Yangyang Guo

alt text

Yangyang Guo (郭洋洋)
Senior Research Fellow
School of Computing
National University of Singapore
Contact: Email, Google Scholar, Github

Short Bio

I'm currently a senior research fellow with the National University of Singapore.
I obtained my Doctor's Degree in the School of Computer Science and Technology,
Shandong University, supervised by Prof. Liqiang Nie, co-mentored by Prof. Zhiyong Cheng from Hefei University of Technology.
My research interests lie in the bias problem, robustness, and efficiency of AI systems.

Experiences

National University of Singapore, Oct. 2024 - Now

  • Senior Research Fellow, School of Computing
  • Advisor: Prof. Mohan Kankanhalli

National University of Singapore, Aug. 2021 - Sep. 2024

  • Research Fellow, School of Computing
  • Advisor: Prof. Mohan Kankanhalli

Shandong University, Sep. 2016 - Jun. 2021

  • PhD Student, Computer Science and Technology
  • Advisor: Prof. Liqiang Nie; Co-Mentor: Prof. Zhiyong Cheng

Alibaba Group, Dec. 2020 - Apr. 2021

  • Research Intern

National University of Singapore, Oct. 2017 - Sep. 2018

  • Research Intern, School of Computing
  • Advisor: Prof. Mohan Kankanhalli

Selected Publications (Google Scholar)

  • UNK-VQA: A Dataset and a Probe into the Abstention Ability of Multi-modal Large Models.
    Yangyang Guo, Fangkai Jiao, Zhiqi Shen, Liqiang Nie, Mohan Kankanhalli.
    IEEE TPAMI, 2024. [CCF A]. (Paper && Code)

  • Diffusion Facial Forgery Detection.
    Harry Cheng, Yangyang Guo*, Tianyi Wang, Liqiang Nie*, Mohan Kankanhalli.
    ACM MM, 2024. (Full Paper, acceptance rate: 26.2%) [CCF A]. (Paper && Code)

  • PELA: Learning Parameter-Efficient Models with Low-Rank Approximation.
    Yangyang Guo, Guangzhi Wang, Mohan Kankanhalli.
    CVPR, 2024. (Full Paper, acceptance rate: 23.6%) [CCF A]. (Paper && Code)

  • Bilateral Adaptation for Human-Object Interaction Detection with Occlusion-Robustness.
    Guangzhi Wang, Yangyang Guo, Ziwei Xu, Mohan Kankanhalli.
    CVPR, 2024. (Full Paper, acceptance rate: 23.6%) [CCF A]. (Paper && Code)

  • Voice-face Homogeneity Tells Deepfake.
    Harry Cheng, Yangyang Guo*, Tianyi Wang, Qi Li, Xiaojun Chang, Liqiang Nie*.
    ACM ToMM, 2024. [CCF B]. (Paper && Code)

  • Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration.
    Harry Cheng, Yangyang Guo*, Liqiang Nie*, Zhiyong Cheng, Mohan Kankanhalli.
    ACM MM, 2023. (Full Paper, acceptance rate: 29.3%). [CCF A]. (Paper && Code)

  • Do Vision-Language Transformers Exhibit Visual Commonsense? An Empirical Study of VCR.
    Zhenyang Li, Yangyang Guo, Kejie Wang, Xiaolin Chen, Liqiang Nie, Mohan Kankanhalli.
    ACM MM, 2023. (Full Paper, acceptance rate: 29.3%). [CCF A]. (Paper)

  • On Modality Bias Recognition and Reduction.
    Yangyang Guo, Liqiang Nie, Harry Cheng, Zhiyong Cheng, Mohan Kankanhalli, Alberto Del Bimbo.
    ACM ToMM, 2023. [CCF B] (Paper && Code)

  • Joint Answering and Explanation for Visual Commonsense Reasoning.
    Zhenyang Li, Yangyang Guo*, Kejie Wang, Yinwei Wei, Liqiang Nie*, Mohan Kankanhalli.
    IEEE TIP, 2023. [CCF A] (Paper && Code)

  • Learning to Agree on Vision Attention for Visual Commonsense Reasoning.
    Zhenyang Li, Yangyang Guo*, Kejie Wang, Fan Liu, Liqiang Nie*, Mohan Kankanhalli.
    IEEE TMM, 2023. [CCF B] (Paper && Code)

  • Enhanced Multi-domain Dialogue State Tracker with Second-order Slot Interactions.
    Fangkai Jiao, Yangyang Guo*, Minlie Huang, Liqiang Nie*.
    IEEE TASL, 2022. [CCF B] (Paper && Code)

  • Chairs Can be Stood on: Overcoming Object Bias in Human-Object Interaction Detection.
    Guangzhi Wang, Yangyang Guo*, Yongkang Wong, Mohan Kankanhalli.
    ECCV, 2022. (Full Paper, acceptance rate: 28.4%). [CCF B] (Paper && Code)

