arXiv:2609.37923
EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory
arXiv, 2026
Ziyun Zeng
Second-year Ph.D. student in the VIStA Lab at the University of Rochester, advised by Albert Arendt Hopeman Professor Jiebo Luo.
My research focuses on Multimodal Agent and Visual Generation.
Portrait 1 of 3
Selected Publications
All
arXiv:2608.05485
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing
arXiv preprint, 2026
arXiv:2605.18652
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
arXiv preprint, 2026
CVPR 2026
MIRA: Multimodal Iterative Reasoning Agent for Image Editing
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
ACM Transactions on Computing for Healthcare 2026
Automated Detection and Quantitative Assessment of Dental Plaque in Intraoral Images
ACM Transactions on Computing for Healthcare, 2026
TMLR 2026
MMComposition: Revisiting the Compositionality of Pre-trained Vision-Language Models
Transactions on Machine Learning Research (TMLR), 2026
NeurIPS 2025
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-modal Image Generation Models
Advances in Neural Information Processing Systems (NeurIPS), 2025
CVPR 2024
VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
EpiCon: Collective Agent Learning through Co-Evolving Multimodal Memory
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing
MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents
Aurora: Unified Video Editing with a Tool-Using Agent
MIRA: Multimodal Iterative Reasoning Agent for Image Editing
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing
Aurora: Unified Video Editing with a Tool-Using Agent
MIRA: Multimodal Iterative Reasoning Agent for Image Editing
MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-modal Image Generation Models
OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
PromptFix: You Prompt and We Fix the Photo
Experience
Education
University of California, Berkeley
Visiting Student ·
ShanghaiTech University
B.Eng. in Computer Science ·