About Me

Here is a virtual but warm greeting from Ziqiao, as you just came across this page! As many of my friends found it hard to pronounce my name (马子乔, pronounced as Tsz-Chaw in Mandarin), it's absolutely fine to just call me Martin alternatively.

Bio

Ziqiao (Martin) Ma is a 3rd year Ph.D. candidate in Computer Science and Engineering and a Graduate Certificate Student at Weinberg Institute for Cognitive Science at the University of Michigan. He is advised by Professor Joyce Chai as a member of the Situated Language and Embodied Dialogue (SLED) Lab, and worked with Adobe Research and Amazon AGI. He obtained dual-bachelor degrees from the University of Michigan and Shanghai Jiao Tong University. He received an Outstanding Paper Award at ACL 2023, an Amazon Alexa Prize Award, and an Outstanding GSI Award for teaching. He co-organized SpLU-RoboNLP @ ACL 2024, and serve as a regular PC member/reviewer for NLP venues (e.g., ARR, ACL, EMNLP, NAACL, EACL, COLING, COLM, ...), ML venues (e.g., ICLR, NeurIPS, TMLR, DMLR, ...), CV venues (CVPR, ECCV, ...), Cognitive Science venues (COGSCI), and sometimes HCI/HRI/CSS/DM venues (CHI, HRI, ICWSM, ...).

My Research

The three constant themes of my research are Language, Interaction, and Embodiment from a scalable and developmental angle. My current research focus is two-fold:

Grounding language models to (and developing frontier models of) the 4D world and human interactions.
  • Grounding language to the physical world: Understanding and generating language that is grounded to sensorimotor experiences and physical situations. There are more to look at beyond 2D grounding, e.g., video, 3D, generative world models.
  • Grounding language to human interactions: (Co-)situated Human-AI interaction in shared environment with disparate mental states, and collaborations towards a common ground.
  • Applications of grounded frontier models in situated agents.
Scalable computational models of human cognition, scientifically.
  • Scaling law and developmental psychology: Exploring the developmental trajectories of large-scale frontier models and the emergent cognitive capabilities over the course of development.
  • Computational inquiry of human cognition: Computational abstractions to inquire about potential mechanisms of how humans acquire and process language as well as collaborate.
  • Human-like learning: Machine learning that is (inter)active, data-efficient, and continual on (semi-)structured data upon pre-trained systems.
I include a more dynamic and spontaneous sharing of my thoughts in Research and Mentoring Statements.

Programming Languages:
Python C/C++ C# JavaScript Java
Platforms:
Unity Unreal

Updates

News

Archived news...
  • [May. 2023] I started my intern with Amazon Alexa AI (Amazon AGI)!!
  • [Sep. 2022] I will serve as the Poster/Demo Session Chair for Michigan AI Symposium 2022.
  • [Aug. 2022] I will be the Graduate Student Instructor for EECS 595 (NLP) in Fall 2022 at Michigan.
  • [Aug. 2021] I graduated from SJTU!
  • [May. 2021] I graduated from Michigan!
  • [Mar. 2021] I will join the family of the Michigan AI as a Ph.D. student this fall. Go Blue!
  • [Dec. 2020] I will be the Instructional Aide for EECS 492 (Intro. AI) in Winter 2021 at Michigan.
  • [May. 2020] I will be the Teaching Assistant for VE 492 (Intro. AI) and VE 280 (Program. & Intro. Data Struct.) Summer 2020 at SJTU.

Paper Alerts

Archived news...
  • [Oct. 2022] Two papers to appear in EMNLP 2022, and I will serve as an on-site volunteer in Abu Dhabi :)

Experiences

Education

Industry

Teaching

Archived teaching...
  • VP 141 Physics Lab I, Shanghai Jiao Tong University.
  • VY 200 Academic Writing II, Shanghai Jiao Tong University.
  • VY 100 Academic Writing I, Shanghai Jiao Tong University.

Selected Awards/Recognitions

Selected Fellowships/Scholarships

Academic Services

Publications

* indicates equal contributions; § indicates correspondence and mentoring.

