World Models · Multimodal Agents · Persistent Visual Memory
Hi! I am an undergraduate student in the Department of Electrical and Computer Engineering at the University of Toronto. I am currently a Research Intern at UW–Madison, working with Prof. Xiao Luo. I am also a Software Engineer Intern at Microchip Technology. Previously, I was an AI Research Intern at Memories.ai and a Machine Learning Intern at Themis AI.
My research focuses on world models, multimodal agents, and persistent visual memory. I am interested in building AI systems that can model how environments evolve, reason across visual and language information, and retain useful context from long-form video over time.
Seeking Fall 2028 CS PhD opportunities.
News
One paper (NeTron) has been accepted to IEEE VLSI 2026! Link
Joined Microchip Technology Inc. as a Software Engineer Intern.
Joined Memories.ai as an AI Research Intern.
Joined UW–Madison as a Research Intern, working with Prof. Xiao Luo.
Joined Themis AI as a Machine Learning Intern.
Publications
Open full-size figure ↗
ICM-Bench evaluates whether multimodal agents can remember recurring people and reason about their identities and relationships across long video memories. It contains 839 synthetic clips spanning 141 minutes and 1,217 open-ended questions across three identity-centric memory tasks.
Open full-size figure ↗
IEEE VLSI 2026
We present a split-inference intracortical interface IC for battery-free, millimeter-scale brain implants, with validation across motor reach-to-grasp and inner-speech decoding. The work connects low-power neural decoding, spike-sorting pipelines, and system-level evaluation, showing neural output data-rate reductions of 1,066× and 16,732× while preserving decoding performance.
Experience
May 2026 - Present
Working on research-driven FPGA EDA tools for PolarFire 2, combining timing and power analysis with AI and LLM-assisted approaches for interconnect timing modeling and design automation.
Jan 2026 - May 2026
Researched LLM post-training, long-video understanding, and memory-augmented models for persistent visual intelligence.
Dec 2025 - Present
Focused on LLM post-training and agent applications under the supervision of Professor Xiao Luo.
May 2025 - Sep 2025
Contributed to VLSI 2026 work and developed low-power neural decoding and spike-sorting pipelines for neural interface systems.
May 2025 - Sep 2025
Built an active-learning data labeling framework using uncertainty sampling, clustering-driven selection, and adaptive relabeling.
May 2024 - Sep 2024
Researched embodied intelligence trends and applied YOLOv8-based UI detection toward automated iPhone food-ordering workflows.
Education
2023 - 2028 · Five-year program with one year of co-op
Electrical & Computer Engineering (ECE)
Academic Service
Reviewer
Projects
Kaggle · BirdCLEF 2025 · Bronze Medal
Bronze Medal solution for BirdCLEF 2025, reaching Private Leaderboard Top 10% among 2,000+ teams with a 0.893 score.
Kaggle BirdCLEF 2025
Private leaderboard score
Private leaderboard
Teams worldwide
Rainforest soundscapes
Contact
I am broadly interested in Artificial Intelligence and its applications. I am currently open to Fall 2028 PhD opportunities in AI and related areas. I am always happy to connect with researchers, students, and practitioners with shared interests — feel free to reach out.