Yue Zhang

Hello! I am a postdoctoral research associate in the MURGe-Lab led by Prof. Mohit Bansal, at the University of North Carolina, Chapel Hill. I earned my Ph.D. at Michigan State University, where I was advised by Prof. Parisa Kordjamshidi. I was a visiting scholar at Virginia Tech, collaborating with Prof. Lifu Huang. Prior to Ph.D. study, I obtained my master’s degree from Peking University. My research interests include multimodal learning, embodied agents, and spatial reasoning.

Email / CV / Google Scholar / Github / LinkedIn

News

[2026.6] EgoMemReason is accepted to COLM 2026!
[2026.6] Five papers (DEER3D, AnchorWeave, VisionCoach, V-Co, and PQSG) were accepted to ECCV 2026, and MedForget was accepted to TMLR.
[2026.5] EPiC is accepted to ICML 2026!
[2026.4] Two papers were accepted to the ACL main, and two papers will appear in CVPR Findings!
[2025.8] Two papers got accepted by EMNLP 2025!
[2025.4] Officially Joined MURGe-Lab!

Research Directions

Embodied & Vision-and-Language Navigation: building agents that perceive, reason, and navigate in 3D environments by following natural-language instructions, including VLN Survey, SkillNav, Prune-Then-Plan, VLN-Analogy, NavHint, Dual-Action-VLN-CE, VLN-Trans and LOViS.
Spatial & 3D Reasoning: equipping (multimodal) LLMs with situated spatial understanding and 3D grounding, and studying when models should abstain, including SpatialUncertain, AViC, DEER-3D, and SPARTUN3D.
Video Generation & World Models: controllable, physics- and world-consistent video generation guided by structured priors, verification, and evaluation, including PhyMotion, SketchVerify, AnchorWeave, EPiC, and PQSG.
Video Understanding & Reasoning: long-horizon, memory-driven, and spatial-temporal grounded reasoning over videos, including EgoMemReason and VisionCoach.
Multimodal Reasoning & Agents: dynamic expert aggregation, tool recruitment, and routing for general multimodal reasoning, including MEXA, DART, and RGD.
Trustworthy & Forensic Multimodal AI: interpretable forgery and deepfake detection and multimodal unlearning for safe deployment, including Deepfake-Agent, M2F2-Det, Deepfake-VQA, and MedForget.

Selected Preprints

	Seeing Isn’t Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)? Yue Zhang, Zun Wang, Han Lin, Yonatan Bitton, Idan Szpektor, Mohit Bansal Preprint, 2026 ArXiv/ Code
	PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation Yidong Huang, Zun Wang, Han Lin, Dong-Ki Kim, Shayegan Omidshafiei, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal Preprint, 2026 ArXiv/ Code
	When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning Shoubin Yu, Yue Zhang, Zun Wang, Jaehong Yoon, Huaxiu Yao, Mingyu Ding, Mohit Bansal Preprint, 2026 ArXiv/ Code
	Planning with Sketch-Guided Verification for Physics-Aware Video Generation Yidong Huang, Zun Wang, Han Lin, Dong-Ki Kim, Shayegan Omidshafiei, Jaehong Yoon, Yue Zhang, Mohit Bansal Preprint, 2025 ArXiv/ Code

