Sign in

Erin Grant

@eringrant.me
5.6K followers 1.5K following 33 posts

Assistant Professor @ualberta.bsky.social & Fellow @amiithinks.bsky.social studying cognition in mind & brain with neural nets, Bayes, and other tools (eringrant.github.io). elsewhere: sigmoid.social/@eringrant, twitter.com/ermgrant @ermgrant

PostsRepliesMedia
Reposted by Erin Grant
Eleanor Holton @eleanor-holton.bsky.social · 31/07/2026
So thrilled to be joining the Psychology Department at @columbiauniversity.bsky.social as an assistant prof next summer! I'll be recruiting for PhD/postdoc to start in Autumn 2027, so if you're interested in using computational approaches to studying human cognition please get in touch!
1312218
Erin Grant @eringrant.me · 01/05/2026
Yes :)
040
Reposted by Erin Grant
Badr AlKhamissi @bkhmsi.bsky.social · 27/04/2026
Good morning #ICLR2026 ☀️ The Re-Align workshop kicks off in under an hour! A full day on what we can actually do with representational alignment, from brains to language models to agents. Schedule in the thread 👇
1112
Reposted by Erin Grant
Andrew Saxe @saxelab.bsky.social · 02/04/2026
Very excited by this year's Analytical Connectionism Summer School! A dream lineup of speakers on the topic of language acquisition in minds and machines Bursaries available to cover costs Aug 17 – Aug 28, 2026 Gothenburg Details: www.analytical-connectionism.net//school/2026/
0172
Reposted by Erin Grant
Stefano Sarao Mannelli @stefsm.bsky.social · 25/02/2026
Join us! We are opening many postdoc positions both in London and in Gothenburg! London 🔗https://www.lesswrong.com/posts/GTt33CasvWjxxazJw/hiring-principia-research-fellows 📅 deadline: March 26th Gothenburg 🔗 www.chalmers.se/en/about-cha... 📅 deadline: April 1st
chalmers.se
Vacancies
Phone +46-317721000Mail addressChalmers University of Technology412 96 GothenburgE-mail and more contact informationOrganisation number 556479-5598
063
Reposted by Erin Grant
Andrew Saxe @saxelab.bsky.social · 16/02/2026
Excited to launch Principia, a nonprofit research organisation at the intersection of deep learning theory and AI safety. Our goal is to develop theory for modern machine learning systems that can help us understand complex network behaviors, including those critical for AI safety and alignment. 1
19428
Reposted by Erin Grant
Debbie Yee @debyee.bsky.social · 28/01/2026
#CCN2026 Proceedings submissions are open and due in *two* weeks! Info about how to submit in the thread below👇 Come share your science and hang out in NYC in August. :)
021
Erin Grant @eringrant.me · 07/12/2025
@dataonbrainmind.bsky.social starting now in Room 10 with opening remarks from @crji.bsky.social and the first invited talk from @dyamins.bsky.social!
Cathy gives the opening remarks.Dan gives the opening invited talk.
0113
Erin Grant @eringrant.me · 06/12/2025
Thrilled to start 2026 as faculty in Psych & CS @ualberta.bsky.social + Amii.ca Fellow! 🥳 Recruiting students to develop theories of cognition in natural & artificial systems 🤖💭🧠. Find me at #NeurIPS2025 workshops (speaking coginterp.github.io/neurips2025 & organising @dataonbrainmind.bsky.social)
410928
Reposted by Erin Grant
Dan Goodman @neural-reckoning.org · 27/11/2025
Nature Sci Rep publishes incoherent AI slop. eLife publishes a paper which the reviewers didn't agree with, making all the comments and responses public with thoughtful commentary. One of these journals got delisted by Web of Science for quality concerns from not doing peer review. Guess which one?
Two posts from Bluesky. The first one shows a figure from a paper published in Nature Scientific Reports full of totally incoherent AI fabricated gibberish words. The other a comment on a recently published paper by eLife discussing the paper and its peer reviews which were published along with the paper.
415568
Reposted by Erin Grant
Diana Cai @dianarycai.bsky.social · 07/11/2025
I'm on the academic job market! I design and analyze probabilistic machine-learning methods---motivated by real-world scientific constraints, and developed in collaboration with scientists in biology, chemistry, and physics. A few highlights of my research areas are:
Probabilistic ML in scientific pipelines
23914
Reposted by Erin Grant
Blake Bordelon @frostedblakess.bsky.social · 23/10/2025
Applying to do a postdoc or PhD in theoretical ML or neuroscience this year? Consider joining my group (starting next Fall) at UT Austin! POD Postdoc: oden.utexas.edu/programs-and... CSEM PhD: oden.utexas.edu/academics/pr...
