Meng Fang

I am an Assistant Professor in AI at University of Liverpool. I'm also a visiting (assistant) professor at Eindhoven University of Technology (TU/e). I co-lead the UTS NLP Group. I received my Ph.D. from University of Technology Sydney, advised by Prof. Dacheng Tao, and then worked as a postdoctoral research fellow with Prof. Trevor Cohn at the University of Melbourne NLP group. I had been a research scientist/intern at Tencent Robotics X / AI, CSIRO and Microsoft Research Asia before.

My research goal is to build intelligent agents that can perform human-like language understanding, reasoning, and decision-making. My main areas include NLP and ML/RL.

People / Teaching & Service / Email / Github / Scholar /

  • 2 papers accepted to ICLR 2024 and one of them is spotlight. Congratulations to our students and collaborators.
  • We have 3 new papers at ACL 2023 and 3 papers at NeurIPS 2023. Congratulations to our students and collaborators.
  • We have 2 new papers at ICLR 2023 and EACL 2023. Congratulations to our students and collaborators.
  • Our work on Untrained GNNs received the Best Paper Award at Learning on Graphs Conference 2022 (LoG 2022).
  • Looking for motivated prospective students working with us. Please contact me to discuss potential topics and PhD opportunites.

Text-based games
TL;DR: We consider language understanding and reasoning for agents in text-based games.
Keywords: responsible AI, knowledge graphs, attention, RL, hierarchical RL. [project page]

Conversational AI
TL;DR: We consider chatbots for dialogue generation and reasoning.
Keywords: Language generation, persona. [project page]

Question & Answering
TL;DR: We consider the reasoning process for question and answering problems.
Keywords: knowledge graphs, graph neural networks, open domain. [project page]

Reinforcement learning
TL;DR: We propose new agents and environments for robotics and Game AI.
Keywords: sparse/delayed rewards, sample efficient, multi-goal RL, continual learning. [project page]


Selected: (Full publication list)

Where Would I Go Next? Large Language Models as Human Mobility Predictors
Xinglei Wang*, Meng Fang*, Zichao Zeng, Tao Cheng
Preprint Aug 2023 [code]

CHBias: Bias Evaluation and Mitigation of Chinese Conversational Language Models
Jiaxu Zhao*, Meng Fang*, Zijing Shi, Yitong Li, Ling Chen, Mykola Pechenizkiy
In ACL 2023 [code]

NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist
Iftitahu Nimah, Meng Fang, Vlado Menkovski, Mykola Pechenizkiy
In ACL 2023 [code]

A Survey for Efficient Open Domain Question Answering
Qin Zhang, Shangsi Chen, Dongkuan Xu, Qingqing Cao, Xiaojun Chen, Trevor Cohn, Meng Fang
In ACL 2023 [resource]

Stay Moral and Explore: Learn to Behave Morally in Text-based Games
Zijing Shi*, Meng Fang*, Yunqiu Xu, Ling Chen, Yali Du
In ICLR 2023 [code]

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach
Yudi Zhang, Yali Du, Biwei Huang, Ziyan Wang, Jun Wang, Meng Fang, Mykola Pechenizkiy
In NeurIPS 2023 [code]

COOM: A Game Benchmark for Continual Reinforcement Learning
Tristan Tomilin, Meng Fang, Yudi Zhang, Mykola Pechenizkiy
In NeurIPS 2023 [code]

Dynamic Sparsity Is Channel-Level Sparsity Learner
Lu Yin, Gen Li, Meng Fang, Li Shen, Tianjin Huang, Zhangyang Wang, Vlado Menkovski, Xiaolong Ma, Mykola Pechenizkiy, Shiwei Liu
In NeurIPS 2023 [code]

Are Large Kernels Better Teachers than Transformers for ConvNets?
Tianjin Huang, Lu Yin, Zhenyu Zhang, Li Shen, Meng Fang, Mykola Pechenizkiy, Zhangyang Wang, Shiwei Liu
In ICML 2023 [code]

Lottery Pools: Winning More by Interpolating Tickets without Increasing Training or Inference Cost
Lu Yin, Shiwei Liu, Meng Fang, Tianjin Huang, Vlado Menkovski, Mykola Pechenizkiy
In AAAI 2023 [code]

Perceiving the World: Question-guided Reinforcement Learning for Text-based Games
Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Joey Tianyi Zhou, Chengqi Zhang
In ACL 2022 [code]

Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based Games
Dongwon Kelvin Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Gholamreza Haffari
In ACL 2022 [code]

A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation
Yu Cao, Wei Bi, Meng Fang, Shuming Shi, Dacheng Tao
In ACL 2022 [code]

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets
Tianjin Huang, Tianlong Chen, Meng Fang, Vlado Menkovski, Jiaxu Zhao, Lu Yin, Yulong Pei, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, Shiwei Liu
In LoG 2022 [LoG 2022 Best Paper Award]

Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL
Rui Yang, Yiming Lu, Wenzhe Li, Hao Sun, Meng Fang, Yali Du, Xiu Li, Lei Han, Chongjie Zhang
In ICLR 2022 [code]

TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack
Yu Cao, Dianqi Li, Meng Fang, Tianyi Zhou, Jun Gao, Yibing Zhan, Dacheng Tao
In EMNLP 2022 [code]

Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for Topics
Zihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad
In NAACL 2022 [code]

Phrase-level Textual Adversarial Attack with Label Preservation
Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy
In NAACL 2022 (Findings)

Diversity-augmented intrinsic motivation for deep reinforcement learning
Tianhong Dai, Yali Du, Meng Fang, Anil Anthony Bharath
In Neurocomputing 2022 [code]

Generalization in Text-based Games via Hierarchical Reinforcement Learning
Yunqiu Xu, Meng Fang, Ling Chen, Yali Du, Chengqi Zhang
In EMNLP 2021 (Findings) [code]

ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
Iftitahu Ni'mah, Meng Fang, Vlado Menkovski, Mykola Pechenizkiy
In EMNLP 2021 (Findings) [code]

DAGN: Discourse-Aware Graph Network for Logical Reasoning
Yinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang
In NAACL 2021 [Leaderboard: the 1st until 17th Nov., 2020] [code]

REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement
Yinya Huang, Meng Fang, Xunlin Zhan, Qingxing Cao, Xiaodan Liang, Liang Lin
In AAAI 2021 [code]

Towards Efficiently Diversifying Dialogue Generation via Embedding Augmentation
Yu Cao, Liang Ding, Zhiliang Tian, Meng Fang
In ICASSP 2021

Deep Reinforcement Learning for Prefab Assembly Planning in Robot-based Prefabricated Construction
Aiyu Zhu, Gangyan Xu, Pieter Pauwels, Bauke de Vries, Meng Fang
In IEEE International Conference on Automation Science and Engineering (CASE) 2021 [IEEE CASE2021 Best Student Paper Award Finalists]

Reinforcement Learning With Multiple Relational Attention for Solving Vehicle Routing Problems
Yunqiu Xu, Meng Fang, Ling Chen, Gangyan Xu, Yali Du, Chengqi Zhang
In IEEE Transactions on Cybernetics 2021

On the Guaranteed Almost Equivalence Between Imitation Learning From Observation and Demonstration
Zhihao Cheng, Liu Liu, Aishan Liu, Hao Sun, Meng Fang, Dacheng Tao
In IEEE Transactions on Neural Networks and Learning Systems 2021 [code]

TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game
Lei Han*, Jiechao Xiong*, Peng Sun*, Xinghai Sun, Meng Fang, Qingwei Guo, Qiaobo Chen, Tengfei Shi, Hongsheng Yu, Zhengyou Zhang
Report 2021[code]

Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games
Yunqiu Xu*, Meng Fang*, Ling Chen, Yali Du, Joey Tianyi Zhou, Chengqi Zhang
In NeurIPS 2020 [code]

Pretrained Language Models for Dialogue Generation with Multiple Input Sources
Yu Cao, Wei Bi, Meng Fang, Dacheng Tao
In EMNLP 2020 (Findings) [code]

Unsupervised Domain Adaptation on Reading Comprehension
Yu Cao, Meng Fang, Baosheng Yu, Joey Tianyi Zhou
In AAAI 2020 [code]

Curriculum-guided hindsight experience replay
Meng Fang, Tianyi Zhou, Yali Du, Lei Han, Zhengyou Zhang
In NeurIPS 2019 [code]

DHER: Hindsight experience replay for dynamic goals
Meng Fang, Cheng Zhou, Bei Shi, Boqing Gong, Jia Xu, Tong Zhang
In ICLR 2019 [project webpage] [code]

LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning
Yali Du*, Lei Han*, Meng Fang, Ji Liu, Tianhong Dai, Dacheng Tao
In NeurIPS 2019

Dual adversarial neural transfer for low-resource named entity recognition
Joey Tianyi Zhou*, Hao Zhang*, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, Kenneth Kwok
In ACL 2019

Bag: Bi-directional attention entity graph convolutional network for multi-hop reasoning question answering
Yu Cao, Meng Fang, Dacheng Tao
In NAACL 2019 [code]

Learning how to Active Learn: A Deep Reinforcement Learning Approach
Meng Fang, Yuan Li, Trevor Cohn
In EMNLP 2017 [code]

Model transfer for tagging low-resource languages using a bilingual dictionary
Meng Fang, Trevor Cohn
In ACL 2017 [code]

TrGraph: Cross-Network Transfer Learning via Common Signature Subgraphs
Meng Fang, Jie Yin, Xingquan Zhu, Chengqi Zhang
In TKDE 2015

Networked bandits with disjoint linear payoffs
Meng Fang, Dacheng Tao
In KDD 2014

Active Learning for Crowdsourcing Using Knowledge Transfer
Meng Fang, Jie Yin, Dacheng Tao
In AAAI 2014


I would like to thank all my collaborators, interns and students.

(imitation is the sincerest form of flattery)