  • Compute to Tell the Tale: Goal-Driven Narrative Generation.
    Yongkang Wong, Shaojing Fan, Yangyang Guo, Ziwei Xu, Karen Stephen, Rishabh Sheoran, Anusha Bhamidipati, Vivek Barsopia, Jianquan Liu, Mohan Kankanhalli.
    ACM MM BNI (Best BNI Award), 2022, [CCF A]. (Paper)

  • A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA.
    Yangyang Guo, Liqiang Nie, Yongkang Wong, Yibing Liu, Zhiyong Cheng, Mohan Kankanhalli.
    ACM MM, 2022. (Full Paper, acceptance rate: 27.9%). [CCF A] (Paper && Code)

  • Distance Matters in Human-Object Interaction Detection.
    Guangzhi Wang, Yangyang Guo*, Yongkang Wong, Mohan Kankanhalli.
    ACM MM, 2022. (Full Paper, acceptance rate: 27.9%). [CCF A] (Paper && Code)

  • Rethinking Attention-Model Explainability through Faithfulness Violation Test.
    Yibing Liu, Haoliang Li, Yangyang Guo, Chenqi Kong, Jing Li, Shiqi Wang.
    ICML, 2022. (Full Paper, acceptance rate: 21.9%). [CCF A (Spotlight)] (Paper && Code)

  • MERIt: Meta-Path Guided Contrastive Learning for Logical Reasoning.
    Fangkai Jiao, Yangyang Guo*, Xuemeng Song, Liqiang Nie*.
    ACL, 2022. (Findings, Full Paper). [CCF A] (Paper && Code)

  • Answer Questions with Right Image Regions: A Visual Attention Regularization Approach.
    Yibing Liu, Yangyang Guo, Jianhua Yin, Xuemeng Song, Weifeng Liu, Liqiang Nie, Min Zhang.
    ACM ToMM, 2022. [CCF B] (Paper && Code)

  • Loss Re-scaling VQA: Revisiting the Language Prior Problem from a Class-imbalance View.
    Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Qi Tian, Min Zhang.
    IEEE TIP, 2021. [CCF A] (Paper && Code)

  • Audio-driven Talking Video Frame Restoration.
    Harry Cheng, Yangyang Guo, Jianhua Yin, Haonan Chen, Jiafang Wang, Liqiang Nie.
    IEEE TMM, 2021. [CCF B] (Paper)

  • REPT: Bridging Language Models and Machine Reading Comprehension via Retrieval-Based Pre-training.
    Fangkai Jiao, Yangyang Guo, Yilin Niu, Feng Ji, Feng-Lin Li, Liqiang Nie.
    ACL, 2021. (Findings, Full Paper, acceptance rate: 39.1%). [CCF A] (Paper && Code)

  • AdaVQA: Overcoming Language Priors with Adapted Margin Cosine Loss.
    Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto Del Bimbo.
    IJCAI, 2021. (Full Paper, acceptance rate: 13.9%). [CCF A] (Paper && Code)

  • Quantifying and Alleviating the Language Prior Problem in Visual Question Answering.
    Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Yibing Liu, Yinglong Wang and Mohan Kankanhalli.
    ACM SIGIR, 2019. (Full Paper, acceptance rate: 20%). [CCF A] (Paper && Code)

  • Enhancing Factorization Machines with Generalized Metric Learning.
    Yangyang Guo, Zhiyong Cheng, Jiazheng Jing, Yanpeng Lin, Liqiang Nie, Meng Wang.
    IEEE TKDE, 2020. [CCF A] (Paper && Code)

  • Attentive Long Short-Term Preference Modeling for Personalized Product Search.
    Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Yinglong Wang, Jun Ma and Mohan Kankanhalli.
    ACM TOIS, 2019. [CCF A] (Paper && Code)

  • Multi-modal Preference Modeling for Product Search.
    Yangyang Guo, Zhiyong Cheng, Liqiang Nie, Xin-Shun Xu and Mohan Kankanhalli.
    ACM MM, 2018. (Full Paper, acceptance rate: 27.5%). [CCF A] (Paper && Code)

Academic Services

Conference Reviewer

  • CVPR 2022-2025, ICCV 2023, ECCV 2022-2024
  • ACM MM 2020-2024, MM Asia 2020-2022
  • AAAI 2021-2025, IJCAI 2023-2024, ICML 2023-2024, NeurIPS 2023-2024, ICLR 2024-2025
  • KDD 2022, WSDM 2022-2023

Journal Reviewer

  • IEEE TIP, TIFS, TKDE, TMM, TCSVT
  • ACM ToMM, TOIS, TWEB

Honors

  • Champion of the ICML 2024 TiFA Workshop MLLM Attack Challenge (Team Leader - Yangyang Guo, Ziwei Xu, Xilie Xu, Yongkang Wong, Liqiang Nie, and Mohan Kankanhalli)
  • Outstanding PC Award for WSDM, 2022
  • Outstanding Reviewer Award for IEEE TMM, 2021
  • Shandong University President Scholarship, 2019
  • National Scholarship for Ph.D. students, 2019
  • ACM SIGIR Student Travel Grant, 2019
  • ACM MM Student Travel Grant, 2018