Fatemeh Ghezloo

Sr. Applied Scientist @Microsoft
PhD @UW @uwcse

[Fatemeh Ghezloo @fghezloo]

🤖🩺 Introducing PathFinder: A multi-agent system that navigates WSIs akin to pathologists, collecting findings towards interpretable diagnosis. It achieves 74% accuracy on melanoma diagnosis, outperforming experts by 9%!

🌎: https://t.co/s6yLlLGJ7n
📰: https://t.co/1GWdxuxbyN

[Sina Malakouti @ ICLR 2026 @MalakoutiSina]

📢 Can AI understand how to persuades us?

We are excited to announce the Visual Persuasion (VisPer) workshop at @eccvconf  

📄 Submit your work and join us in Malmö 🇸🇪!

⏳Deadline: July 15, 2026
🔗https://t.co/E9RWKRO70L

Topics include (but not limited to):
✨ Visual persuasion & communication
✨ Multimodal reasoning
✨ Personalization
✨ Persuasive image & video generation
✨ Creativity, symbolism & metaphor
✨ Evaluation and benchmarks for visual persusion
✨ Advertisement understanding and generation
✨ Ethics and cultural impact in persuasion
✨ Detection of manipulative content

#ECCV2026

[Fatemeh Ghezloo @fghezloo]

Looking forward to presenting my work on multimodal pathology and diagnostic AI with the Cohere Labs ML Healthcare community next week.

[Cohere Labs @Cohere_Labs]

Our ML Healthcare group is excited to host @fghezloo, Senior Applied Scientist at Microsoft AI on November 21st. Fatemeh will introduce Quilt-1M, a large-scale vision-language pathology dataset; Quilt-LLaVA, a multimodal model for spatially grounded medical reasoning; and PathFinder, a multi-agent system modeling pathologists’ diagnostic behavior—collectively advancing interpretable, data-centric AI for scalable clinical diagnostics. 🏥

Thanks to @AnasZaf79138457, @LeemaMurali and @oumayma_es_ for organizing this event!

Learn more: https://t.co/hsnA4IAQDX

[Fatemeh Ghezloo @fghezloo]

📢Excited to present PathFinder at #ICCV2025 !

📍 Where to find us:
📅 Oral Presentation: “Multi-Modal Foundation Models for Cancer Detection & Prevention” Workshop, Sunday, Oct 19 at 4:40 PM, Room 326 B

📅 Main Conference Poster: Thursday, Oct 23 (AM) Poster #342

[Fatemeh Ghezloo @fghezloo]

🤖🩺 Introducing PathFinder: A multi-agent system that navigates WSIs akin to pathologists, collecting findings towards interpretable diagnosis. It achieves 74% accuracy on melanoma diagnosis, outperforming experts by 9%!

🌎: https://t.co/s6yLlLGJ7n
📰: https://t.co/1GWdxuxbyN

[Fatemeh Ghezloo @fghezloo]

Extremely thankful to my incredible coauthors and their contribution to this work: @mehsaygin, @rusor_, @wizdom_dominic, @beibin79, Tejoram Vivekanandan, Joann Elmore, @RanjayKrishna and @lindashapiro.

Our code, data, and models will be available soon, so stay tuned! 9/9

[Fatemeh Ghezloo @fghezloo]

🤖🩺 Introducing PathFinder: A multi-agent system that navigates WSIs akin to pathologists, collecting findings towards interpretable diagnosis. It achieves 74% accuracy on melanoma diagnosis, outperforming experts by 9%!

🌎: https://t.co/s6yLlLGJ7n
📰: https://t.co/1GWdxuxbyN

[Fatemeh Ghezloo @fghezloo]

This marks the first time an AI model has surpassed the consensus-level accuracy of pathologists on this task. Additionally, thanks to its agentic design, PathFinder provides explainable insights at each step by describing visited patches and how they inform final diagnosis. 8/9

[Mehmet Saygın Seyfioğlu @mehsaygin]

Just presented Quilt-LLaVA @CVPR with @wizdom_dominic and @fghezloo! Huge thanks to everyone who stopped by to chat with us!

[Mehmet Saygın Seyfioğlu @mehsaygin]

Excited to present Quilt-LLaVA https://t.co/Snm8ZzeBH6 with my co-leads @wizdom_dominic and @fghezloo @CVPR tomorrow! Join us at the poster session from 10 AM to 12 PM in ARCH 4A-E #342

[Jia-Bin Huang @jbhuang0604]

How to write the Introduction?

As a junior student, writing the introduction of a research paper is arguably the most daunting part of paper writing. 😱

Here is a simple template I find useful:

3 Figures 🖼️ + 5 Questions 🤔

[Mehmet Saygın Seyfioğlu @mehsaygin]

Excited to share that Quilt-LLaVA has been accepted at @CVPR! As promised, we are making our model, datasets, and training scripts available to the community: https://t.co/Snm8ZzeBH6

See you all in Seattle!
@wizdom_dominic @fghezloo @RanjayKrishna @lindashapiro

[Ranjay Krishna @RanjayKrishna]

We are open sourcing Quilt-LLaVA: a large vision-language assistant for histopathology. Quilt-LLaVA can support pathologists by engaging in dialogue as they examine whole-slide images. It's build on top of QUILT and QUILT-NET, which we released earlier this year.

It's built on top of QUILT and QUILT-NET, which is the largest open-sourced histopathology dataset we released earlier this year.

[Fatemeh Ghezloo @fghezloo]

🚨Check out our latest preprint building up on Quilt-1M (https://t.co/WaY2THb21P) where we introduce a large vision language histopathology agent with reasoning and spatial awareness capabilities. Code and data coming soon!

See our website for more info:
https://t.co/PQO1Mc7DA1

[Mehmet Saygın Seyfioğlu @mehsaygin]

Introducing Quilt-LLaVA, a Large Language and Vision Assistant for #Pathology trained with spatially localized instruction tuning data generated from educational #YouTube videos, outperforming SOTA in various tasks.

🌎: https://t.co/vqLYKD7SAx
📜: https://t.co/l5tvpo401U
A 🧵:

[Fatemeh Ghezloo @fghezloo]

I'm presenting our work (https://t.co/ctPOGgLotv) at #NeurIPS2023 with @wizdom_dominic and @mehsaygin.
🗣️ Oral Session: Ballroom A - C (level 2) on Wednesday, DEC 13 at 3:30 PM
🖼️ Poster Session: Great Hall & Hall B1+B2 (level 1) Poster #301 on Wednesday, DEC 13th at 5:00 PM

[Fatemeh Ghezloo @fghezloo]

🔍 Checkout our recent work: Quilt-1M, a multimodal histopathology dataset curated from Youtube. Excited to see how this extensive resource will advance research in the field!

[Ranjay Krishna @RanjayKrishna]

Our submission received my first ever 10/10 review from NeurIPS. Check out our #NeurIPS2023 Oral.

We release the largest vision-language dataset for histopathology and train a SOTA model for classifying histopathology images across 13 benchmarks across 8 sub-pathologies.