Jie Fu

Jie Fu

Research Scientist

Shanghai AI Lab

Jie Fu (付杰) is a happy and funny research scientist at Shanghai AI Lab (上海人工智能实验室), chasing his human-centered big AI dream.

He was a postdoctoral fellow (funded by Microsoft Research Montreal) supervised by Yoshua Bengio at University of Montreal, Quebec AI Institute (Mila). He was an IVADO postdoctoral fellow supervised by Chris Pal at Polytechnique Montreal, Quebec AI Institute (Mila). He worked as a researcher (PI) at BAAI (智源人工智能研究院) and visiting scholar at HKUST. He obtained his PhD from National University of Singapore under the supervision of Tat-Seng Chua. He received outstanding paper awards at NAACL 2024, ICLR 2021.

His research agenda is centered around establishing machine intelligence within a safe and scalable world model framework, having an tight integration of System-1 (e.g., intuitive, fast) and System-2 (e.g., slow, algorithmic, reasoning, planning) functionalities. More concretely:

Selected Publications

I’m (still…) training myself (slowly…)

My full publications can be found in Google Scholar.
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
NeurIPS 2024 Spotlight
Tracking single cell evolution via clock-like chromatin accessibility
Nature Biotechnology 2024
HyperMoE: Towards Better Mixture of Experts via Transferring Among Experts
ACL 2024
Think Before You Act: Decision Transformers with Working Memory
ICML 2024
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
ICLR 2024
AI Alignment: A Comprehensive Survey
arXiv
When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability
NeurIPS 2023
Running Ahead of Evolution - AI based Simulation for Predicting Future High-risk SARS-CoV-2 Variants
IJHPCA, ACM Gordon Bell COVID Finalist 2022
Interactive Natural Language Processing
arXiv
MUDiff: Unified Diffusion for Complete Molecule Generation
LoG 2023
Learning Multi-Objective Curricula for Robotic Policy Learning
CoRL 2022
Biological Sequence Design with GFlowNets
ICML 2022
CoCon: A Self-Supervised Approach for Controlled Text Generation
ICLR 2021
Interactive Machine Comprehension with Information Seeking Agents
ACL 2020