Isabelle Lee

Excited to share our paper: "Chain-of-Thought Is Not Explainability"! We unpack a critical misconception in AI: models explaining their steps (CoT) aren't necessarily revealing their true reasoning. Spoiler: the transparency can be an illusion. (1/9) 🧵

weve reached that point in this submission cycle, no amount of coffee will do 😞🙂‍↔️😞

INCOMING

a leaf falls on moo deng the pygmy hippo , blocking her vision

moo deng is upset presumably because she can’t see!

titled: peer review

CDS building which looks like a jenga tower

Life update: I'm starting as faculty at Boston University
@bucds.bsky.social in 2026! BU has SCHEMES for LM interpretability & analysis, I couldn't be more pumped to join a burgeoning supergroup w/ @najoung.bsky.social @amuuueller.bsky.social. Looking for my first students, so apply and reach out!

or if you're awesome and happen to be in sf, also message me

pls message me if you wanna meet up for coffee and chat about ai/physics/llms/interpretability

really excited to be headed to OFC in SF! so excited to revisit optical physics 😀

Transformers employ different strategies through training to minimize loss, but how do these tradeoff and why?

Excited to share our newest work, where we show remarkably rich competitive and cooperative interactions (termed "coopetition") as a transformer learns.

Read on 🔎⏬

i use the same template and need help getting a butterfly button help

New paper–accepted as *spotlight* at #ICLR2025! 🧵👇

We show a competition dynamic between several algorithms splits a toy model’s ICL abilities into four broad phases of train/test settings! This means ICL is akin to a mixture of different algorithms, not a monolithic ability.

Out-of-Sync ‘Loners’ May Secretly Protect Orderly Swarms Studies of collective behavior usually focus on how crowds of organisms coordinate their actions. But what if the individuals that don’t participate have just as much to tell us?

Starlings move in undulating curtains across the sky. Forests of bamboo blossom at once. But some individuals don’t participate in these mystifying synchronized behaviors — and scientists are learning that they may be as important as those that do.

Paper page - Fully Autonomous AI Agents Should Not be Developed Join the discussion on this paper page

New piece out!
We explain why Fully Autonomous Agents Should Not be Developed, breaking “AI Agent” down into its components & examining through ethical values.
With @evijit.io, @giadapistilli.com and @sashamtl.bsky.social
huggingface.co/papers/2502....

The Poetry Fan Who Taught an LLM to Read and Write DNA | Quanta Magazine By treating DNA as a language, Brian Hie’s “ChatGPT for genomes” could pick up patterns that humans can’t see, accelerating biological design.

Brian Hie harnessed the powerful parallels between DNA and human language to create an AI tool that interprets genomes. Read his conversation with Ingrid Wickelgren: www.quantamagazine.org/the-poetry-f...

How do tokens evolve as they are processed by a deep Transformer?

With José A. Carrillo, @gabrielpeyre.bsky.social and @pierreablin.bsky.social, we tackle this in our new preprint: A Unified Perspective on the Dynamics of Deep Transformers arxiv.org/abs/2501.18322

ML and PDE lovers, check it out!

it’s finally raining in la:)

part of me wants to quip, is this why i quit smoking, but i think im actually getting a lil scared. hope we get thru the next few days okay cause feels like theres very little we can do here rn

when i lived in seattle, fires were a summer expectation at a distance. here, it feels very different, to see it actually closing in on us

i go on a really long walk almost every day, and at a high point in silverlake, i saw fire from all sides. and it's harder to breathe. and everything is orange.

New paper <3
Interested in inference-time scaling? In-context Learning? Mech Interp?
LMs can solve novel in-context tasks, with sufficient examples (longer contexts). Why? Bc they dynamically form *in-context representations*!
1/N

Sunset fire in Hollywood Hills: Evacuations, shelter An evacuation zone was established between the 101 Freeway and Laurel Canyon and between Mulholland Drive and Hollywood Boulevard.

Hollywood High School will serve as an evacuation site for the Sunset fire in Hollywood, KTLA reported. The school is at 1521 Highland Ave. www.latimes.com/california/s...

hello bluesky! we have a new preprint on solvation free energies:

tl;dr: We define an interpolating density by its sampling process, and learn the corresponding equilibrium potential with score matching. arxiv.org/abs/2410.15815

with @francois.fleuret.org and @tbereau.bsky.social
(1/n)

look at our sheep

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here
drive.google.com/file/d/1eLa3...

Slides from the tutorial are now posted here!

neurips.cc/media/neurip...

An Evolved Universal Transformer Memory

sakana.ai/namm/

Introducing Neural Attention Memory Models (NAMM), a new kind of neural memory system for Transformers that not only boost their performance and efficiency but are also transferable to other foundation models without any additional training!

Tomorrow (Dec 12) poster #2311! Go talk to @emalach.bsky.social and the other authors at #NeurIPS, say hi from me!

Sometimes our anthropocentric assumptions about how intelligence "should" work (like using language for reasoning) may be holding AI back. Letting AI reason in its own native "language" in latent space could unlock new capabilities, improving reasoning over Chain of Thought. arxiv.org/pdf/2412.06769

The broader spectrum of in-context learning The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...

What counts as in-context learning (ICL)? Typically, you might think of it as learning a task from a few examples. However, we’ve just written a perspective (arxiv.org/abs/2412.03782) suggesting interpreting a much broader spectrum of behaviors as ICL! Quick summary thread: 1/7