James Michaelov

Postdoc @MIT. Previously: @CogSciUCSD, @CARTAUCSD, @AmazonScience, @InfAtEd, @SchoolofPPLS. Research: Language in humans and machines

[James Michaelov @jamichaelov]

Had a great first day at #HSP2026 yesterday! Looking forward to presenting on the relationship between reading time, n-grams, and language model scaling at the 12.10-2pm poster session today!

[James Michaelov @jamichaelov]

Presenting this at the poster session this morning (11-2pm) at #5109

[James Michaelov @jamichaelov]

Excited to announce that I’ll be presenting a paper at #NeurIPS this year! Reach out if you’re interested in chatting about LM training dynamics, architectural differences, shortcuts/heuristics, or anything at the CogSci/NLP/AI interface in general! #Neurips2025

[James Michaelov @jamichaelov]

Looking forward to #NeurIPS25 this week 🏝️! I'll be presenting at Poster Session 3 (11-2 on Thursday). Feel free to reach out!

[James Michaelov @jamichaelov]

Excited to announce that I’ll be presenting a paper at #NeurIPS this year! Reach out if you’re interested in chatting about LM training dynamics, architectural differences, shortcuts/heuristics, or anything at the CogSci/NLP/AI interface in general! #Neurips2025

[James Michaelov @jamichaelov]

I'll also be presenting this paper with @linguist_cat at #CogInterp! https://t.co/oHJLl16syg

[Catherine Arnett @linguist_cat]

@jamichaelov and I will be presenting our paper at the @CogInterp workshop 13:15 - 14:45 on Dec 7th. We show how disaggregating grammatical benchmarks over the course of training reveals stages of training where models learn heuristics before learning more generalizable patterns.

[James Michaelov @jamichaelov]

Excited to announce that I’ll be presenting a paper at #NeurIPS this year! Reach out if you’re interested in chatting about LM training dynamics, architectural differences, shortcuts/heuristics, or anything at the CogSci/NLP/AI interface in general! #Neurips2025

[James Michaelov @jamichaelov]

Preprint link: https://t.co/AtMeWfA9eA

[James Michaelov @jamichaelov]

See the full paper here: https://t.co/F8lMhSomHP

[James Michaelov @jamichaelov]

New paper accepted at Findings of ACL! TL;DR: While language models generally predict sentences describing possible events to have a higher probability than impossible (animacy-violating) ones, this is not robust for generally unlikely events + is impacted by semantic relatedness

[James Michaelov @jamichaelov]

In the most extreme case, LMs assign sentences such as ‘the car was given a parking ticket by the explorer’ (unlikely but possible event) a lower probability than ‘the car was given a parking ticket by the brake’ (impossible event, related final word) over half of the time.

[James Michaelov @jamichaelov]

Excited to share the second paper of this research project!

[Catherine Arnett @linguist_cat]

✨New pre-print✨ Crosslingual transfer allows models to leverage their representations for one language to improve performance on another language. We characterize the acquisition of shared representations in order to better understand how and when crosslingual transfer happens.

[James Michaelov @jamichaelov]

Also generally interested in chatting about cognitive modeling, scaling, and language comprehension/understanding in humans and machines! @COLM_conf #COLM2024

[James Michaelov @jamichaelov]

Excited to present this at COLM this week! Reach out if you want to meet/chat!

[James Michaelov @jamichaelov]

Excited to present this at COLM this week! Reach out if you want to meet/chat!

[James Michaelov @jamichaelov]

New preprint with @linguist_cat and Ben Bergen! We’ve all heard of the new wave of recurrent language models, but how good are they for modeling human language comprehension? Quite good, it turns out! 🧵 https://t.co/ADtxfcDVBb

[James Michaelov @jamichaelov]

This paper is now accepted to be presented at @COLM_conf! Updated version is on arXiv. Feeling excited for the conference, let me know if you want to meet!

[James Michaelov @jamichaelov]

New preprint with @linguist_cat and Ben Bergen! We’ve all heard of the new wave of recurrent language models, but how good are they for modeling human language comprehension? Quite good, it turns out! 🧵 https://t.co/ADtxfcDVBb

[James Michaelov @jamichaelov]

@linguist_cat And the current wave of recurrent architectures has just started! As we see more and more new architectures and developments, it will be interesting to see how they compare. One thing does seem clear though: recurrent models are back with a vengeance!

[James Michaelov @jamichaelov]

New preprint with @linguist_cat and Ben Bergen! We’ve all heard of the new wave of recurrent language models, but how good are they for modeling human language comprehension? Quite good, it turns out! 🧵 https://t.co/ADtxfcDVBb

[James Michaelov @jamichaelov]

@linguist_cat With reading time, the results are more variable between experiments, and this seems like it might be related to the difference in stimuli (see paper for more details)

[James Michaelov @jamichaelov]

Exciting to see our paper (with @MeganBardolph, Cyma K. Van Petten, Benjamin K. Bergen, and @CoulsonSeana) 'in print' at @jneurolang!

[Ev (like in 'evidence', not Eve) Fedorenko 🇺🇦 @ev_fedorenko]

5️⃣Michaelov etal. find surprisal explains N400s to sentence-final words varying in predictability, plausibility, and relation to the likely completion better than sem. similarity. The results support lexical predictive coding accounts. https://t.co/EnuOJeNO9O @jamichaelov 7/n

[James Michaelov @jamichaelov]

This is concerning, and I wouldn't be surprised if it leads to some students having to withdraw their papers from the conference

[Eve Fleisig @enfleisig]

NAACL 2024 seems to charge $750 for students to register if they're a presenter (every paper requires at least one registered presenter). @naacl am I reading this right? Seems like a major burden on students, especially if (as is common) only a paper's student authors attend.

[James Michaelov @jamichaelov]

Really enjoyed the @babyLMchallenge talks and posters hosted by @conll_conf/@CMCL_NLP at @emnlpmeeting last year! Looking forward to seeing what people come up with this time round!

[babyLM @babyLMchallenge]

👶 BabyLM Challenge is back!
Can you improve pretraining with a small data budget?

BabyLMs for better LLMs
& for understanding how humans learn from 100M words

New:
How vision affects learning
Bring your own data
Paper track

https://t.co/uU12YWwLTe
🧵