iiinova — where your digital self keeps evolving

Houjun Liu @jemoka.com · 14/09/2026

🚨 new package day!! 🚨 hi friends, I'm open-sourcing the system I use to do architectures research: github.com/Jemoka/thx

100

Reposted by Houjun Liu

Naomi Saphra @nsaphra.bsky.social · 11/11/2025

meet me at this button friends

refresh button for address bar visiting openreview.net

3181

Reposted by Houjun Liu

Claas Voelcker @cvoelcker.bsky.social · 11/11/2025

LMAO, openreview down point 9pm UCT when ICLR is supposed to be releasing. Coincidence?

041

Reposted by Houjun Liu

Houjun Liu @jemoka.com · 02/10/2025

Introducing 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝗯𝘂𝗯𝗯𝗹𝗲𝘀: a *fully unsupervised* LM for input-adaptive parallel latent reasoning ✅ Learn yourself a reasoning model with normal pretraining ✅ Better perplexity compared to fixed thinking tokens No fancy loss, no chain of thought labels 🚀

173

Houjun Liu @jemoka.com · 02/10/2025

173

Reposted by Houjun Liu

Houjun Liu @jemoka.com · 20/08/2025

New Paper Day! For EMNLP findings—in LM red-teaming, we show you have to optimize for **both** perplexity and toxicity for high-probability, hard to filter, and natural attacks!

162

Houjun Liu @jemoka.com · 20/08/2025

New Paper Day! For EMNLP findings—in LM red-teaming, we show you have to optimize for **both** perplexity and toxicity for high-probability, hard to filter, and natural attacks!

162

Reposted by Houjun Liu

FOCS 2026 @focs2026.bsky.social · 13/07/2025

The list of accepted papers at #FOCS2025 is up! focs.computer.org/2025/accepte...

focs.computer.org

Accepted Papers – FOCS 2025

03615

Reposted by Houjun Liu

Haskell programming language @haskell.org · 21/06/2025

You're not too dumb for Haskell, you just need a reason to practice. :)

0143

Reposted by Houjun Liu

Journal of Open Source Software @joss-openjournals.bsky.social · 03/07/2025

Just published in JOSS: 'Turftopic: Topic Modelling with Contextual Representations from Sentence Transformers' doi.org/10.21105/joss.08183

011

Reposted by Houjun Liu

Martin Kleppmann @martin.kleppmann.com · 27/06/2025

OCaml @ocaml.org is in The Economist!

4549

Reposted by Houjun Liu

TTIC @tticconnect.bsky.social · 27/06/2025

We’re proud to announce three new tenure-track assistant professors joining TTIC in Fall 2026: Yossi Gandelsman, Will Merrill, and Nick Tomlin (@nickatomlin.bsky.social). Meet them here: buff.ly/JH1DFtT

072

Reposted by Houjun Liu

Mathurin Massias @mathurinmassias.bsky.social · 18/06/2025

New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719 🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*? w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇

25617

Reposted by Houjun Liu

Houjun Liu @jemoka.com · 02/06/2025

New Paper Day! For ACL 2025 Findings: You should **drop dropout** when you are training your LMs AND MLMs!

1114

Houjun Liu @jemoka.com · 02/06/2025

New Paper Day! For ACL 2025 Findings: You should **drop dropout** when you are training your LMs AND MLMs!

1114

Reposted by Houjun Liu

Kristina Gligoric @IC2S2 @gligoric.bsky.social · 30/05/2025

I'm excited to announce that I’ll be joining the Computer Science department at Johns Hopkins as an Assistant Professor this Fall! I’ll be working on large language models, computational social science, and AI & society—and will be recruiting PhD students. Apply to work with me!

14914

Reposted by Houjun Liu

Sky @sky.app · 28/05/2025

Introducing Sky for Mac. Watch this 90-second sneak peek:

55611

Houjun Liu @jemoka.com · 21/05/2025

looks like deepmind has been busy deepmind.google/models/veo/ deepmind.google/models/gemin...

000

Houjun Liu @jemoka.com · 17/05/2025

@radbuglet.bsky.social since when did you become a user of bluesky?

000

Reposted by Houjun Liu

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 06/05/2025

Jax has a debugger now! This changes everything: docs.jax.dev/en/latest/de...

docs.jax.dev

Compiled prints and breakpoints — JAX documentation

1161

Houjun Liu @jemoka.com · 11/04/2025

Is it just me or is the latest style guide of ChatGPT's IFT is like terribly sarcastic? I don't need 👉 finger guns after every single message.

000

Houjun Liu @jemoka.com · 01/03/2025

I'm to this day still confused about why people are so hyped about softmax-bottlenecked "deep research" approaches; idk about you but I don't usually need to compose a 10 page treatise on first order logic to decide whether or not an if statement is backwards....

000

Houjun Liu @jemoka.com · 22/02/2025

cs theory seems like an outlier within theoretical sciences where we are living in the era of Euler, Gauss, etc. for math with substantial results being continuously developed live as a part of frontier research. what a time to be alive.

