In the content attribute of the

I am a Research Associate at Columbia University, immensely fortunate to be advised by Carl Vondrick.

My research interests lie primarily in learning-based Computer Vision. More specifically, I enjoy building models that emulate the abilities toddlers - new to their visual environment - naturally acquire and curiously self-teach. I am hence also interested in leveraging multi-modal (auditory, tactile, olfactory!) signals complementary to and in the absence of vision. I believe that such models can creatively reconstruct, efficiently generalize, and playfully interact.

Previously, I graduated from Columbia Engineering with a B.S. in Computer Science, where I was introduced to research by Shuran Song and Carl Vondrick.


[2024 Feb]: pix2gestalt was accepted to CVPR 2024 as Highlight!

[2023 Sep]: Started as a (pre-doctoral) Research Associate (Staff Associate I) at Columbia University, Department of Computer Science.

[2023 May]: Received the Andrew Kosoresow Memorial Award for Excellence in Teaching and Service.


  • pix2gestalt: Amodal Segmentation by Synthesizing Wholes Ege Ozguroglu, Ruoshi Liu, Dídac Surís, Dian Chen, Achal Dave, Pavel Tokmakov, Carl Vondrick
    arXivPaperProject PageCode
    CVPR 2024 (Highlight)
  • Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis Basile Van Hoorick, Rundi Wu, Ege Ozguroglu, Kyle Sargent, Ruoshi Liu, Pavel Tokmakov, Achal Dave, Changxi Zheng, Carl Vondrick
    arXivPaperProject PageCode
    arXiv 2024


I spent the majority of my undergraduate years learning to help teach, with the great Paul Blaer as my teaching mentor here. I am nostalgic of each wonderful iteration, listed below.

Computer Vision II: Learning (COMS 4732)
Teaching Assistant
Spring 2023
Data Structures & Algorithms (COMS 3134)
Head Teaching Assistant
Spring 2021, Summer B 2021, Fall 2021, Spring 2022, Spring 2023
Introduction to CS and Programming (COMS 1004)
Head Teaching Assistant
Summer A 2021, Fall 2021, Summer A 2022, Fall 2022