Mengdi Li

Mengdi Li / 李梦迪

I am a Ph.D. student at the Knowledge Technology group at the University of Hamburg (Germany), advised by Prof. Stefan Wermter. Before that, I obtained my Master's degree in Computer Science and Bachelor's degree in Electronic Engineer at the China Agricutural University. Please feel free to leave anonymous feedback and suggestions about both my work and me here.

Email / CV / Google Scholar / Twitter / Github / Linkedin

News

Our paper on enhancing zero-shot reasoning of LLMs got accepted to LREC-COLING 2024. [Paper link]
Our paper on explainable reinforcement learning got accepted for oral presentation to CLeaR 2024. [Paper link]
Our paper on using LLMs for robotic multimodal exploration got accepted to IROS 2023. [Paper link]
Our paper on stabalizing RL when the reward is produced by a jointly optimized reward model got accepted to ICML 2023. [Paper link]

Research

I'm working on reinforcement learning related to reward models, LLMs, and embodied agents.

Selected Publications

(see all publications here)

In reversed chronological order / * equal contributions

	Enhancing Zero-Shot Chain-of-Thought Reasoning in Large Language Models through Logic Xufeng Zhao, Mengdi Li, Wenhao Lu, Cornelius Weber, Jae Hee Lee, Stefan Wermter, LREC-COLING, 2024 project page / arXiv / Aiming to improve the zero-shot chain-of-thought reasoning ability of LLMs, we propose LoT (Logical Thoughts), a neurosymbolic framework that leverages principles from symbolic logic to verify and revise the reasoning processes accordingly.
	Chat with the Environment: Interactive Multimodal Perception using Large Language Models Xufeng Zhao, Mengdi Li, Cornelius Weber, Burhan Hafez, Stefan Wermter, IROS, 2023 project page / code / video / arXiv / poster / slides / We develop an LLM-centered modular network to provide high-level planning and reasoning skills and control interactive robot behaviour in a multimodal environment.
	Internally Rewarded Reinforcement Learning Mengdi Li, Xufeng Zhao, Jae Hee Lee, Cornelius Weber, Stefan Wermter, ICML, 2023 project page / code / arXiv / poster We propose the clipped linear reward to stablize reinforcement learning where reward signals for policy learning are generated by a discriminator-based reward model that is dependent on and jointly optimized with the policy.
	Robotic Occlusion Reasoning for Efficient Object Existence Prediction Mengdi Li, Cornelius Weber, Matthias Kerzel, Jae Hee Lee, Zheni Zeng, Zhiyuan Liu, Stefan Wermter, IROS, 2021 code / video / arXiv We propose an RNN-based model that is jointly trained with supervised and reinforcement learning to achieve the task of predicting the existence of objects in occusion scenarios.
	Neural Networks for Detecting Irrelevant Questions During Visual Question Answering Mengdi Li, Cornelius Weber, Stefan Wermter, ICANN, 2020 paper We demonstrate that an efficient neural network designed for VQA can achieve high accuracy on detecting the relevance of questions to images, however joint training the model on relevance detection and VQA leads to performance degradation on VQA.
	Generating Steganographic Image Description by Dynamic Synonym Substitution Mengdi Li, Kai Mu, Ping Zhong, Juan Wen, Yiming Xue, Signal Processing, 2019 paper We propose a novel image captioning model to automatically generate stego image descriptions. The proposed model is able to generate high-quality image descriptions in both human evaluation and statistical analysis.

The template of this website is borrowed from Jon Barron.