Selected Publications

	EgoMemReason: A Memory-driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding Ziyang Wang, Yue Zhang Shoubin Yu, Ce Zhang, Zenqi Zhao, Jaehong Yoon, Hyunji Lee, Gedas Bertasius, Mohit Bansal COLM, 2026 ArXiv/ Code
	AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories Zun Wang, Han Lin, Jaehong Yoon, Jaemin Cho, Yue Zhang, Mohit Bansal ECCV, 2026 ArXiv/ Code
	Error-Driven Scene Editing for 3D Grounding in Large Language Models Yue Zhang, Zun Wang, Han Lin, Jialu Li, Jianing Yang, Yonatan Bitton, Idan Szpektor, Mohit Bansal ECCV, 2026 ArXiv/ Code
	VisionCoach: Reinforcing Grounded Video Reasoning via Visual-Perception Prompting Daeun Lee, Shoubin Yu, Yue Zhang, Mohit Bansal ECCV, 2026 ArXiv/ Code
	Physics Question Scene Graph: Fine-grained Evaluation of Physical Plausibility in Text-to-Video Generation Atin Pothiraj, Jaemin Cho, Yue Zhang, Elias Stengel-Eskin, Mohit Bansal ECCV, 2026 ArXiv/ Code
	V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal ECCV, 2026 ArXiv/ Code
	Hierarchy-Aware Multimodal Unlearning for Medical AI Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal TMLR, 2026 ArXiv/ Code
	EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance Zun Wang, Jaemin Cho, Jialu Li, Han Lin, Jaehong Yoon, Yue Zhang, Mohit Bansal ICML, 2026 ArXiv/ Code
	Breaking Down and Building Up: Mixture of Skill-Based Vision-and-Language Navigation Agents Tianyi Ma, Yue Zhang, Zehao Wang, Parisa Kordjamshidi ACL (Oral), 2026 ArXiv/ Code
	Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection Tianyi Niu, Justin Chih-Yao Chen, Genta Indra Winata, Shi-Xiong Zhang, Supriyo Chakraborty, Sambit Sahu, Yue Zhang, Elias Stengel-Eskin, Mohit Bansal ACL (Oral), 2026 ArXiv/ Code
	Deepfake-Agent: Aggregating Semantic Forgery Clues for Generalizable Detection Xiao Guo, Yue Zhang, Mohit Bansal, Xiaoming Liu CVPR Findings, 2026 ArXiv/ Code
	Prune-Then-Plan: Step-Level Calibration for Stable Frontier Exploration in Embodied Question Answering Noah Frahm, Prakrut Patel, Yue Zhang, Shoubin Yu, Mohit Bansal, Roni Sengupta CVPR Findings, 2026 ArXiv/ Code
	DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning Nithin Sivakumaran, Justin Chih-Yao Chen, David Wan, Yue Zhang, Jaehong Yoon, Elias Stengel-Eskin, Mohit Bansal EACL, 2026 ArXiv/ Code
	MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation Shoubin Yu, Yue Zhang, Ziyang Wang, Jaehong Yoon, Mohit Bansal EMNLP Findings, 2025 ArXiv/ Code
	Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs Yue Zhang, Tianyi Ma, Zun Wang, Yanyuan Qiao, Parisa Kordjamshidi EMNLP, 2025 ArXiv/ Code
	Rethinking Vision Language Model in Face Forensic: Multi-modal Interpretable Forged Face Detector Xiao Guo, Xiufeng Song, Yue Zhang, Xiaohong Liu, Xiaoming Liu CVPR (Oral), 2025 ArXiv/ Code
	SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models Yue Zhang, Zhiyang Xu, Ying Shen, Parisa Kordjamshidi, Lifu Huang ICLR, 2025 ArXiv/ Code
	Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models Yue Zhang, Ziqiao Ma, Jialu Li, Yanyuan Qiao, Zun Wang, Joyce Chai, Qi Wu, Mohit Bansal, Parisa Kordjamshidi TMLR*, 2024 ArXiv/ Code
	Narrowing the Gap between Vision and Action in Navigation Yue Zhang, Parisa Kordjamshidi ACM MM, 2024 ArXiv/ Code
	Common Sense Reasoning for Deepfake Detection Yue Zhang, Ben Colman, Xiao Guo, Ali Shahriyari, Gaurav Bharaj ECCV, 2024 ArXiv/ Code
	NavHint: Vision and Language Navigation Agent with a Hint Generator Yue Zhang, Quan Guo, Parisa Kordjamshidi EACL Findings, 2024 ArXiv/ Code
	VLN-Trans: Translator for the Vision and Language Navigation Agent Yue Zhang, Parisa Kordjamshidi ACL (Oral), 2023 ArXiv Code
	LOViS: Learning Orientation and Visual Signals for Vision and Language Navigation Yue Zhang, Parisa Kordjamshidi COLING (Oral), 2022 ArXiv/ Code
	Explicit Object Relation Alignment for Vision and Language Navigation Yue Zhang, Parisa Kordjamshidi ACL SRW, 2022 ArXiv/ Code
	Towards Navigation by Reasoning over Spatial Configurations Yue Zhang, Quan Guo, Parisa Kordjamshidi ACL workshop on SpLU-RoboNLP, 2021 ArXiv/ Code

Professional Service

[2024.7] Co-organizer of SpLU-RoboNLP @ ACL 2024
[2022.11] Invited talk at Sichuan University
Reviewer for ACL, EMNLP, NAACL