Publications (* indicates equal contribution)

• Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer
  Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, Devi Parikh
  To appear in the European Conference on Computer Vision (ECCV), 2022
  [Code] [Video] [Project Page]


• MUGEN: A Playground for Video-Audio-Text Multimodal Understanding and GENeration
  Thomas Hayes, Songyang Zhang, Xi Yin, Guan Pang, Sasha Sheng, Harry Yang, Songwei Ge, Isabelle Hu, Devi Parikh
  To appear in the European Conference on Computer Vision (ECCV), 2022
  [Code] [Dataset] [Project Page]


• Robust Contrastive Learning Using Negative Samples with Diminished Semantics
  Songwei Ge, Shlok Mishra, Haohan Wang, Chun-Liang Li, David Jacobs
  In the Thirty-fifth Annual Conference on Neural Information Processing Systems (NeurIPS), 2021
  [Code and Dataset]


• Shift Invariance Can Reduce Adversarial Robustness
  Songwei Ge*, Vasu Singla*, Ronen Basri, David Jacobs
  In the ICLR Workshop on Security and Safety in Machine Learning Systems, 2021
  In the Thirty-fifth Annual Conference on Neural Information Processing Systems (NeurIPS), 2021
  [Code]


• Visual Conceptual Blending with Large-scale Language and Vision Models
  Songwei Ge and Devi Parikh
  In the International Conference on Computational Creativity (ICCC), 2021 (oral)
  


• Creative Sketch Generation
  Songwei Ge, Vedanuj Goswami, Larry Zitnick, Devi Parikh
  In the NeurIPS Workshop on Machine Learning for Creativity and Design, 2020 (oral)
  In the International Conference on Learning Representations (ICLR), 2021
  [Demo] [Code] [Dataset] [Project Page]


• Supervised Adversarial Alignment of Single-Cell RNA-seq Data
  Songwei Ge, Haohan Wang, Amir Alavi, Eric Xing, Ziv Bar-Joseph
  In 24th International Conference on Research in Computational Molecular Biology (RECOMB), 2020
  [Code]


• Learning Robust Global Representations by Penalizing Local Predictive Power
  Haohan Wang, Songwei Ge, Eric P. Xing, Zachary C. Lipton
  In Thirty-third Conference on Neural Information Processing Systems (NeurIPS), 2019
  [Code] [Dataset]


• From Text to Sound: a Preliminary Study on Retrieving Sound Effects to Radio Stories
  Songwei Ge, Curtis Xuan, Ruihua Song, Chao Zou, Wei Liu, Jin Zhou
  In ACM International Conference on Research and Development in Information Retrieval (SIGIR), 2019


• Developing Creative AI to Generate Sculptural Objects for Interactive Art Installation
  Songwei Ge*, Austin Dill*, Eunsu Kang, Chun-Liang Li, Manzil Zaheer, Barnabas Poczos
  In NeurIPS Workshop on Machine Learning for Creativity and Design, 2018
  In Inter-Society for the Electronic Arts (ISEA), 2019


• A computational strategy for finding novel targets and therapeutic compounds for opioid dependence
  Xiaojun Wu, Siwei Xie, Lirong Wang, Peihao Fan, Songwei Ge, Xiang-Qun Xie, Wei Wu
  In PLoS One, 2018


• Personalizing Search Results Using Hierarchical RNN with Query-aware Attention
  Songwei Ge, Zhicheng Dou, Zhengbao Jiang, Jian-Yun Nie, Ji-Rong Wen
  In ACM International Conference on Information and Knowledge Management (CIKM), 2018