|
Joey Tianyi Zhou (周天異)
I am acting Deputy Director, Principal Scientist II, and Investigator with the A*STAR Centre for Frontier AI Research (CFAR), Singapore. In CFAR, I am leading ZHOU Group focusing on fundamental AI research. Concurrently, I am holding a joint appointment as the Principal Scientist in the Centre for Advanced Technologies in Online Safety (CATOS).
In CATOS, I lead the "attack team" focused on generating Deepfake and AIGC Videos to fool human users and machine detectors (Please see some demos here). I am also an adjunct faculty member at the National University of Singapore (NUS).
I obtained my Ph.D. from Nanyang Technological University (NTU), SG, in 2015. I was a senior research engineer at Sony US Research Center, San Jose, USA.
A*STAR Email / NUS Email / People / NUS Teaching / Github / Google Scholar / |
|
ZHOU (Towards Zero-carbon, High-reliability, Open-environment, Unbiased AI) Research Group in CFAR
|
|
| Research |
|
Resource-efficient Learning |
|
|
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment |
|
|
Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification |
|
|
Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning |
|
|
Multisize Dataset Condensation |
|
|
Data-independent Module-aware Pruning for Hierarchical Vision Transformers |
|
|
You Only Condense Once: Two Rules for Pruning Condensed Datasets |
|
|
Sequential Subset Matching for Dataset Distillation |
|
|
Sharpness-aware training for free |
|
|
RCT: Resource Constrained Training for Edge AI |
|
|
Efficient Spiking Neural Networks with Radix Encoding |
|
|
EDCompress: Energy-Aware Model Compression for Dataflows |
|
|
Utility Optimal Thread Assignment and Resource Allocation in Multi-Server Systems |
|
|
Dual Adversarial Neural Transfer for Sequence Labeling |
|
|
Multi-source Meta Transfer for Low Resource Multiple Choice Question Answering |
|
|
A Deep Learning Framework for Hybrid Heterogeneous Transfer Learning |
|
|
Multi-class Heterogeneous Domain Adaptation |
|
|
Safe and Reliable AI |
|
|
Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning |
|
|
Meta Knowledge Condensation for Federated Learning |
|
|
Trusted Multi-View Classification with Dynamic Evidential Fusion |
|
|
XAI Beyond Classification: Interpretable Neural Clustering |
|
|
PointBA: Towards Backdoor Attacks in 3D Point Cloud |
|
|
Trusted Multi-View Classification |
|
|
Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributions |
|
|
Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment |
|
|
Query-efficient Meta Attack to Deep Neural Networks |
|
|
Others |
|
|
Difformer: Multi-resolutional differencing transformer with dynamic ranging for time series analysis |
|
|
Locality-Aware Crowd Counting |
|
|
Natural Language Video Localization: A Revisit in Span-based Question Answering Framework |
|
|
Ordered or Orderless: A Revisit for Video based Person Re-Identification |
|
|
AnomalyNet: An Anomaly Detection Network for Video Surveillance |
|
| Academic Service |
Standard Editor:
|
| Acknowledgements I would like to thank all my collaborators, interns and students. |
|
|