@omerNLP

A postdoc at @CHIA_Cambridge and @CambridgeLTL. If I'm not here I'm at @omagolda following the news

Joined August 2019
  • Tweets335
  • Following271
  • Followers430
38Media
Wanna check how well a model can share knowledge between languages? Of course you do! 🤩 But can you do it without access to the model’s weights? Now you can with ECLeKTic 🤯
1
16
4
45
4,435
It turns out tokenizer evaluations might not tell us as much about how models turn out as we thought (or hoped). Very interesting results in our new EMNLP findings paper!
Antonio Lopardo @ EMNLP@AntonioLprdOct 22
🆕 Findings of #EMNLP2026 🆕 Can you tell a good tokenizer from a bad one without training a model? We tested 29 intrinsic tokenizer metrics against 159 language models in nine languages. None of them reliably predicts downstream performance across suite and language combos 🧵
1
7
33
1,361
Will you be at EMNLP? Come check our lab's work: papers, a workshop and a keynote
CambridgeLTL@CambridgeLTLOct 23
The @Cambridge_Uni Language Technology Lab is heading to Budapest for #EMNLP2026 next week! 🇭🇺 Our very own @annalkorhonen will deliver a keynote, "AI for the Many: Starting from the World, Not the Model" 🗓️ October 27, 14:00–15:00 Full sched below, come say hi! 👋
1
23
431
omer goldman @ EMNLP retweeted
Benjamin Minixhofer
@bminixhoferOct 7
Super excited to share that our method to convert language models to byte-level has been published in @Nature! This was originally the approach behind Bolmo. We now generalized it to other model families. All checkpoints (including new Qwen and Llama models) and data are public!
Ai2
@allen_aiOct 7
Our paper on retrofitting language models to operate over bytes – the approach behind Bolmo – has been accepted to Nature! 🎉 We’re also releasing new checkpoints that extend our method from Olmo to Qwen & Llama. 🧵 nature.com/articles/s41586-0…
6
8
2
68
3,491
omer goldman @ EMNLP retweeted
Tomasz Limisiewicz @COLM@TomLimiOct 6
We trained first language model for Yiddish! On the way we learned how low-resource tasks are still a challenge for modern LLMs. See us at a poster session at 11 am today @COLM_conf P.S. MameLoshne is rather BabeLoshn for me, as Yiddish was native lanaguage of my grandmother.
Uri Katz@UrikaUriOct 6
Replying to @UrikaUri
Yiddish combines Germanic grammar, Hebrew script, and fusion vocabulary. Multilingual LMs can produce readable Yiddish while missing its distinctive vocabulary and grammar. The result is a flatter version of the language.
2
2
20
704
omer goldman @ EMNLP retweeted
Djamé..
@zehavocOct 6
very cool !
omer goldman @ EMNLP@omerNLPOct 6
We trained an LLM for Yiddish! Existing pretraining data is only about 40% real Yiddish and models miss a lot of what makes the language what it is. MameLoshnLM fixes quite a bit of that! Come hear @UrikaUri talk about it at #COLM2026. Tmrw 11am Grand Ballroom Poster #123
1
3
266
We trained an LLM for Yiddish! Existing pretraining data is only about 40% real Yiddish and models miss a lot of what makes the language what it is. MameLoshnLM fixes quite a bit of that! Come hear @UrikaUri talk about it at #COLM2026. Tmrw 11am Grand Ballroom Poster #123
Uri Katz@UrikaUriOct 6
Replying to @UrikaUri
Yiddish combines Germanic grammar, Hebrew script, and fusion vocabulary. Multilingual LMs can produce readable Yiddish while missing its distinctive vocabulary and grammar. The result is a flatter version of the language.
3
3
2
31
2,520
omer goldman @ EMNLP retweeted
Benjamin Minixhofer
@bminixhoferSep 30
It’s been a pleasure to contribute to this survey and to see it come together! @marco_computers did an amazing job leading this highly ambitious project which should become the go-to resource for any questions on or adjacent to tokenization.
Marco🍞
@marco_computersSep 30
🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
2
26
1,272
omer goldman @ EMNLP retweeted
Tomasz Limisiewicz @COLM@TomLimiOct 1
Big start of #TOKtober ! 🎃 👉 Just out: Token _ization Survey 👉 Oct 9: Tokenization Workhop @tokshop2025 @COLM_conf 👉 San Francisco 👉Oct 28: Tokenization tutorial @emnlpmeeting 👉Budapest Save the dates! Links below
1
4
13
463
omer goldman @ EMNLP retweeted
Sander Land@magikarp_tokensSep 30
The tokenization survey is finally out! It was nice to collaborate with such a talented group of researchers and learn a lot about the breadth of this field. Kudos to @marco_computers for leading the project! ~> tokenize.rs/survey

Tokenization: A Survey for Modern NLP

Tokenization is presented as a core language-model design choice that shapes sequence length, computational cost, multilingual equity, evaluation, and security—not merely as preprocessing. The...

alphaxiv.org
Marco🍞
@marco_computersSep 30
🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
2
32
1,219
omer goldman @ EMNLP retweeted
Yuval Pinter@yuvalpiSep 30
It's finally out! Marco says 8 months but it's really been brewing for years. Super excited and proud of this fantastic team's magnum opus, your guide to everything tokens.
Marco🍞
@marco_computersSep 30
🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
2
6
36
1,370
omer goldman @ EMNLP retweeted
Konstantin Dobler
@konstantdoblerSep 30
One hundred pages of pure, concentrated tokenizer knowledge are finally out! Proud to have contributed to this huge effort.
Marco🍞
@marco_computersSep 30
🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
3
19
646
Everything you need to know about tokenizers but never dared asking, and even more!
Marco🍞
@marco_computersSep 30
🚨 [Token][ization] Paper Alert 🚨 Tokenization is a wildly understudied area of language modeling despite it having effects across all of NLP. Over the past ~8 months, 32 (!) tokenizer researchers put together the most comprehensive survey of the field. Check it out!
1
1
25
1,451
omer goldman @ EMNLP retweeted
LION Lab@LIONLabNLPSep 17
🦁LION Lab is hiring! 🧑‍🔬One fully funded PhD student (TVL-13 100%) for 3 years 🧪Topic: Interpretability for Protein Language Models 👥Advised by @LAWeissweiler together with Clara Schoeder 🌍Leipzig, Germany 🔗Apply by Oct 15 lionlabnlp.github.io/jobs/ai… Please share! #NLProc #NLP
5
2
11
1,586
In deep research reports, many sentences aren't supported by their citations: recall is 58.7% in NVIDIA AI-Q and 7.1% in TrajectoryKit. Our #EMNLP2026 paper (main conf) proposes an algorithm that traces each error to the agent that introduced it, and identifies the error type.
3
16
1
36
2,774
I've just heard people saying "queueline"! #Chinese #butinEnglish
2
132
omer goldman @ EMNLP retweeted
Edoardo Ponti@PontiEdoardoSep 11
I am looking for 1 postdoc and 2 fully funded PhDs at Imperial @ICComputing to join my @ERC_Research project AToM ⚛ We aim to build models that learn to compress what they perceive and remember, for permanent memory, longer horizons, and >10x speedups ducdauge.github.io/atom/
5
54
5
202
14,862
omer goldman @ EMNLP retweeted
Yanai Elazar@yanaielaSep 8
I'm looking for an intern to join my group, around February next year for four months, through the Azrieli PhD Fellowship. DM/email me if you're interested! Link in the next tweet.
5
33
231
19,401
omer goldman @ EMNLP retweeted
Shir Ashury-Tahan @ EMNLP@ShirAshuryTahanSep 1
Fascinating work! This adds lens on how models internalize representations: it makes you wonder if cross-lingual skill variance isn't just a failure of generalization, but a reflection of how models bind reasoning strategies to language-specific behavioral priors 🤔
omer goldman @ EMNLP@omerNLPAug 28
for quite a while I was trying to find a way to measure x-ling consistency without resorting to knowledge, @bobbycxy and @LChoshen came with this games approch. It is honestly brilliant!
1
2
89
omer goldman @ EMNLP retweeted
Adam Gaber
@AdamJaber248Aug 28
New preprint! We let LLMs play games against themselves in diffrent languages, different languages show different skill levels
Bobby
@bobbycxyAug 28
Will the same model become a different player depending on the interface language? We report our findings in our paper "Skill Issue: Are Skills Language-Invariant in LLMs?". And with it, TextArena is now multilingual 🌍 with 65 games in 193 languages. 🧵
3
1
7
505
omer goldman @ EMNLP retweeted
omer goldman @ EMNLP@omerNLPAug 28
for quite a while I was trying to find a way to measure x-ling consistency without resorting to knowledge, @bobbycxy and @LChoshen came with this games approch. It is honestly brilliant!
Bobby
@bobbycxyAug 28
Will the same model become a different player depending on the interface language? We report our findings in our paper "Skill Issue: Are Skills Language-Invariant in LLMs?". And with it, TextArena is now multilingual 🌍 with 65 games in 193 languages. 🧵
2
9
2
22
1,366
Load more