Jie Fu

Jie Fu

Researcher (Principal Investigator)

Beijing Academy of Artificial Intelligence (BAAI)

Jie Fu (付杰) is a happy1 and funny machine learning researcher (principal investigator), currently at Beijing Academy of Artificial Intelligence2 (BAAI, 北京智源人工智能研究院), with his human-friendly big AI dream.

He worked as a postdoc with Yoshua Bengio at University of Montreal, Quebec AI Institute (Mila), funded by Microsoft Research Montreal. He was an IVADO postdoc fellow working with Chris Pal at Polytechnique Montreal, Quebec AI Institute (Mila). He obtained his PhD from National University of Singapore under the supervision of Tat-Seng Chua. He received ICLR 2021 Outstanding Paper Award.

He is currently working towards scalable system-2 deep learning and its adaption to various real-world tasks, including large-scale mixed-modality learning with decent reasoning capabilities, and AI for science (drug discovery in particular) that can benefit all of society. He is also broadly interested in general deep learning, reinforcement learning, and language processing. More concretely:

  • Towards System-2 Deep Learning: Meta learning, Lifelong learning, Reasoning, Modular neural architectures, Causal representation learning, etc
  • Applications: Multi-modal learning (e.g., NLP, CV), Multi-modal embodied intelligence, AI for science, etc

  1. Not that happy now. Chat? ↩︎

  2. Not-for-profit private-owned organization. ↩︎

Selected Publications

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

My full publications can be found in Google Scholar.
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
Think Before You Act: Decision Transformers with Internal Working Memory
Interactive Natural Language Processing
MUDiff: Unified Diffusion for Complete Molecule Generation
When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability
Chinese Open Instruction Generalist: A Preliminary Release
Running Ahead of Evolution - AI based Simulation for Predicting Future High-risk SARS-CoV-2 Variants
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
Rikinet: Reading Wikipedia Pages for Natural Question Answering
ACL 2020
Interactive Machine Comprehension with Information Seeking Agents
ACL 2020