13211
Reposted by Erin Grant
Alona Fyshe @alonaf.bsky.social · 31/10/2025
I'm hiring (another) post doc, this time in collaboration with Natalie Brito @nataliebrito.bsky.social at Columbia! We will be exploring some of the characteristics of human development using deep learning models. Email with questions! iaejup.fa.ocs.oraclecloud.com/hcmUI/Candid...
iaejup.fa.ocs.oraclecloud.com
Postdoctoral Fellow - Large Language Models as Models for Human Development
This position is part of the Post Doctoral Fellows Association and has an initial appointment of two years. This position has a comprehensive benefits package. Location - This role is in-person at Nor...
084
Erin Grant @eringrant.me · 03/10/2025
Hoping you find out and share! 🤗
000
Erin Grant @eringrant.me · 23/09/2025
Congrats Richard!!
010
Reposted by Erin Grant
Alona Fyshe @alonaf.bsky.social · 15/09/2025
I am hiring a post doc at UAlberta, affiliated with Amii! We study language processing in the brain using LLMs and neuroimaging. Looking for someone with experience with ideally both neuroimaging and LLMs, or a willingness to learn. Email me with Qs apps.ualberta.ca/careers/post...
apps.ualberta.ca
Postdoctoral Fellow - Language Models and Neuroscience - Careers@UAlberta.ca
University of Alberta: Careers@UAlberta.ca
0147
Reposted by Erin Grant
Jacob Zavatone-Veth @jzv.bsky.social · 04/09/2025
Since I'm back on BlueSky - with @frostedblakess.bsky.social and @cpehlevan.bsky.social we wrote a brief perspective on how ideas about summary statistics from the statistical physics of learning could potentially help inform neural data analysis... (1/2)
frontiersin.org
Frontiers | Summary statistics of learning link changing neural representations to behavior
How can we make sense of large-scale recordings of neural activity across learning? Theories of neural network learning with their origins in statistical phy...
1349
Reposted by Erin Grant
Data on the Brain & Mind @NeurIPS2025 @dataonbrainmind.bsky.social · 25/08/2025
📢 10 days left to submit to the Data on the Brain & Mind Workshop at #NeurIPS2025! 📝 Call for: • Findings (4 or 8 pages) • Tutorials If you’re submitting to ICLR or NeurIPS, consider submitting here too—and highlight how to use a cog neuro dataset in our tutorial track! 🔗 data-brain-mind.github.io
data-brain-mind.github.io
Data on the Brain & Mind
085
Erin Grant @eringrant.me · 19/08/2025
I’m recruiting committee members for the Technical Program Committee at #CCN2026. Please apply if you want to help make submission, review & selection of contributed work (Extended Abstracts & Proceedings) more useful for everyone! 🌐 Helps to have: programming/communications/editorial experience.
31914
Reposted by Erin Grant
Richard Gao @rdgao.bsky.social · 11/08/2025
arguably the most important component of AI for neuroscience: data, and its usability
1202
Reposted by Erin Grant
Grace Lindsay @neurograce.bsky.social · 15/08/2025
The rumors are true! #CCN2026 will be held at NYU. @toddgureckis.bsky.social and I will be executive-chairing. Get in touch if you want to be involved!
417330
Erin Grant @eringrant.me · 13/08/2025
many thanks to my collaborators, @saxelab.bsky.social and especially Lukas :)
010
Erin Grant @eringrant.me · 13/08/2025
I like the how Rosa Cao (sites.google.com/site/luosha) & @dyamins.bsky.social speculated about task constraints here (doi.org/10.1016/j.co...). I think the Platonic Representation hypothesis is a version of their argument, for multi-modal learning.
020
Erin Grant @eringrant.me · 13/08/2025
Definitely! Task constraints certainly play a role in determining representational structure, which might interact with what we consider here (efficiency of implementation). We don't explicitly study it. Someone should!
110
Erin Grant @eringrant.me · 13/08/2025
Main takeaway: Valid representational comparison relies on implicit assumptions (task-optimization *plus* efficient implementation). ⚠️ More work to do on making these assumptions explicit! 🧠 CCN poster (today): 2025.ccneuro.org/poster/?id=w... 📄 ICML paper (July): icml.cc/virtual/2025/poster/44890
icml.cc
ICML Poster Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networksICML 2025
0151
Erin Grant @eringrant.me · 13/08/2025
Our theory predicts that representational alignment is consistent with *efficient* implementation of similar function. Comparing representations is ill-posed in general, but becomes well-posed under minimum-norm constraints, which we link to computational advantages (noise robustness).
