Alireza Rezazadeh
[ Email | Google Scholar | LinkedIn | GitHub ]Embedded Files
I’m a Senior Machine Learning Engineer at Adobe, working at the intersection of agentic AI, multimodal systems, and applied machine learning.
Previously, I helped shape AI Refinery at Accenture’s Center for Advanced AI, building agentic LLM systems across memory, reasoning, tool-use, and real-time interaction. My work bridged research and production, with an emphasis on turning research ideas into reliable platform capabilities.
I received my Ph.D. from the University of Minnesota, where my research focused on learning multimodal, graph-structured world models for robotic manipulation and long-horizon physical reasoning.
Education
Ph.D. in Electrical and Computer Engineering, University of Minnesota
Thesis: "Learning Graph-Structured Representations for Robotic Manipulation"M.Sc. in Electrical and Computer Engineering, University of Minnesota
Minor: EconomicsM.Sc. in Mechanical Engineering, University of Illinois Chicago
Thesis: "Force Field Generalization and the Internal Representation of Motor Learning"B.Sc. in Mechanical Engineering, Sharif University of Technology
Selected Publications
Selected Publications
Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control
A Rezazadeh, Z Li, A Lou, Y Zhao, W Wei, Y Bao
ICML 2025 (Multi-Agent Systems Workshop)
[Paper]
From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
A Rezazadeh, Z Li, W Wei, Y Bao
ICLR 2025
NeurIPS 2024 (Sys2-Reasoning Workshop)
[Paper]
Google Sites
Report abuse