cyrilzakka Profile Banner
Cyril Zakka, MD Profile
Cyril Zakka, MD

@cyrilzakka

Followers
6K
Following
5K
Media
449
Statuses
7K

Health Lead x @Huggingface | Medical Doctor & ML Researcher. Prev: @Stanford

Joined December 2013
Don't wanna be here? Send us removal request.
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
2 years
There’s been a lot of buzz surrounding multimodal LLMs in medicine. At the @HiesingerLab we’ve been building Almanac Chat for over 6 months alongside our collaborators and we’re excited to showcase the first preview!. • Almanac Chat is the first truly multimodal medical LLM
16
56
345
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
2 days
RT @abidlabs: and it's out!
Tweet media one
0
3
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
7 days
So many great releases today, with a new medical model to boot! 27B multimodal MedGemma featuring my all-time favorite encoder:
@osanseviero
Omar Sanseviero
@osanseviero
7 days
🏥Introducing MedGemma, part 2, including:. 🔥A 27B multimodal MedGemma.👀MedSigLIP, a lightweight image/text encoder for medical image retrieval/classification.📜A technical report with details. Blog: Paper:
Tweet media one
0
2
20
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
7 days
RT @abhinadduri: We updated the State Embedding 600M checkpoint on the @ArcInstitute Hugging Face. This model was trained with 4x FLOPs com….
0
9
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
7 days
RT @Michael_D_Moor: Want to do a postdoc in my research group? . I can support one ETH Postdoc fellowship applicati….
0
10
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
8 days
RT @ClementDelangue: We just released the best 3B model, 100% open-source, open dataset, architecture details, exact data mixtures and full….
0
244
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
8 days
RT @LoubnaBenAllal1: Introducing SmolLM3: a strong, smol reasoner!. > SoTA 3B model.> dual mode reasoning (think/no_think).> long context,….
0
197
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
15 days
RT @victormustar: Sad news: HuggingChat is gone 😢.It was a wild adventure. 🔹20+ Open Source models .🔹1M+ users.🔹100k+ assistants created….
0
14
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
16 days
RT @abidlabs: Why would you create an MCP server??. When you could create a UI, API, and MCP server all with the same Python code? https://….
0
6
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
16 days
RT @reach_vb: @Yuchenj_UW no matter when it drops it'll be at
0
2
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
16 days
RT @Michael_D_Moor: 🚨New preprint! 🚨In-context learning (ICL) is the intriguing ability of LLMs to learn to solve tasks purely from context….
0
20
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
20 days
RT @nalidoust: I f*** love this. And to put even more momentum behind this awesome movement by our @arcinstitute friends:. 🥁@tahoe_ai will….
0
12
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
23 days
Great new model from the @arcinstitute. Model links here: ...
@arcinstitute
Arc Institute
@arcinstitute
23 days
Introducing Arc Institute’s first virtual cell model: STATE
Tweet media one
1
1
14
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
27 days
RT @MarkDSiegel1: Excellent commentary, @cyrilzakka. Fascinating implications for teaching residents. @TradIMYale.
0
1
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
27 days
RT @zakkohane: Very good point. But the cognitive impact of technology is a recurrent question over at least the last 75 years (more recent….
0
8
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
27 days
RT @AdamRodmanMD: Unsurprisingly @cyrilzakka says it better than I could. These are the exact concerns I have about the way we are integr….
0
18
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
27 days
Link to paper: PDF:
0
0
6
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
27 days
There's a lot to be said on this newest preprint showing that reliance on LLMs in writing tasks leads to a 'consistent underperformance' in neural and behavioral levels with potential long-term consequences. Interestingly, I think this ties to similar but (early)
Tweet media one
6
12
59
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
30 days
RT @reach_vb: Your AI just got a MAJOR upgrade - psyched to partner with @GroqInc to bring blazingly fast inference on select Hugging Face….
0
24
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
1 month
RT @zakkohane: Excited to share results of the SHEPHERD program "Few shot learning for phenotype-driven diagnosis of patients with rare gen….
0
11
0
@cyrilzakka
Cyril Zakka, MD
@cyrilzakka
1 month
RT @tsounack: Very excited to share the release of BioClinical ModernBERT!. Highlights:.- biggest and most diverse biomedical and clinical….
0
13
0