4th @NeurIPS2022 Workshop: Shared Visual Representations in Human and Machine Intelligence. Organizers: @ArtDeza @joshuacpeterson @apurvaratan @cocosci_lab
New Orleans, Louisiana
Joined July 2019
- Tweets380
- Following864
- Followers661
- Likes2.1K
Pinned Tweet
And that’s a wrap for this year! Thanks for supporting us and do reach out to tell us about things you liked and things we could improve upon. Until next year!
SVRHM 2022 Workshop retweeted
🎉 Exciting News! 🎉 I'm thrilled to announce that I will be joining #GeorgiaTech as an Assistant Professor starting Jan 1, 2024! I'm actively recruiting members to join the lab. So please spread the word! The lab website also goes live today.
murtylab.com/
SVRHM 2022 Workshop retweeted
Personally I'd suggest a 6 month moratorium on people overreacting to LLMs (in either direction)
a big deal: @elonmusk, Y. Bengio, S. Russell, @tegmark, V. Kraknova, P. Maes, @Grady_Booch, @AndrewYang, @tristanharris & over 1,000 others, including me, have called for a temporary pause on training systems exceeding GPT-4 futureoflife.org/open-letter…
SVRHM 2022 Workshop retweeted
It's surprisingly how little there is on "how to run a research group."
Lots of great resources on being a researcher (eg. You and Your Research), and on leading other types of teams (eg. books on software engineering management). Research leadership seems like an open problem.
SVRHM 2022 Workshop retweeted
Looking forward to reading this paper from @skornblith and colleagues on human alignment of neural network representations:
arxiv.org/abs/2211.01201
tl;dr: objective fn and dataset have a larger impact than architecture and scale, so scale isn't all you...
SVRHM 2022 Workshop retweeted
looking forward to the first video of a tesla trying to drive directly through it
The display behind the truck shows the front so that you can decide to overtake it... #CES
Congratulations to @wenxuan_guo_ & @TalGolanNeuro for the @CSM_ai Best Paper Award on Distinguishing Representational Geometries with Controversial Stimuli (Achieving the highest score from all papers, including a perfect 10!) with @SchuettHeiko @NKriegeskorte
@KriegeskorteLab
Congratulations to @dfinz for the NeuroAI Best Paper Award Sponsored by @NVIDIA for her paper: "Topographic DCNNs trained on a single self-supervised task capture the functional organization of cortex into visual processing streams" @eshedmargalit @cvnlab @dyamins K.Grill-Spector
SVRHM 2022 Workshop retweeted
#NeurIPS2022 is not over yet ! Today (3.30 pm CST) I'll give a short online talk on our - w/ Ulisse Ferrari, Peter Neri (@lsp_ens) and @RetinaGeek - approach for the Sensorium Competition on modeling mice V1, which allowed us to finish 3rd 🐭
Join us tomorrow for the #NeurIPS online workshop about our Sensorium competition!
There'll be talks by the Sensorium team, as well as talks by the winners and two keynotes by @neurograce and @DeanPospisil.
Tomorrow (Tue, Dec 6) from 1 - 3.30 PM PST
neurips.cc/virtual/2022/comp…
SVRHM 2022 Workshop retweeted
It was great to meet in person again at @SVRHM_workshop! In this thread, I briefly describe our SVRHM paper (openreview.net/forum?id=a3YP…), for which @wenxuan_guo_ (equal-co-1st), @SchuettHeiko, @KriegeskorteLab, and I won the @CSM_ai best paper award. 1/13
SVRHM 2022 Workshop retweeted
🧵 Introducing Torchlens, a package for extracting & mapping the results of every intermediate step in any PyTorch model in 1 line of code ("every" & "1" mean just that; "any model" is the goal 🤞) 1/
GitHub:
github.com/johnmarktaylor91/…
CoLab Demo:
colab.research.google.com/dr…
SVRHM 2022 Workshop retweeted
Come see our work on Homomorphic Self Supervised Learning today at the @NeurIPSConf SSL workshop! Stemming from my internship at Apple with Xavier Suau and Luca Zappella, we explored the synergistic relationship between equivariant backbones and SSL: arxiv.org/abs/2211.08282
ALT We show an equivalence between augmentation-based self-supervised learning losses and self-supervised learning with equivariant backbone feature extractors which we call Homomorphic self-supervised learning.
A relevant Mid-Level Vision Toolbox developed by @DirkBWalther 's group that popped up during his talk earlier today! : github.com/bwlabToronto/MLV_…
The second invited Oral presentation will be delivered by @TalGolanNeuro and @wenxuan_guo_ from @Columbia. Distinguishing representational geometries with controversial stimuli: Bayesian experimental design and its application to face dissimilarity judgments. #SVRHM2022