Peiqi Liu | 刘沛淇

I am a senior undergraduate student major in computer science at Peking University, advised by Prof. Hao Dong as a part of PKU-Agibot Lab.

Previously, I was a visiting student at MIT CSAIL, where I worked in the groups led by Prof. Leslie Pack Kaelbling and Prof. Josh Tenenbaum, advised by Jiayuan Mao. I also spent a semester on exchange at the University of California, Berkeley, and interned with the BAIR.

Always excited to discussing cool ideas and potential collaborations. Feel free to book a meeting with me!

Email  /  Github /  LinkedIn /  Book a Meeting

Actively seeking PhD opportunities for Fall 2026.

Research

My long-term research goal is to build human-like intelligence that can continually learn from experience and apply them for reasoning and planning in the physical world. The central theme of my research is to abstract reusable knowledge from data (internet, simulation, and embodied interaction data) and translate it into structured representations (scene maps, programs, affordance maps) that enhance model capability and enable more efficient task execution.

A framework for lifelong experience abstraction and planning that enables agents to learn and adapt continuously across different environments and tasks.

We propose a multi-object demand-driven navigation benchmark and train an coarse-to-fine attribute-based exploration agent to solve this task.

Experience

Template, Last updated: Nov 2025 © 2025 Peiqi Liu