Jay Thiagarajan (@jjayaram7) 's Twitter Profile
Jay Thiagarajan

@jjayaram7

Machine Learning Researcher. Science Enthusiast. Poetry Lover. "The creative adult is the child who survived"

ID: 1359972247

calendar_today17-04-2013 17:34:21

410 Tweet

373 Followers

902 Following

Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Is it just me or are the #neurips2023 reviews pretty harsh this time? Not even the scores. But the reasons given for low scores!!!

Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Here comes G-∆UQ, a scalable uncertainty quantification method for graph neural networks!! check the preprint and reach out to us if you want to try this or apply this to your problems!!

Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Happening now!! Stop by our #ICCV2023 Poster 064 in room Foyer Soud and learn about our work on limited angle CT reconstruction using diffusion models. Also do ping lead author Jiaming Liu who could not be here in person. Joint work with Rushil Ulugbek S. Kamilov #HyojinKim #AdityaMohan

Happening now!! Stop by our #ICCV2023 Poster 064 in room Foyer Soud and learn about our work on limited angle CT reconstruction using diffusion models. Also do ping lead author <a href="/Jiaming__Liu/">Jiaming Liu</a> who could not be here in person. Joint work with <a href="/RUSH1L/">Rushil</a> <a href="/ukmlv/">Ulugbek S. Kamilov</a> #HyojinKim #AdityaMohan
Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Super excited to present G-ΔUQ for improving GNN calibration under shifts at #ICLR2024 . Using stochastic centering and graph anchoring, G-ΔUQ achieves SoTA calibration in node and graph classifiers! Poster session 2 (Tue. 4.30 PM) - Halle B #253 Link: tinyurl.com/6usn2cj3

Super excited to present G-ΔUQ for improving GNN calibration under shifts at #ICLR2024 . Using stochastic centering and graph anchoring, G-ΔUQ achieves SoTA calibration in node and graph classifiers!
Poster session 2 (Tue. 4.30 PM) - Halle B #253
Link: tinyurl.com/6usn2cj3
Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Interested in using deep learned surrogates to close the gap between simulations and experiments? ✨ Our recent Machine Learning: Science and Technology paper provides new insights into transformer adaptation and model selection with extremely limited data!! ✨ Lawrence Livermore National Laboratory LLNL Computing

Sukhada (@appadappajappa) 's Twitter Profile Photo

Doing a giveaway of a Kindle copy of one of the most interesting books I read in the last couple of years. Just retweet this tweet to be eligible for the giveaway. One person chosen at random wins it - will announce winner at 8 PM tomorrow (14 June)✨

Doing a giveaway of a Kindle copy of one of the most interesting books I read in the last couple of years.

Just retweet this tweet to be eligible for the giveaway. One person chosen at random wins it - will announce winner at 8 PM tomorrow (14 June)✨
Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

✨⭐️✨If you are at #ICML2024, check out PAGER, a new approach for proactive failure detection in deep networks (both regression and classification)! Paper: tinyurl.com/pager-paper Session: tinyurl.com/pager-ICML Vivek Sivaraman Puja Trivedi Rushil LLNL Computing

✨⭐️✨If you are at #ICML2024,  check out PAGER, a new approach for proactive  failure detection in deep networks (both regression and classification)! 

Paper: tinyurl.com/pager-paper
Session: tinyurl.com/pager-ICML

<a href="/VivekSivaraman1/">Vivek Sivaraman</a> <a href="/puja_computes/">Puja Trivedi</a> <a href="/RUSH1L/">Rushil</a> 
<a href="/Livermore_Comp/">LLNL Computing</a>
Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Super elated that our paper on improving generalization using anchored ViTs accepted as a spotlight at #neurips2024. Excited about the potential opportunities of leveraging anchoring for large scale pre training and multimodal models

Jay Thiagarajan (@jjayaram7) 's Twitter Profile Photo

Interested to learn about anchored transformers? Stop by our spotlight poster at the East Exhibit Hall A-C #2006 today at 4.30 PM #NeurIPS2024