Zhenfang Chen

Zhenfang Chen

Bio

I am a researcher at MIT-IBM Watson AI Lab in Cambridge, MA, USA. I received my Ph.D. degree from the Department of Computer Science at The University of Hong Kong. My interests are centered around machine learning and its applications to computer vision and natural language processing. My ultimate research goal is to develop an AI system that can perceive and reason about the physical world, and communicate with humans in natural language.

Publications

ContPhy: Continuum Physical Concept Learning and Reasoning from Videos
- - Zhicheng Zheng
  - Xin Yan
  - et al.
- 2024
- ICML 2024
SOK-Bench: A Situated Video Reasoning Benchmark with Aligned Open-World Knowledge
- - Andong Wang
  - Bo Wu
  - et al.
- 2024
- CVPR 2024
GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
- - Zhenfang Chen
  - Rui Sun
  - et al.
- 2024
- ICLR 2024
SALMON: SELF-ALIGNMENT WITH INSTRUCTABLE REWARD MODELS
- - Zhiqing Sun
  - Yikang Shen
  - et al.
- 2024
- ICLR 2024
COVLM: COMPOSING VISUAL ENTITIES AND RELATIONSHIPS IN LARGE LANGUAGE MODELS VIA COMMUNICATIVE DECODING
- - Junyan Li
  - Delin Chen
  - et al.
- 2024
- ICLR 2024
Visual Chain-of-Thought Prompting for Knowledge-Based Visual Reasoning
- - Zhenfang Chen
  - Qinhong Zhou
  - et al.
- 2024
- AAAI 2024
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
- - Zhiqing Sun
  - Yikang Shen
  - et al.
- 2023
- NeurIPS 2023
3D-LLM: Injecting the 3D World into Large Language Models
- - Yining Hong
  - Haoyu Zhen
  - et al.
- 2023
- NeurIPS 2023
Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties
- - Hsiao-yu Tung
  - Mingyu Ding
  - et al.
- 2023
- NeurIPS 2023
3D Concept Learning and Reasoning from Multi-View Images
- - Yining Hong
  - Chunru Lin
  - et al.
- 2023
- CVPR 2023

Patents

- 10 Mar 2025
- US
- 12249148
Object-centric And Relation-centric Graph Neural Networks For Physical Property Discovery
- 23 Dec 2024
- US
- 12175384
Neural-symbolic Action Transformers For video Question Answering
- 29 Jul 2024
- US
- 12051243
Transformers For Real World Video Question Answering
- 24 Jun 2024
- US
- 12020480
Counterfactual Debiasing Inference For Compositional Action Recognition

Projects

Dromedary
Training language models to better follow user intentions and make them more truthful

Top collaborators

DC

David D. Cox

David D. Cox

VP, AI Models; IBM Director, MIT-IBM Watson AI Lab

DG

Dan Gutfreund

Dan Gutfreund

Principal Research Staff Member, Manager, AI Models Science