150
Erin Grant @eringrant.me · 13/08/2025
Function-representation dissociations and the representation-computation link persist in deep nonlinear networks! Using function-invariant reparametrisations (@bsimsek.bsky.social), we break representational identifiability but degrade generalization (a computational consequence).
Function-representation dissociation in ReLU networks. (A-B) MNIST representations before/after prediction-preserving reparametrisation. (C) RSM after function-preserving reparametrisation. (D-E) Performance under input/parameter noise for different solution types.
110
Erin Grant @eringrant.me · 13/08/2025
We demonstrate that representation analysis and comparison is ill-posed, giving both false negatives and false positives, unless we work with *task-specific representations*. These are interpretable *and* robust to noise (i.e., representational identifiability comes with computational advantages).
Hidden-layer representations for a semantic hierarchy task. (A) Task structure. (B) Input/target encoding. (C-E) Hidden representations and representational similarity matrices for task-agnostic (C: LSS) vs. task-specific (D: MRNS, E: MWNS) solutions.
131
Erin Grant @eringrant.me · 13/08/2025
We parametrised this solution hierarchy to find differences in handling of task-irrelevant dimensions: Some solutions compress away (creating task-specific, interpretable representations), while others preserve arbitrary structure in null spaces (creating arbitrary, uninterpretable representations).
The solution manifold. (A) Solution manifold for a 3-parameter linear network, showing GLS and constrained LSS, MRNS, and MWNS solutions. (B-E) Input/output weight relationships and parametrisation structure for each solution type.
120
Erin Grant @eringrant.me · 13/08/2025
To analyse this dissociation in a tractable model of representation learning, we characterize *all* task solutions for two-layer linear networks. Within this solution manifold, we identify a solution hierarchy in terms of what implicit objectives are minimized (in addition to the task objective).
Task solution hierarchy defined by implicit regularisation objectives.
140
Erin Grant @eringrant.me · 13/08/2025
Deep networks have parameter symmetries, so we can walk through solution space, changing all weights and representations, while keeping output fixed. In the worst case, function and representation are *dissociated*. (Networks can have the same function with the same or different representation.)
Example of a failure case. (A) A random walk on the solution manifold of a two-layer linear network reveals that weights can change continuously, inducing changes in the (B) network parametrisation and thus the (C) hidden-layer representations, while preserving the (D) network output.
130
Erin Grant @eringrant.me · 13/08/2025
Are similar representations in neural nets evidence of shared computation? In new theory work w/ Lukas Braun (lukasbraun.com) & @saxelab.bsky.social, we prove that representational comparisons are ill-posed in general, unless networks are efficient. @icmlconf.bsky.social @cogcompneuro.bsky.social
37220
Erin Grant @eringrant.me · 13/08/2025
Co-organized with @susanneharidi.bsky.social, @marcelbinz.bsky.social, Rodrigo Carrasco-Davis, @clementinedomine.bsky.social‬, @eringrant.me, @modirshanechi.bsky.social‬ 🌳
020
Erin Grant @eringrant.me · 13/08/2025
Want to contribute to this debate at #CCN2025? Please come to our session today, fill out the anonymous survey (forms.gle/yDBBcBZybGjogksC8), and comment on the GAC page (sites.google.com/ccneuro.org/gac2020/gacs-by-year/2025-gacs/2025-1)! Your perspectives will shape our eventual GAC paper. 👥
120
Erin Grant @eringrant.me · 13/08/2025
This GAC focuses on three debates/questions around benchmarks in cognitive science (the what, why, and how): (1) Should data or theory come first? (2) Should we focus on replication or exploration? (3) What incentives should we build up, if we choose to invest effort as a community?
The three questions of the GAC?
1. What should benchmarks measure?
2. What should the goals of a benchmark be?
3. How should benchmarks be structured?
140
Erin Grant @eringrant.me · 13/08/2025
Cognitive science aims for more than mere prediction: We aim to build theories. Yet, evaluations in cognitive science tend to be narrow tests of a specific theory. How can we create benchmarks to make empirical validation more systematic, while preserving our goal of theory-driven cognitive science?
