Julia Chae

Julia_headshot2.png

I study how large vision and multimodal models can become more fine-grained, specialized, and useful for real-world and scientific applications.

I’m a PhD student in EECS at MIT CSAIL, advised by Sara Beery. I collaborate closely with Adobe Research, primarily with Cusuh Ham and Richard Zhang. Previously, I studied EngSci at the University of Toronto, working with Sanja Fidler, Florian Shkurti, and Steven Waslander. I co-organize MLTea at MIT.

research interests

I'm currently thinking a lot about:

  • Fine-Grained Perception: Improving how vision and multimodal models distinguish subtle visual differences, particularly by leveraging specialized or synthetic data, or expert knowledge & feedback.
  • Multimodal Representations: Understanding how models organize visual and semantic knowledge across modalities, and how the structure of their representations shapes their capabilities and specialization
  • AI for Scientific Discovery: Accelerating scientific data curation and discovery with multimodal AI models.

news

Oct 2026 Received Honorable Mentions on the MIT Open Data Prize.
Sept 2026 Led the organization of the third CV4E Workshop at ECCV in Molmo.
June 2026 Presented our paper, ID-Sim: An Identity-Focused Similarity Metric, at CVPR 2026 in Denver!
May 2026 Started my internship at Adobe Research in SF working on multimodal embeddings, mentored by Cusuh Ham and hosted by Richard Zhang.
Jan 2026 Gave talks on Interactive Discovery in Large-Scale Biodiversity Databases at Google-MIT lightning talks and the MIT Global Teaching Labs workshop.
Oct 19, 2025 Excited to attend ICCV 2025, co-organize the 2nd CV4Ecology Workshop, and present our PRPG poster at the Instance-Level Recognition and Generation Workshop.
Jun 1, 2025 Started an internship at Adobe Research working on designing a fine-grained visual perceptual metric (w/ mentor Cusuh Ham)
May 28, 2025 Completed my Master of Science (SM) degree at MIT 🎓
Apr 22, 2025 Attending ICLR in Singapore to present Personalized Representation from Personalized Generation (PRPG) at the main conference!
Mar 5, 2025 Gave a talk at Cohere (See recording here)
Jan 22, 2025 Our paper, Personalized Representation from Personalized Generation was accepted to ICLR 2025!
Jan 6, 2025 Served as an instructor for the three-week intensive Computer Vision for Ecology Workshop at Caltech Resnick Sustainability Institute
Sep 30, 2024 Co-Organized 1st ever CV4E Workshop at ECCV in Milan!