Yiquan Li

I'm a CS PhD student at Northwestern University under supervision of Prof. Karan Ahuja. Before that, I was a CS major undergraduate student at UW, Madison and Hong Kong Polytechnic University.

Previously, I was fortunate to be supervised by Prof. Yin Li, Prof. Chaowei Xiao at UW, Madison. I also have the pleasure of collaborating with Yiming Li from New York University and Prof. Xiaolong Wang from UC, San Diego. And I was under the supervision of Prof. Bin Xiao at Hong Kong Polytechnic University.

Email  /  Scholar  /  Github

Research

I am interested in building autonomous models to interact with the physical world and creating interactive systems that enhance daily human life.

A framework to recover the geometry of 3D parametric scenes using very few depth measurements from low-cost, commercially available time-of-flight sensors.

Introduce Dex1B as a largescale, diverse, and high-quality demonstration dataset produced with generative models.

A flexible framework for adapting pre-trained Video LLMs to downstream tasks with side-channel signals, such as audio, 3D cues, or multi-view videos

A one-step denoising purficiation method leveraging consistency models.

Defending jaibreak attack through backdoor alignment.

A new 3D reconstruction method using low-cost single-photon cameras

A 3D point cloud adversarial attack for face recognization model by structural light.

Awards

Thanks to Jon Barron who created the website.