130
Erin Grant @eringrant.me · 13/08/2025
Cognitive science met computational methods sooner than many scientific domains, but hasn’t yet fully embraced *benchmarks*: Shared evaluation challenges that focus on open data and reproducible methods (doi.org/10.1162/99608f92.b91339ef). How could we get benchmarking right for cognitive science? 🤔
doi.org
Data Science at the Singularity
120
Erin Grant @eringrant.me · 13/08/2025
Our #CCN2025 GAC debate w/ @gretatuckute.bsky.social, Gemma Roig (www.cvai.cs.uni-frankfurt.de), Jacqueline Gottlieb (gottlieblab.com), Klaus Oberauer, @mschrimpf.bsky.social &‬ @brittawestner.bsky.social asks: 📊 What benchmarks are useful for cognitive science? 💭 2025.ccneuro.org/gac
Speakers and organizers of the GAC debate. Time and location of the GAC debate: 5 PM in Room C1.03.
15016
Erin Grant @eringrant.me · 11/07/2025
How about controlling sparsity of the code via task alone: doi.org/10.1073/pnas... and our follow-up arxiv.org/abs/2501.17284? Though the loop to experiment is not yet closed :)
doi.org
Data-driven emergence of convolutional structure in neural networks | PNAS
Exploiting data invariances is crucial for efficient learning in both artificial and biological neural circuits. Understanding how neural networks ...
090
Erin Grant @eringrant.me · 23/06/2025
Congrats, Dan!!
020
Reposted by Erin Grant
Alexandra Proca @aproca.bsky.social · 20/06/2025
How do task dynamics impact learning in networks with internal dynamics? Excited to share our ICML Oral paper on learning dynamics in linear RNNs! with @clementinedomine.bsky.social @mpshanahan.bsky.social and Pedro Mediano openreview.net/forum?id=KGO...
openreview.net
Learning dynamics in linear recurrent neural networks
Recurrent neural networks (RNNs) are powerful models used widely in both machine learning and neuroscience to learn tasks with temporal dependencies and to model neural dynamics. However, despite...
13411
Reposted by Erin Grant
Shannon Mattern @shannonmattern.bsky.social · 03/06/2025
"our society selects for the affordances of a medium—speed, ease, efficiency—not for its effects. And it is the effects of literacy that hold its civilizational value. [Those] deep cognitive and ethical capacities are not being selected for. They are not easily monetized or optimized."
jacmullen.substack.com
How To Do Soul-Craft With State Tools
On Literacy and AI
1204
Reposted by Erin Grant
Jasper van den Bosch @jaspervdb.bsky.social · 16/05/2025
Phew decisions are out..!! Congratulations to the authors of the 26 papers selected for the first edition of the CCN Proceedings 📜 @eringrant.bsky.social @neurosteven.bsky.social @cogcompneuro.bsky.social 1/2
283
Reposted by Erin Grant
Grace Lindsay @neurograce.bsky.social · 10/05/2025
Because we must build good things while we scream about the bad, I have started a "Data for Good" team @data-for-good-team.bsky.social that partners with organizations needing short-term data science help. We have three projects ongoing & will add more as our capacity grows. data-for-good-team.org
815168
Reposted by Erin Grant
Dota Tianai Dong @dotadotadota.bsky.social · 28/04/2025
That’s a wrap for Re²-Align 🤖 🧠👤 at #ICLR2025 🦁🥳— thanks for being part of it! We’re probably just getting started… see you all at Re³-Align🌷😉
0272
Reposted by Erin Grant
Siddharth Suresh @siddsuresh97.bsky.social · 28/04/2025
🌟 Don't miss our EXCITING lineup of speakers (@irisgroen.bsky.social, Dianbo Liu, @mschrimpf.bsky.social , Janet Wiles, @itsneuronal.bsky.social) and our 🌶️ panel discussion moderated by @thisismyhat.bsky.social which will also include @noahdgoodman.bsky.social! 🔥
151
Erin Grant @eringrant.me · 28/04/2025
The afternoon session is continuing now! @iclr-conf.bsky.social
0182
Erin Grant @eringrant.me · 03/02/2025
Deadline extended till Feb. 5th!
0142
Erin Grant @eringrant.me · 21/01/2025
Last year, we funded 250 authors and other contributors to attend #ICLR2024 in Vienna as part of this program. If you or your organization want to directly support contributors this year, please get in touch! Hope to see you in Singapore at #ICLR2025!
13714
Erin Grant @eringrant.me · 16/01/2025
Our representational alignment workshop returns to #ICLR2025! Submit your work on how ML/cogsci/neuro systems represent the world & what shapes these representations 💭🧠🤖 w/ @thisismyhat.bsky.social @dotadotadota.bsky.social, @sucholutsky.bsky.social @lukasmut.bsky.social @siddsuresh97.bsky.social
0209