Yifei Zhou

About

Yifei Zhou is a rising researcher at the intersection of robotics, computer vision, and neuromorphic computing. Their work primarily focuses on enabling intelligent systems to perceive, learn, and act in complex, open-world environments. Zhou’s key contributions include developing the KALIE framework, which fine-tunes vision-language models for robotic manipulation without requiring any robot data—a breakthrough that allows generalist robots to handle novel objects in unstructured settings. They have also advanced sensor fusion with the YOLO-SCG and point cloud clustering method for robust object detection and obstacle avoidance. In the domain of brain-inspired computing, Zhou has investigated spike-timing dependent plasticity mechanisms for context-dependent learning in spiking neural networks, and explored masked autoencoders for enhanced EEG data representation. With their most-cited work already garnering attention, Zhou’s research is paving the way for more adaptive, perceptive, and autonomous robotic systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Object Detection and Information Perception by Fusing YOLO-SCG and Point Cloud Clustering

   6 citations · 2024
2. 2
   Enhancing Representation Learning of EEG Data with Masked Autoencoders

   2 citations · 2024
3. 3
   Investigation of Pair and Triplet-Based Spike-Timing Dependent Plasticity Mechanism for Spiking Context-Dependent Learning

   2 citations · 2023
4. 4
   KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation Without Robot Data

   2 citations · 2025
5. 5
   KALIE: Fine-Tuning Vision-Language Models for Open-World Manipulation without Robot Data

   2 citations · 2024

Key Collaborators

Contact & Links