Neda Tavakoli

Ph.D. in Computer Science @GeorgiaTech, working on scalable and parallel algorithms for computational biology

[Neda Tavakoli @Neda_TV]

Thank you @radiology_rsna for the opportunity. @RadiologyEditor @ZahraShakerii @BedayatArash @ulasbagci @HsiaoMDPhD @MRAguy @JamesCCarrMD @a_rahsepar @NURadiology @UofT_dlsph @ihpmeuoft @RadiologyUcla @UCDRadiology @UCSDImaging @MayoRadiology

[@RadiologyEditor @RadiologyEditor]

🧠🤖 Foundation models are shaking up medical imaging! @Neda_TV et al show how these models streamline workflows, boost accuracy, personalize care, & generate synthetic images. For real impact, we need trust, explainability, & integration! #AI #Radiology
https://t.co/JsVwek2hu1

[Northwestern Radiology @NURadiology]

🚨 New in @Radiology_RSNA: Dr. Dan Kim & Dr. Neda Tavakoli @Neda_TV from @NUFeinbergMed explore how GPT-4 can auto-generate complete clinical histories from EHRs.
📰 https://t.co/bEH0IvP8mH
#Radiology #AIinHealthcare #LLMs #GPT4 #RSNA #MedicalAI

[Neda Tavakoli @Neda_TV]

@GTCSE @Jay4w @gtcomputing @GTResearchNews @GeorgiaTechAI @mlatgt @PoloDataClub @acm_chi @sigchi @vsarkar_gt @ForbesUnder30 @OpenAI Congrats @Jay4w, very well-deserved!🥳

[Neda Tavakoli @Neda_TV]

@MHaghshomar Congratulations, Maryam!🥳

[Northwestern Radiology @NURadiology]

In February we feature Northwestern's #cardiovascular and #thoracic imaging research. Neda Tavakoli uses #AI in cardiac analysis. @Neda_TV #CV #MRI

[Neda Tavakoli @Neda_TV]

@gt_sci @gtcomputing Congratulations! Very well deserved!

[Northwestern Radiology @NURadiology]

Dr. @Neda_TV and Dr. Daniel Kim have published in Radiology, "AI-generated Clinical Histories for Radiology Reports: Closing the Information Gap."
It explores how GPT-4 is transforming radiology workflows by generating AI-powered clinical histories.
#AI #MedicalInnovation

[Radiology @radiology_rsna]

In this targeted editorial, Drs. Tavakoli (@neda_tv) and Kim of @NURadiology comment on the use of generative AI to synthesize critical clinical information from complex health record data. https://t.co/vKJdJvtSKb

[Neda Tavakoli @Neda_TV]

🚨 Excited to share our latest publication in the highly prestigious journal Radiology! 🚨

📖 "AI-generated Clinical Histories for Radiology Reports: Closing the Information Gap"

Proud to collaborate with Dr. Daniel Kim! 🚀🔬

#AI #Radiology #NURadiology

[Northwestern Radiology @NURadiology]

Don't miss presentations by Neda Tavakoli, Maria Davo Jimenez, Cagdas Topel, Thara Nallamothu, and David Dushfunian on Saturday at #SCMR2025. @SCMRorg @DavidDushfunian @Neda_TV @cagdastpl

[Neda Tavakoli @Neda_TV]

@NURadiology

[Neda Tavakoli @Neda_TV]

🎉Honored to receive the Radiology Editor’s Recognition Award for Reviewing with Distinction from @RSNA! Grateful to Dr. Linda Moy and the editorial team for this recognition. Proud to contribute to advancing research in medical imaging! 🙏 #Radiology #RSNA #MedicalImaging

[Northwestern Radiology @NURadiology]

Read the commentary of Dr. Rahsepar and Dr. Kim on how cutting-edge high-field-strength scanners are opening new possibilities in noninvasive coronary imaging. Check it out in the latest issue of Radiology! https://t.co/t3LbpXeyMe #CardiacImaging #MRI #Radiology

[Radiology @radiology_rsna]

In this targeted editorial, Drs. @a_rahsepar and Kim discuss the potential clinical applications of high-field-strength (5-T) coronary MR angiography. https://t.co/rWUBnXDBy1

[Jian Ma @jmuiuc]

I'm sharing a public version of my talk slides @UCLA_CGSI two weeks ago - an update from my #LLMs #compbio Primer talk last year - w/ a focus on genomics FMs (DNA, scRNA). As we're exploring related topics, we remain very interested but also skeptical. 1/3 https://t.co/FIpLrvrBH3

[Christopher Potts @ChrisGPotts]

An LLM memorization riddle: A Pythia-6.9B checkpoint generates the following Output, which occurs only 1 time in the Pile. Is this a verbatim memorization?

[Neda Tavakoli @Neda_TV]

@EsiSeraj @Binazir_bfk @amazon Congratulations!🎊🎉 Very well deserved!

[James Zou @james_y_zou]

⚡️This is the most fun project!

We built PyTorch-for-text! 🔥
#TextGrad: automated "differentiation" via text to optimize AI systems by backpropagating LLM text feedback.

TextGrad + GPT4o:
💻LeetCodeHard best score
❓GPQA sota
🧬Designs new molecules
🩺Improves treatments 🧵

[Northwestern Radiology @NURadiology]

Recognizing Dr. Amir Ali Rahsepar who joined our team a few months ago. He completed his residency in diagnostic radiology at Yale New Haven Health, Bridgeport Hospital, and his fellowship in Cardiothoracic imaging at UCLA. Glad to have you with us, Dr. Rahsepar! @NorthwesternMed

[AK @_akhaliq]

Autoregressive Model Beats Diffusion

Llama for Scalable Image Generation

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative