Miranda Zhu 筱萌

Transformer-based neural networks achieve impressive performance on coding, math & reasoning tasks that require keeping track of variables and their values. But how can they do that without explicit memory? 📄 Our new ICML paper investigates this in a synthetic setting! 🧵 1/13

Does vision training change how language is represented and used in meaningful ways?🤔 The answer is a nuanced yes! Comparing VLM-LM minimal pairs, we find that while the taxonomic organization of the lexicon is similar, VLMs are better at _deploying_ this knowledge. [1/9]

🔥 Excited to share MetaFaith: Understanding and Improving Faithful Natural Language Uncertainty Expression in LLMs🔥 How can we make LLMs talk about uncertainty in a way that truly reflects what they internally "know"? Check out our new preprint to find out! Details in 🧵(1/n):

🙇‍♂️NEW PAPER @ NAACL2025🔆 What type of learning is in-context learning? Is ICL a kind of gradient descent? Answer: the phenomenon of syntactic priming from psycholinguistics tells us that ICL behaves like error-driven learning! Paper: aclanthology.org/2025.naacl-lon… 🧵1/n

We wrapped up New England NLP 2025 at @YaleEngineering 🎉! 215 registrations from 37 institutions ✅ An amazing lineup of speakers 🎤 A heated panel 💬 86 posters and 5 oral presentations 🗣️ Attaching some sparkling moments captured by @_Chuhan_Li!

The Department of Linguistics at Yale University is seeking to hire a one-year lecturer with expertise in Computational Linguistics and/or Syntax for the 2025-2026 school year. See the job ad for more info: linguistlist.org/issues/36/1177… Please send to any who might be interested!

New England NLP 2025 is this Friday, at one of the most stunning campuses in the world! @Yale nenlp.github.io/spr2025/

Absolutely despicable that rather than bargaining with us to end this strike,@Wellesley College is forcing students to enroll in RANDOM courses. This completely devalues the Wellesley College educational experience. @Wellesley is making students pay the price.

私've 決ed to 始t 書iting 私y 英語 with some 漢字 in it, just to 見ee 何 起ens. The 振ri仮名 will be a bit 恣意的 at 一st, but that's 大丈夫. Nothing 始ts 完璧. 個人的ly, I 思ink it's not too 悪, I 出来n 読ead 何 私've 書itten here without much 難ty, but some 人 might not 好e it.

We're releasing a preview of OpenAI o1—a new series of AI models designed to spend more time thinking before they respond. These models can reason through complex tasks and solve harder problems than previous models in science, coding, and math. openai.com/index/introduc…

Exploring Bangkok 🇹🇭 at #ACL2024 @aclmeeting with old and new friends @XiaomengMZhu @ShengyueXiong @XuanmingZhang07 @zhaofeng_wu

Happening now at 117:)

✈️to Bangkok🇹🇭 for @aclmeeting #ACL2024 Will present at 𝐈𝐧-𝐏𝐞𝐫𝐬𝐨𝐧 𝐏𝐨𝐬𝐭𝐞𝐫 𝐒𝐞𝐬𝐬𝐢𝐨𝐧 𝟔 (𝐀𝐮𝐠 𝟏𝟒, 𝟏𝟎:𝟑𝟎) for our paper arxiv.org/abs/2403.06301 If you are interested in the intersection of linguistics, cogsci, and LLM, let's find a time to chat😊