Language Grounding to Human Interactions & Theory of Mind

Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models

Ziqiao Ma, Jacob Sansom, Run Peng, Joyce Chai

EMNLP Findings (Theme Track), 2023

[web] [paper] [data]

Towards Collaborative Plan Acquisition through Theory of Mind Modeling in Situated Dialogue

Cristian-Paul Bara, Ziqiao Ma, Yingzhuo Yu, Julie Shah, Joyce Chai

IJCAI, 2023

[paper] [code]

Language Grounding to Vision & Multimodal Learning

GroundHog: Grounding Large Language Models to Holistic Segmentation

Yichi Zhang, Ziqiao Ma, Xiaofeng Gao, Suhaila Shakiah, Qiaozi Gao, Joyce Chai

CVPR, 2024

[web] [paper]

Inversion-Free Image Editing with Natural Language

Sihan Xu*, Yidong Huang*, Jiayi Pan, Ziqiao Ma§, Joyce Chai

CVPR, 2024

[web] [paper] [code]

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Sihan Xu*, Ziqiao Ma*, Yidong Huang, Honglak Lee, Joyce Chai

NeurIPS, 2023

[web] [paper] [code]

World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models

Ziqiao Ma*, Jiayi Pan*, Joyce Chai

ACL (Outstanding Paper Award), 2023

[paper] [code] [model] [video] [slides] [poster]

Language Grounding to Robotics & Embodied AI

SEAGULL: An Embodied Agent for Instruction Following through Situated Dialog

Yichi Zhang, Jianing Yang, Keunwoo Peter Yu, Yinpei Dai, Shane Storks Yuwei Bao, Jiayi Pan, Nikhil Devraj, Ziqiao Ma, Joyce Chai

Alexa Prize SimBot Challenge (1st Place), 2023

[paper]

DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents

Ziqiao Ma, Benjamin VanDerPloeg*, Cristian-Paul Bara*, Huang Yidong*, Eui-In Kim, Felix Gervits, Matthew Marge, Joyce Chai

EMNLP Findings, 2022
Presented at SereTOD Workshop, 2022

[paper] [code] [data] [video] [slides] [poster]

DANLI: Deliberative Agent for Following Natural Language Instructions

Yichi Zhang, Jianing Yang, Shane Storks, Jiayi Pan, Nikhil Devraj, Ziqiao Ma, Keunwoo Peter Yu, Yuwei Bao, Joyce Chai

EMNLP (Oral), 2022

[paper] [code] [video] [slides]

Data-Efficient Learning & Cognitively Motivated Learning

Partition-Based Active Learning for Graph Neural Networks

Jiaqi Ma*, Ziqiao Ma*, Joyce Chai, Qiaozhu Mei

TMLR (Survey Certificate), 2023
Presented at DLG-KDD Workshop (Oral), 2022

[paper] [code] [poster]

AI for Social Good & Community Services

NLP Reproducibility For All: Understanding Experiences of Beginners

Shane Storks, Keunwoo Peter Yu, Ziqiao Ma, Joyce Chai

ACL (Theme Track), 2023

[paper] [code] [video] [slides] [poster]

Non-Academic: Game Design

Misc

Mentoring

I understand that access to research oppotunities can be hard, particularly for beginners and the underrepresented. If there is a match in research interests, I am happy to collaborate with undergrads and masters when I have the bandwidth. Please check my Research and Mentoring Statements and fill out our application form to indicate that you want to collaborate with me.
I've been fortunate to have (co-)mentered and collaborated with these amazingly talented young researchers:

Fun Facts

Friends

Mental Support

Chat?

If you would like to have a random (virtual) coffee chat with me, please visit my calendly page.

Get In Touch

You are welcome to drop me a message :)

  • Phone

    xxx-xxx-xxxx

  • marstin0607

  • ziqiao_ma

  • Address

    Bob and Betty Beyster Building 4909,
    2260 Hayward Street,
    Ann Arbor, MI 48109.