Zeming Chen (Eric)

About me

Hello! I am a PhD student at EPFL NLP Lab, supervised by Dr. Antoine Bosselut. My primary study covers NLP and Machine Learning.

Currently, I focus on complex reasoning over natural language and large language model development. I am doing my research scientist internship at Meta AI's FAIR team, working on multimodal foundation models for video reasoning.

I completed my research internship at the Allen Institute for AI (AI2), supervised by Kyle Richardson and Ashish Sabharwal. I am currently in collaboration with AI2.

I received my bachelor's in 2022 at the Rose-Hulman Institute of Technology, with a double major in Computer Science and Mathematics. I learned to do research in NLP from Larry Moss (Indiana University) and Michael Wollowski.

Complex Reasoning over Natural Language: I am interested in training and improving models to conduct complex reasoning over natural language. This also covers how models can acquire, encode, deliver, and apply knowledge to solve various problems. My current research focuses on the concept of mechnistic reasoning, i.e., using internal model mechanisms for reasoning
Large language model NLP: I am fascinated by how large language models can encode vast amounts of information and generate fluent text. I want to explore how these general-purpose models can be used in downstream NLP tasks such as open-domain QA and commonsense reasoning. I am interested in building systems that allow general-purpose models to be used in a dynamic, real-life setting.
Interpretability, benchmarking, and verified AI: I want to develop new tools and theories that help interpret and probe model behaviors. I also want to build benchmarks that can evaluate models' ability and diagnose potential issues in data and learning, especially asses how reliable a model can be in real-life use cases. I recently started to explore the idea of verified AI, where the goal is to have provable assurances of correctness concerning mathematically-specified requirements.
Design new learning algorithms: How machines can learn to understand and reason similarly to human learning is still open for exploration. I want to design new learning algorithms that help models learn continually, actively, comprehensively, and transparently by drawing inspiration from human cognition.

In my free time, I enjoy doing many different things! Work-life balance is important for everyone's scientific career.

I am a musician. I play five different instruments: piano, flute, saxophone, piccolo, and cello. I enjoy playing classic music.

I also love to play tennis and lift weights in the gym.

I love traveling, visiting different places, and experiencing different cultures.

News

Show & Hide More News

About me

News

MEDITRON-70B: Scaling Medical Pretraining for Large Language Models

Megatron-LLM

Distilling Counterfactual Data from Large Language Models

Neuro-symbolic Reasoning in Modern AI