Michael Wornow
@MichaelWornow
Followers
342
Following
185
Statuses
117
Computer Science PhD Student @ Stanford
Stanford
Joined March 2023
RT @Zepeng_Huo: ๐ Excited to share that our latest research, ๐๐ช๐ฎ๐ฆ-๐ต๐ฐ-๐๐ท๐ฆ๐ฏ๐ต ๐๐ณ๐ฆ๐ต๐ณ๐ข๐ช๐ฏ๐ช๐ฏ๐จ ๐ง๐ฐ๐ณ 3๐ ๐๐ฆ๐ฅ๐ช๐ค๐ข๐ญ ๐๐ฎ๐ข๐จ๐ช๐ฏ๐จ, has been accepted at ๐๐๐๐ฅ 20โฆ
0
3
0
RT @NEJM_AI: In a Case Study, @MichaelWornow et al. investigate the accuracy, efficiency, and interpretability of using LLMs for clinical tโฆ
0
6
0
RT @zakkohane: Medical record to finding a clinical trial through AI? Using "out-of-the-box" "zero-shot" AI model @NEJM_AI
0
42
0
5/ A big thanks to my co-authors @BediSuhana42170 , Miguel Hernandez, Ethan Steinberg, @jasonafries , @sanmikoyejo , Chris Re, and @drnigam and support from @StanfordHealth @StanfordMed @HazyResearch !
0
3
5
RT @SehjKashyap: Great to see MAMBA architecture evaluated on EHR-related tasks and robust analysis of EHR context complexities in this newโฆ
0
1
0
RT @KhaledSaab11: Our approach to evaluating health AI models continues to evolve! (Phase 1) Medical Benchmarks โก๏ธ (Phase 2) Patient Actorโฆ
0
14
0
Grateful to work with an awesome team of co-authors including @Avanika15 @bviggiano_13 @ishanskhare @verma_tathagat and many more!
0
0
6
RT @NeelGuha: What's (1) a "drink of fresh fruit pureed with milk, yogurt, or ice cream" and (2) an unsupervised algorithm for test-time LLโฆ
0
22
0
RT @MayeeChen: Given open-ended generations from K different LLMs for an input, can we learn to select the best generation, without needingโฆ
0
19
0
RT @Avanika15: So excited to be launching @rox__ai with the incredible @IshanMkh, Diogo Ribeiro and @shriram_s. The Rox Agent Swarm is theโฆ
0
18
0
RT @ScienceMagazine: A new Science study presents โEvoโโa machine learning model capable of decoding and designing DNA, RNA, and protein seโฆ
0
444
0
RT @vishal_the_jain: Introducing VivaChat ๐ You can now video chat with realistic AI people! Weโre thrilled for video to make interactionsโฆ
0
20
0
RT @mzhangio: Ever wanted to scale subquadratic models up to 7B+ LLMs? But didn't want to pretrain billions of parameters on trillions of tโฆ
0
54
0