@jwuphysics Profile picture

John F. Wu (@jwuphysics.bsky.social)

@jwuphysics

Assistant Astronomer at @stsci and @JohnsHopkins working on galaxies, machine vision, graph learning, large language models. Opinions my own. He/him.

Similar User
Viviana Acquaviva (now venividivivi on bsky) photo

@AstroVivi

Yuan-Sen Ting 丁源森 photo

@TingAstro

Dr. Rachael Beaton photo

@rareflwr41

Hila Chefer photo

@hila_chefer

Maria Dobko 🇺🇦 photo

@DobkoMaria

Vivian U photo

@JustTheLetterU

Song Huang photo

@dr_guangtou

Dr. Claudia Scarlata photo

@scorfano

Christopher Conselice photo

@conselice

Steve Finkelstein 🪐 photo

@astrosteven

Darek Kłeczek photo

@dk21

Jorryt Matthee photo

@jorryt_m

Sandro Tacchella photo

@sandrotacchella

Dr. Stephanie Juneau photo

@StephaJuneau

Erin Kado-Fong photo

@erin_kadofong

A short 🧵 on my latest paper, which was just published in The Astrophysical Journal! We use interpretable machine learning algorithms to show that galaxy environment strongly impacts how simulated galaxies co-evolve with their dark matter content. iopscience.iop.org/article/10.384…


even AI has work-life balance

Even while recording these demos, we encountered some amusing moments. In one, Claude accidentally stopped a long-running screen recording, causing all footage to be lost. Later, Claude took a break from our coding demo and began to peruse photos of Yellowstone National Park.



John F. Wu (@jwuphysics.bsky.social) Reposted

Our department at UMD is currently looking for a tenure-track Assistant/Associate Professor of astronomy! Come join our department 😎 aas.org/jobregister/ad…


If you think discourse on twitter is toxic then you should see the comments section on yahoo fantasy football


John F. Wu (@jwuphysics.bsky.social) Reposted

State space models have struggled to learn to do things like copying and associative recall 🟢 -- things that self-attention learns easily 🟠... But it turns out we just needed to change SSM initialization a bit 🔵. Our init helps a lot, and even makes state space layers *look*…

Tweet Image 1

John F. Wu (@jwuphysics.bsky.social) Reposted

What makes some LM interpretability research “mechanistic”? In our new position paper in @BlackboxNLP, @sarahwiegreffe and I argue that the practical distinction was never technical, but a historical artifact that we should be—and are—moving past to bridge communities.

Tweet Image 1

John F. Wu (@jwuphysics.bsky.social) Reposted

🚨Call for Proposals! Submit your one-page research proposals for the 2025 Jelinek Workshop on Speech and Language Technologies. Deadline: October 15, 2024! We’re looking for groundbreaking ideas in human language technologies and AI. More info at: clsp.jhu.edu/the-11th-frede…


John F. Wu (@jwuphysics.bsky.social) Reposted

HEY ASTRONOMY STUDENTS! if you are preparing to go to #AAS245 this January then go watch this iPoster tutorial I made in collaboration with @AAS_Office specifically for YOU. I give you all the details of how to make an iPoster and some tips to make your poster stand out in the…


Loading...

Something went wrong.


Something went wrong.