031

Houjun Liu @jemoka.com · 14/02/2025

the world if I could spell "causal interventions" correctly on the first try

120

Reposted by Houjun Liu

Hao Zhu 朱昊 @zhuhao.me · 06/02/2025

Ever dreamed of AI agents learning through interacting with the open world unsupervisedly? Our latest preprint introduces NNetNav-Live which collects training data through exploration on real websites and hindsight labeling, which produces a SOTA OSS agent.

142

Reposted by Houjun Liu

Yijia Shao @echoshao8899.bsky.social · 17/01/2025

LM agents today primarily aim to automate tasks. Can we turn them into collaborative teammates? 🤖➕👤 Introducing Collaborative Gym (Co-Gym), a framework for enabling & evaluating human-agent collaboration! I now get used to agents proactively seeking confirmations or my deep thinking.(🧵 with video)

12210

Houjun Liu @jemoka.com · 15/01/2025

shout out to @sfcompute.bsky.social for saving my last-minute compute ass

000

Reposted by Houjun Liu

Dan Jurafsky @jurafsky.bsky.social · 12/01/2025

Happy New Year everyone! Jim and I just put up our January 2025 release of Speech and Language Processing! Check it out here: web.stanford.edu/~jurafsky/sl...

web.stanford.edu

Speech and Language Processing

115250

Houjun Liu @jemoka.com · 29/12/2024

I feel like the instagram onboarding is at this point the primary blocker of me getting an instagram. They *insist* that I’m {fake, spam, using an open proxy} literally no matter what I try or where I try it. So be it, better that way probably too :/ But I do want to post pictoors… maybe Pinterest?

000

Reposted by Houjun Liu

Robert Csordas @robertcsordas.bsky.social · 12/12/2024

Come visit our poster "MoEUT: Mixture-of-Experts Universal Transformers" on Friday at 4:30 in East Exhibit Hall A-C #1907 on #NeurIPS2024. With Kazuki Irie, Jürgen Schmidhuber, Christopher Potts and @chrmanning.bsky.social.

1145

Reposted by Houjun Liu

David Mortensen @davidrmortensen.bsky.social · 12/12/2024

I'm going to publish a paper entitled, “Large language models surpass human experts at estimating the probability of token sequences.”

0121

Houjun Liu @jemoka.com · 11/12/2024

I feel like evals like this highlight how far we still have to go to have useful “assistant” LMs; but it’s a darn shame if we made this (or anything else) a “benchmark” it’ll be instantly Goodhart’s Law’d

100

Houjun Liu @jemoka.com · 05/12/2024

glorious. 🎶 you'll scream for mor-mor-mor-morphology 🎶

021

Houjun Liu @jemoka.com · 28/11/2024

🎶All I want for Christmas is ~~you~~ sublinear decidability 🎶🎵

010

Reposted by Houjun Liu

Stanford NLP Group @stanfordnlp.bsky.social · 18/11/2024

Missed some – or all – of our papers at #EMNLP2024? It's not too late to catch up using this handy list from the Stanford AI Lab blog: ai.stanford.edu/blog/emnlp-2...

0244

Houjun Liu @jemoka.com · 24/11/2024

except if a linear probe somehow got the cat rotating with the wheel (jk)

020

Houjun Liu @jemoka.com · 20/11/2024

fly the friendly (or at least open source) skies

020

Houjun Liu @jemoka.com · 20/11/2024

just one more thing that only #emacs users can get right within their editors :p

040

Reposted by Houjun Liu

Caleb Ziems @calebziems.com · 15/11/2024

I wanted to contribute to "Starter Pack Season" with one for Stanford NLP+HCI: go.bsky.app/VZBhuJ5 Here are some other great starter packs: - CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK - NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk - HCI: go.bsky.app/p3TLwt - Women in AI: go.bsky.app/LaGDpqg

22510

Reposted by Houjun Liu

Christopher Manning @chrmanning.bsky.social · 10/11/2024

Papers at #EMNLP2024 #2 MSCAW-coref: Efficient and high performing coreference, extending CAW-coref multilingually and to singleton mentions. Fri Nov 15 CRAC workshop 14:10-14:30 aclanthology.org/2024.crac-1.4 In Stanza: stanfordnlp.github.io/stanza/

0151

Houjun Liu @jemoka.com · 17/11/2024

Thank FUCK for flighty and United gate agents at MIA for saving my ass today; had a connection delayed by 2 hours that I got a notif for and was able to rebook on a flight which was about to take off when United’s notif came through

100

Reposted by Houjun Liu

Federico Viticci @viticci.macstories.net · 16/11/2024

fine, I'll talk about the iPad here too

2935110

Reposted by Houjun Liu

Tailscale @tailscale.com · 13/11/2024

We're live at KubeCon NA! Stop by booth R12, meet the team, see how Tailscale can simplify and secure your Kubernetes connectivity, and pick up some unique swag while you're here. More info: tailscale.com/kubecon-na

The Tailscale team with KubeCon badges in front of our conference booth

2344

Houjun Liu @jemoka.com · 05/03/2024

will i get the old experience twitter back here? let's find out.

050