I'm a first-year PhD Student at Columbia University, immensely fortunate to be advised by Carl Vondrick. I also collaborate with the wonderful Andrew Owens.
My research lies primarily in computer vision & multimodal machine learning, while drawing close inspiration from cognitive science. I would like to scientifically study intelligence and its emergence.
Toddlers and other ecological organisms - new to their sensory bubble [umwelt] - acquire intelligence partially through evolution and self-play with the physical world. Instead of heavily relying on human supervision, I study such self-supervised machines that capitalize on unlabeled, multimodal sensory data (sight, sound, touch, smell!) and their natural synchronization.
Previously, I graduated from Columbia Engineering with a B.S. in Computer Science, where I was introduced to research by Shuran Song and teaching by Paul Blaer.
News
[2024 Sep]: Recent papers accepted to ECCV and CoRL 2024!
[2024 Feb]: pix2gestalt was accepted to CVPR 2024, as Highlight! gestalt.cs.columbia.edu
[2023 May]: Received Columbia's Andrew Kosoresow Memorial Award for Excellence in Teaching and Service.
Research
-
Dreamitate: Real-World Visuomotor Policy Learning via Video Generation Junbang Liang*, Ruoshi Liu*, Ege Ozguroglu, Sruthi Sudhakar, Achal Dave, Pavel Tokmakov, Shuran Song, Carl Vondrick
arXivPaperProject PageCode
CoRL 2024
-
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
ECCV 2024 (Oral)
-
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)
Teaching/Service
Teaching AssistantSpring 2023
Head Teaching AssistantSpring 2021, Summer B 2021, Fall 2021, Spring 2022, Spring 2023
Head Teaching AssistantSummer A 2021, Fall 2021, Summer A 2022, Fall 2022