CV / Google Scholar / GitHub / Twitter / LinkedIn
I am a Master of Computing (AI Specialization) student at the National University of Singapore. I am interested in the intersection between self-supervised learning, world models and object-centric representations for robotics.
Previously, I held these positions:
- Researcher at the Agency for Science, Technology and Research (A*STAR), worked with Dr. Cheston Tan and Dr. Zhu Hongyuan.
- Researcher in the DeCLaRe Lab at the Singapore University of Technology and Design (SUTD), worked with Prof. Soujanya Poria.
- Computer science undergraduate student at SUTD, graduated with Honours with Distinction.
Research
2022
BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios
Jiafei Duan*, Samson Yu*, Nicholas Tan, Li Yi, Cheston Tan
arXiv preprint
paper / code
Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation
Jenny Zhang, Samson Yu, Jiafei Duan, Cheston Tan
arXiv preprint
paper
ABCDE: An Agent-Based Cognitive Development Environment
Jieyi Ye, Jiafei Duan, Samson Yu, Bihan Wen, Cheston Tan
IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) 2022, Embodied AI Workshop
paper
Single Image Video Prediction with Auto-Regressive GANs
Jiahui Huang, Yew Ken Chia, Samson Yu, Kevin Yee, Dennis Küster, Eva G. Krumhuber, Dorien Herremans, Gemma Roig
Sensors
paper
2021
PIP: Physical Interaction Prediction via Mental Simulation with Span Selection
Jiafei Duan*, Samson Yu*, Soujanya Poria, Bihan Wen, Cheston Tan
European Conference on Computer Vision (ECCV) 2022
paper
Aspect Sentiment Triplet Extraction using Reinforcement Learning
Samson Yu, Tapas Nayak, Navonil Majumder, Soujanya Poria
ACM International Conference on Information and Knowledge Management (CIKM) 2021
paper / code
SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments
Jiafei Duan, Samson Yu, Cheston Tan
IEEE International Conference on Computer Vision (ICCV) 2021, Simulation Technology for Embodied AI (SEAI) Workshop (Spotlight)
paper / code
A Survey Of Embodied AI: From Simulator To Research Tasks
Jiafei Duan, Samson Yu, Hui Li Tan, Hongyuan Zhu, Cheston Tan
IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI)
paper
2020
Recognizing Emotion Cause in Conversations
Soujanya Poria, Navonil Majumder, Devamanyu Hazarika, Deepanway Ghosal, Rishabh Bhardwaj, Samson Yu, Romila Ghosh, Niyati Chhaya, Alexander Gelbukh, Rada Mihalcea
Cognitive Computation 2021
paper / code
ActioNet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment
Jiafei Duan, Samson Yu, Hui Li Tan, Cheston Tan
IEEE International Conference for Image Processing (ICIP) 2020
paper / code / video
Concept Collection
In this section, I catalog interesting concepts/terms from research papers to help me remember them and spark ideas with lateral thinking. I also list their source(s) and a short summary of each concept. Feel free to reach out to me and let me know if I get any of them wrong.
- Reward learning (https://arxiv.org/abs/2212.04717)
- Social MDP (https://arxiv.org/abs/2110.10298)
- Reasoning about actions and change (https://arxiv.org/abs/2212.03866)
- Correspondence learning (learn a mapping between state, action pairs of agents of different dynamics or embodiments): https://arxiv.org/abs/2203.00904
- Rule hierarchy ()