Maya Varma
@mayavarma23
Followers
106
Following
45
Statuses
20
@Stanford CS PhD student // @KnightHennessy, @NDSEG, & @QuadFellowship
Stanford, CA
Joined October 2020
(1/4) Excited to share RaVL, which is appearing this week at #NeurIPS2024! RaVL discovers and mitigates spurious correlations in fine-tuned vision-language models (VLMs). 📄 Paper: 💻 GitHub:
1
5
16
RT @Dr_ASChaudhari: 1/ Updates on our improved open-source CheXagent with new transparent benchmarks! We ran a new reader study mimicking r…
0
7
0
0
0
1
RT @IAMJBDEL: So proud of the release of the GREEN metric. See what you can do when you merge medical AI research and open-sourceness. 26,…
0
10
0
RT @loublanks: 🧙 Excited to introduce Merlin, a vision language foundation model for 3D computed tomography 🐈⬛🩻 Trained to understand 3D…
0
38
0
RT @curtlanglotz: Five years ago, thanks to the leadership of @mattlungrenMD, @stanfordAIMI released the CheXpert images: 223K JPG CXRs wit…
0
35
0
RT @JB38076320: 🧵[1/3]🚀Exciting news from AIMI! We're leading the charge in #ClinicalTextGeneration with two pivotal tasks at #BioNLP2024 &…
0
4
0
RT @zhjohnchan: ⭐️ Excited to share our latest work about AI in healthcare. We present CheXagent, a foundation model for Chest X-ray interp…
0
28
0
RT @simran_s_arora: Ran out of OpenAI credits?💰 We present a prompting strategy that enables open-source and off-the-shelf GPT-J-6B to outp…
0
108
0
Excited to share Domino, which is appearing as an oral at #ICLR22! We use cross-modal embeddings to identify & describe systematic errors in ML models. 📜: Joint work w/ @EyubogluSabri @KhaledSaab11 @jdunnmon @james_y_zou @HazyResearch & others!
Do you ever wonder if your model - despite logging impressive accuracy - is still failing on an important but unknown slice of your dataset? We certainly do! Stoked to share recent work @iclr22 in which we develop & evaluate ~slice discovery methods~ (1/7)
1
2
5
RT @MayeeChen: New preprint alert! 📣 How do we produce transferable and robust representations with supervised contrastive learning? We n…
0
55
0
RT @m_leszczy: New preprint alert! 📣 How do we improve long-tailed performance of entity retrieval? We use a supervised contrastive loss…
0
25
0
(6/6) A model pretrained on this dataset and injected with structural knowledge improves disambiguation of rare entities by between 2.5 and 57 accuracy points across two benchmark datasets!
0
0
0