Muzaffar Qureshi
Papers
2
Total Citations
16
H-Index
2
About
Muzaffar Qureshi is a rising star in robotics, whose work is redefining how robots perceive and interact with the physical world. His research centers on two critical frontiers: bridging the simulation-to-reality (sim2real) gap and advancing intelligent visual servoing. In his seminal 2025 paper, "SplatSim," Qureshi introduces a groundbreaking framework that leverages 3D Gaussian Splatting to achieve zero-shot sim2real transfer for RGB-based manipulation policies. This work, already garnering 11 citations, directly tackles the visual domain shift that has long plagued robotic learning, enabling policies trained purely in simulation to deploy seamlessly in the real world without fine-tuning. Complementing this, his 2024 work "Imagine2Servo" (5 citations) revolutionizes visual servoing by integrating diffusion-driven goal generation, eliminating the traditional need for a pre-captured target image at test time. This innovation allows robots to autonomously imagine and servo toward task-specific goals, vastly expanding their operational flexibility. Together, these contributions position Qureshi as a leading voice in data-efficient, generalizable robotic control, with his work promising to accelerate the deployment of dexterous, vision-based robots in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2