Publications

• Regularized Langevin Dynamics for Combinatorial Optimization [pdf]
  • Shengyu Feng, Yiming Yang
  • Under Review
• Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo [pdf]
  • Shengyu Feng, Xiang Kong, Shuang Ma, Aonan Zhang, Dong Yin, Chong Wang, Ruoming Pang and Yiming Yang
  • International Conference on Learning Representations (ICLR), 2025
• Sampling-Enhanced Large Neighborhood Search for Solving Integer Linear Programs
  • Shengyu Feng, Zhiqing Sun and Yiminig Yang
  • Under Review
• SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch [pdf]
  • Shengyu Feng, Yiming Yang
  • Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
• ARIEL: Adversarial Graph Contrastive Learning [pdf]
  • Shengyu Feng, Baoyu Jing, Yada Zhu and Hanghang Tong
  • TKDD
• Concept Discovery for Fast Adaptation [pdf]
  • Shengyu Feng, Hanghang Tong
  • SIAM International Conference on Data Mining (SDM), 2023
• Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs [pdf]
  • Shengyu Feng, Subarna Tripathi, Hesham Mostafa, Marcel Nassar and Somdeb Majumdar
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023
• X-GOAL: Multiplex Graph Prototypical Contrastive Learning [pdf]
  • Baoyu Jing, Shengyu Feng, Yuejia Xiang, Xi Chen, Yu Chen and Hanghang Tong
  • ACM International Conference on Information and Knowledge Management (CIKM), 2022
• Adversarial Graph Contrastive Learning with Information Regularization [pdf]
  • Shengyu Feng, Baoyu Jing, Yada Zhu and Hanghang Tong
  • ACM Web Conference (WWW), 2022
• Coreference by appearance: Visually Grounded Event Coreference Resolution [pdf]
  • Liming Wang, Shengyu Feng, Xudong Lin, Manling Li, Shih-Fu Chang and Heng Ji
  • EMNLP 2021 Workshop on Computational Models of Reference, Anaphora and Coreference (CRAC), 2021
• Batch Reinforcement Learning through Continuation Method [pdf]
  • Yijie Guo, Shengyu Feng, Nicolas Le Roux, Ed Chi, Honglak Lee and Minmin Chen
  • International Conference on Learning Representations (ICLR), 2021
• Memory Based Trajectory-conditioned Policies for Learning from Sparse Rewards [pdf]
  • Yijie Guo, Jongwook Choi, Marcin Moczulski, Shengyu Feng, Samy Bengio, Mohammad Norouzi and Honglak Lee
  • Neural Information Processing Systems (NeurIPS) 2020