACL 2022 (Main conference).
    Document: [arXiv]

17. DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization
    Ming Zhong, Yang Liu, Yichong Xu, Chenguang Zhu and Michael Zeng. AAAI 2022.
    Document: [arXiv]

18. Want To Reduce Labeling Cost? GPT-3 Can Help
    Shuohang Wang, Yang Liu, Yichong Xu, Chenguang Zhu and Michael Zeng. Findings of EMNLP 2021.
    Document: [arXiv]

19. Fusing Context Into Knowledge Graph for Commonsense Reasoning
    Yichong Xu∗ , Chenguang Zhu∗ , Ruochen Xu, Yang Liu, Michael Zeng and Xuedong Huang. Findings of ACL 2021.
    Document: [arXiv][code]

20. Retrieval Enhanced Model for Commonsense Generation
    Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu and Michael Zeng. Findings of ACL 2021.
    Document: [arXiv][code]

21. Preference-based Reinforcement Learning with Finite-Time Guarantees.
    Yichong Xu, Ruosong Wang, Lin F. Yang, Aarti Singh and Artur Dubrawski. Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS 2020). Spotlight presentation.
    ​Document: [link][arXiv]

22. Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
    Yichong Xu, Sivaraman Balakrishnan, Aarti Singh, Artur Dubrawski. Journal of Machine Learning Research (JMLR), 2020. Short version in ICML2018 and Asilomar2018.
    Document: [link][arXiv][data]

23. Learning and Decision Making from Diverse Forms of Information
    Yichong Xu
    PhD thesis, Machine Learning Department, Carnegie Mellon University.
    Document: [pdf]

24. Zeroth Order Non-convex optimization with Dueling-Choice Bandits
    Yichong Xu, Aparna Joshi, Aarti Singh and Artur Dubrawski. The Conference on Uncertainty in Artificial Intelligence (UAI 2020).
    Document: [link][arXiv]

25. Thresholding Bandit Problem with both Duels and Pulls.
    Yichong Xu, Xi Chen, Aarti Singh and Artur Dubrawski. The 23rd International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
    Document: [link][arXiv]

26. Active Learning for Graph Neural Networks via Node Feature Propagation.
    Yuexin Wu∗, Yichong Xu∗, Aarti Singh, Yiming Yang and Artur Dubrawski. arXiv preprint arXiv:1910.07567, 2019. Short version in NeurIPS2019 Graph Representation Learning Workshop (GRL).
    ​Document: [arXiv][code]

27. DoubleTransfer at MEDIQA 2019: Multi-Source Transfer Learning for Natural Language Understanding in the Medical Domain
    Yichong Xu, Xiaodong Liu, Chunyuan Li, Hoifung Poon, Jianfeng Gao. The BioNLP workshop, ACL 2019. #1st place on Medical QA Task.
    ​Document: [arXiv][code]

28. On Strategyproof Conference Peer Review
    Yichong Xu*, Han Zhao*, Xiaofei Shi and Nihar B. Shah. 28th International Joint Conference on Artificial Intelligence (IJCAI 2019).
    Document: [link][supplement][arXiv][code and data]

29. Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension
    Yichong Xu, Xiaodong Liu, Yelong Shen, Jingjing Liu and Jianfeng Gao. North American Chapter of the Association for Computational Linguistics (NAACL2019). Long Oral.
    Document: [link][arXiv][code] 

30. Interactive Linear Regression with Pairwise Comparisons
    Yichong Xu, Sivaraman Balakrishnan, Aarti Singh and Artur Dubrawski. Asilomar Conference on Signals, Systems and Computers 2018, invited paper.
    Document: [link][pdf]

31. Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
    Yichong Xu, Hariank Muthakana, Sivaraman Balakrishnan, Aarti Singh and Artur Dubrawski. 35th International Conference on Machine Learning (ICML 2018). Long Oral.
    Document: [link][arXiv][poster][slides]

32. Dynamic Fusion Networks for Machine Reading Comprehension
    Yichong Xu, Jingjing Liu, Jianfeng Gao, Yelong Shen and Xiaodong Liu. arXiv preprint arXiv:1711.04964, 2017
    Document: [arXiv]

33. Noise-Tolerant Interactive Learning Using Pairwise Comparisons
    Yichong Xu, Hongyang Zhang, Kyle Miller, Aarti Singh, Artur Dubrawski. The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS2017).
    Document: [link][arXiv][video][poster]

34. Computational issues in time-inconsistent planning
    Pingzhong Tang**, Yifeng Teng**, Zihe Wang**, Shenke Xiao**, Yichong Xu**. AAAI-2017. Oral Presentation.
    Document: [link][arXiv]

35. Novel Quantization Strategies for Linear Prediction with Guarantees
    Simon Du*, Yichong Xu*, Hongyang Zhang, Christy Li, Aarti Singh and Pulkit Grover. ICML 2016 Workshop on On-Device Intelligence.
    Document: [pdf]

36. The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification
    Tianjun Xiao, Yichong Xu, Kuiyuan Yang, Jiaxing Zhang and Zheng Zhang. IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2015)
    Document: [link][arXiv] [Supplementary Material]

37. Scale-Invariant Convolutional Neural Network
    Yichong Xu, Tianjun Xiao, Jiaxing Zhang, Kuiyuan Yang and Zheng Zhang. arXiv preprint arXiv:1411.6369,2014
    Document: [arXiv] [Supplementary Material]