Yuchen Guo

I am pursuing the MS in Artificial Intelligence at Northwestern University. I received my BSc in Computer Science with First Class Honours from Hong Kong Baptist University.

I was a research intern with the XPixel Group, MMLab at the Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences (SIAT, CAS), advised by Prof. Chao Dong, and at the Institute for AI Industry Research (AIR), Tsinghua University, advised by Prof. Yilun Chen. I was also a summer visiting student in Artificial Intelligence and Machine Learning at the University of Oxford, advised by Prof. Tom Rainforth.

I also work closely with Dr. Wei Ji at Yale & Tencent, Dr. Shihao Zou at SIAT and Prof. Weifeng Su at BNBU.

Research
Interest

I am interested in studying intelligence by building multimodal systems that learn and develop through experience and interaction with the world.

My current work asks how such systems can expand what they perceive, internalize what they experience, and use their understanding to reason about and act in the world.

Multimodal Perception Grounded Reasoning Agent Memory Continual Learning

Multimodal Perception

A system's perception need not be confined to the narrow band of the spectrum humans happen to see. I work on what else it should sense, and whether that sensing can run fast enough to be acted on.

FusionProxy·DAE-Fuse·FuScore

Grounded Reasoning

Whether what a model perceives is sufficient to reason about action, or only enough to label what is there.

SegWorld·SAM3-I

Agent Memory

How interaction consolidates into the model itself, rather than accumulating in a buffer the model looks things up in.

PEAM

Continual Learning

How a system keeps developing after training ends.

In submission

Selected Publications

Peer-reviewed

SAM3-I: Segment Anything with Instructions

Jingjing Li*, Yue Feng*, Yuchen Guo*, Jincai Huang*, Wei Ji, Qi Bi, Yongri Piao, Miao Zhang, Xiaoqi Zhao, Qiang Chen, Shihao Zou, Huchuan Lu, Li Cheng

Association for Computational Linguistics (ACL), 2026 Main Conference Paper

Adding Thermal Awareness to Visual Systems in Real-Time via Distilled Diffusion Models

Yuchen Guo, Junli Gong, Wenjun Dong, Yiu-ming Cheung, Weifeng Su

Computer Vision and Pattern Recognition (CVPR Workshop), 2026
World Models Meet Active Sensing and Closed-Loop Planning Paper

DAE-Fuse: An Adaptive Discriminative Autoencoder for Multi-Modality Image Fusion

Yuchen Guo*, Ruoxiang Xu*, Rongcheng Li, Weifeng Su

International Conference on Multimedia and Expo (ICME), 2025 Oral Project Paper

Towards Unified Surgical Scene Understanding: Bridging Reasoning and Grounding via MLLMs

Jincai Huang*, Shihao Zou*, Yuchen Guo, Jingjing Li, Wei Ji, Kai Wang, Shanshan Wang, Weixin Si

Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026 Early Accept Paper

Preprints & under review

Can Segmentation Models Understand the World? Towards Proactive Affordance Reasoning via Visual Chain-of-Thought

Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung, Weifeng Su

Preprint Paper

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

Yuchen Guo, Junli Gong, Weicheng Wang, Hongmin Cai, Yiu-ming Cheung, Weifeng Su

Preprint Paper

Accelerating Reasoning and Grounding for Surgical Intelligence via Multi-Granular Token Compression

Weixin Si, Jincai Huang, Jingjing Li, Wei Ji, Hoayuan Zheng, Yuchen Guo, Kai Wang, Shihao Zou, Yang Gao, Shanshan Wang

Under Review in IEEE Transactions on Medical Imaging (TMI)

Bringing Multimodal Large Language Models to Infrared-Visible Image Fusion Quality Assessment

Yuchen Guo*, Junli Gong*, Yao Lu, Xintong Xu, Yiu-ming Cheung, Weifeng Su

Preprint Paper

Fuse4Seg: Image Fusion for Multi-Modal Medical Segmentation via Bi-level Optimization

Yuchen Guo, Junli Gong, Hongmin Cai, Yiu-ming Cheung, Weifeng Su

Preprint Paper

* denotes equal contribution.

What I cannot create, I do not understand. — Richard Feynman