iiinova — where your digital self keeps evolving

Lisa Bylinina @bylinina.bsky.social · 20h

yaaay our workshop is going to macau!!

Reposted by Lisa Bylinina

Lukas Edman @lukasnlp.bsky.social · 17/09/2026

Ever feel like it's too hard to keep track of what LLMs cannot do as well as humans? We're making your life easier over at: what-llms-can-not-do.github.io We're compiling a list of papers testing the abilities of LLMs against humans. Check it out! And you can help contribute too!

what-llms-can-not-do.github.io

What LLMs Can(not) Do

A living survey of benchmarks that compare large language models with humans.

24516

Lisa Bylinina @bylinina.bsky.social · 11/09/2026

look at my new babylm paper! arxiv.org/abs/2609.11870 basically, i initialize token embeddings with representations from an image encoder rather than randomly and then train text-only as usual. kind of a visual demonstration to start off the word learning process

1155

Lisa Bylinina @bylinina.bsky.social · 05/11/2025

there is this guy on my flight to shanghai sitting next to me checking out the emnlp program and a bunch of papers and his bsky feed is 90% emnlp stuff and on the one hand it would be nice to chat but on the other hand it‘s a 12-hour flight so maybe i it’a better if i focus on my netfix downloads..

040

Reposted by Lisa Bylinina

Ece Takmaz @ecekt.bsky.social · 01/11/2025

I will be attending EMNLP in China to present our paper with @bylinina.bsky.social (who will be in China, too) and Jakub Dotlacil in the BabyLM workshop! Looking forward to meeting people there! ✨ 😊 #EMNLP2025 @emnlpmeeting.bsky.social lnkd.in/e-Bzz6De

1123

Lisa Bylinina @bylinina.bsky.social · 12/05/2025

got a tiny (approx 50k) grant from NWO to do something about whether (instruction-tuned) lms are an 'agent', a superposition of agents, what's going on there epistemically and also how people interact with these 'personae' -- we'll seeeeee www.nwo.nl/en/researchp...

071

Reposted by Lisa Bylinina

Noam Ross @noamross.net · 19/04/2025

🚨Report your NSF grant terminations! 🚨 We are starting to collect information on NSF grant terminations to create a shared resource as we have for NIH. The more information we collect, the more we can organize, advocate, and fight back! Please share widely! airtable.com/appGKlSVeXni...

NSF Grant Termination Information Collection Form

Please use this form to submit information identifying specific NSF grants that have been cancelled for any reason after January 20, 2025.

We are tracking these grants to increase transparency, organize affected PIs, and facilitate responses, including via litigation. Please share the form as widely as possible with your networks.

We are actively building a pipeline to organize these terminations and will soon have a tracker akin to our NIH grant tracker at https://airtable.com/appjhyo9NTvJLocRy/shrNto1NNp9eJlgpA

WE WILL NOT DISCLOSE THE IDENTITY OF ANYONE WHO USES THIS FORM TO PROVIDE INFORMATION. We will keep your identity confidential.

These resources are maintained by Noam Ross of rOpenSci and Scott Delaney of the Harvard T.H. Chan School of Public Health, with input and support from additional volunteers. For any questions, please contact Scott Delaney on Signal (sdelaney.84).

THANK YOU FOR YOUR ASSISTANCE!

7636659

Reposted by Lisa Bylinina

Eiko Fried @eikofried.bsky.social · 17/04/2025

Four large Dutch universities, including Leiden University where I work, have decided to throw international psychology bachelor programs under the bus in an effort to appease the rightwing government. Here's my blog why this is a terrible idea. eiko-fried.com/cutting-inte...

eiko-fried.com

Cutting international bachelor programs threatens psychological science » Eiko Fried

Two days ago, four Dutch universities announced discontinuing their English-speaking psychology bachelor programs (1, 2). I will briefly explain (1) how this decision came to be, (2) why this is such ...

10228102

Lisa Bylinina @bylinina.bsky.social · 16/04/2025

do we know a pair of base vs. instruct models that are both deployed by an inference provider on hf (or maybe a hf space but less preferable..) AND that don't require students sending their info for the license agreement?

200

Lisa Bylinina @bylinina.bsky.social · 05/04/2025

i mean i'd be really surprised if what lms generate as 'reasoning' text faithfully reflected the ways they come up with the answer. like, what would guarantee that

160

Reposted by Lisa Bylinina

Kanishka Misra @kanishka.bsky.social · 02/04/2025

another day another minicons update (potentially a significant one for psycholinguists?) "Word" scoring is now a thing! You just have to supply your own splitting function! pip install -U minicons for merriment

from minicons import scorer
from nltk.tokenize import TweetTokenizer

lm = scorer.IncrementalLMScorer("gpt2")

# your own tokenizer function that returns a list of words
# given some sentence input
word_tokenizer = TweetTokenizer().tokenize

# word scoring
lm.word_score_tokenized(
["I was a matron in France", "I was a mat in France"],
bos_token=True, # needed for GPT-2/Pythia and NOT needed for others
tokenize_function=word_tokenizer,
bow_correction=True, # Oh and Schuler correction
surprisal=True,
base_two=True
)

'''
First word = -log_2 P(word | <beginning of text>)

[[('I', 6.1522440910339355),
('was', 4.033324718475342),
('a', 4.879510402679443),
('matron', 17.611848831176758),
('in', 2.5804288387298584),
('France', 9.036953926086426)],
[('I', 6.1522440910339355),
('was', 4.033324718475342),
('a', 4.879510402679443),
('mat', 19.385351181030273),
('in', 6.76780366897583),
('France', 10.574726104736328)]]
'''

3217

Lisa Bylinina @bylinina.bsky.social · 28/03/2025

you have to tell me which starter pack i apparently suddenly ended up in

110

Reposted by Lisa Bylinina

Jonathan Ginzburg @yonatanginzburg.bsky.social · 15/12/2024

Forthcoming titles in Elements in Semantics: 1. Abzianidze, @bylinina.bsky.social, Paperno Deep Learning and Semantics. 2.K. Davidson Semantics of Depiction, 3. Chatzikyriakidis Cooper, Gregoromichelaki, Sutton Types and the structure of meaning: Issues in compositional and lexical semantics (2/3)

032

Lisa Bylinina @bylinina.bsky.social · 04/12/2024

all invitations i find in my inbox are actually invitations to work a bit more

040

Lisa Bylinina @bylinina.bsky.social · 30/11/2024

in order to actually do smth in research directions i'm interested in i need some bandwidth: research time, phd students to work with, experiment budgets. in nl it's getting more and more complicated (for obv reasons): some ways to get phd students are frozen, some grants not announced anymore..

130

Lisa Bylinina @bylinina.bsky.social · 19/11/2024

linguists? computational linguists? nlp people? semantics people? anybody?

381