Erin Grant

Assistant Professor / Faculty Fellow @NYUDataScience studying cognition in mind & brain with neural nets, Bayes, other tools |

[Erin Grant @ermgrant]

at #ICLR2026 this week spotting 🌿green brutalism😌

as @iclr_conf Participation Chair w/ @pcastr, supporting ECRs to attend #ICLR2026! (Say hi!)

also: Recruiting for my lab @UAlberta @AmiiThinks; hosting Re-Align ... 👇

PSA: Use Scholar Inbox :)
https://t.co/1ji7QBHUoS

[Mandana Samiei @MandanaSamiei]

Excited to see our perspective out today!

We argue that schemas may not be fundamentally distinct from semantic and episodic memories, but instead lie along a spectrum of abstraction, from detailed episodic experiences to highly abstract knowledge.

https://t.co/EMdYfImZEm

[Erin Grant @ermgrant]

@sh_reya Woohoo!!!!!!!!! 🥳

[Valentina Pyatkin @valentina__py]

I'm excited to be giving an invited talk at the #iclr2026 Re-Align workshop, talking about how we can improve precise instruction following generalization:

9:15 AM Rio time, Monday, April 27

https://t.co/OC7lF6XgJe

[Sharut Gupta @sharut_gupta]

I’ll be giving a talk tomorrow at the Re-Align workshop at 11:15 AM (Room 207) on our recent work showing that independently trained multimodal contrastive models are equivalent up to an orthogonal transform!

https://t.co/0v9KQ8iTlK

Drop by to say hi!

[David Bau @davidbau]

Good morning #ICLR2026 sleepyheads!

At 9:00am today rm 207 I will talk at the Re-Align workshop and challenge ol' Wittgenstein

I promise some fun, pointing neural microscopes at Brazilian and Spanish felines. And trying a new tool for doing AI brain transplants in a minute.

[Badr AlKhamissi @bkhmsi]

Good morning #ICLR2026 ☀️

The Re-Align workshop kicks off in 30 minutes! A full day on what we can actually do with representational alignment, from brains to language models to agents.

Schedule in the thread 👇

[Erin Grant @ermgrant]

@MarlosCMachado @pcastr come!! i’m slower than you think!!

[Erin Grant @ermgrant]

@MarlosCMachado @pcastr 😂 follow us on Strava to find out :)

[Erin Grant @ermgrant]

@MarlosCMachado @pcastr 6.5-7km!

[Blake Bordelon ☕️🧪👨‍💻 @blake__bordelon]

Modern deep learning is very complex. We are hopeful that many lines of research will improve our scientific understanding of DL through the lens of learning mechanics. Hope to find more solveable models & limits, empirical laws, scaling arguments, universal phenomena, etc

[Erin Grant @ermgrant]

@ZhongpaiGao @pcastr olympic park is very safe in the morning and in a group

[Erin Grant @ermgrant]

@tw_killian @pcastr @iclr_conf @UAlberta @AmiiThinks thank you! old news but a new audience :)

[Erin Grant @ermgrant]

at #ICLR2026 this week spotting 🌿green brutalism😌

as @iclr_conf Participation Chair w/ @pcastr, supporting ECRs to attend #ICLR2026! (Say hi!)

also: Recruiting for my lab @UAlberta @AmiiThinks; hosting Re-Align ... 👇

PSA: Use Scholar Inbox :)
https://t.co/1ji7QBHUoS

[Andrew Saxe @SaxeLab]

Come chat about this @iclr_conf, at 3:15 PM on Friday in Pavilion 4 Poster #4216!

[Erin Grant @ermgrant]

see you there!!

[Pablo Samuel Castro @pcastr]

Are you at #ICLR2026 and staying at (or near) the Marriott? Come run with me tomorrow (Friday) at 7am! Starting from the Marriott.
#runconference

https://t.co/k8yYQCvUAD

[Erin Grant @ermgrant]

on Monday, we're hosting the 3rd edition of the Re-Align Worskhop (w/ @dotaDong @bkhmsi in person + organizers from afar):
https://t.co/mIhdDqPn8M

If you have an #ICLR2026 main conf poster on a related topic, you can sign up to present at Re-Align too!

https://t.co/FJa9PQKM8r

[Badr AlKhamissi @bkhmsi]

I’m also co-organizing the #ICLR2026 Re-Align workshop on April 27th.

We've got an amazing lineup of speakers spanning CogSci, Neuroscience, and ML! 🧠🤝🤖

Link: https://t.co/BEtKUM9oQP

[Andrew Saxe @SaxeLab]

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: https://t.co/fP4HYwRF9C

[Stefano Sarao Mannelli @stefsmlab]

Join us at the Mathematical Foundations of AI Workshop!

📍Gothenburg 🗓️ June 8-10

We have great speakers and expect great discussions on DMs, transformers, and associative memories.

Do you have a related work? The call for contributions is open!

[Stefano Sarao Mannelli @stefsmlab]

Hiring 2 Postdocs to work on Theoretical Foundations of AI Safety @chalmersuniv

If you have a background in Physics, Math, or ML and want to tackle AI alignment at a fundamental level alongside UCL, apply below!

🔗Apply: https://t.co/Z4Pmw4nT5E
🔬Lab: https://t.co/Ip7ciueRhG

[Francesco Cagnetta @Fraccagnetta]

❓ How do LLMs learn hierarchical structure from sentences alone?

🚨 We build PCFG-like synthetic datasets with two knobs---hierarchy + ambiguity---and derive a correlation-based learning mechanism that predicts the sample complexity of deep nets.

Results 👇