PhD Student in Computational Linguistics @univienna
Joined April 2024
- Tweets15
- Following74
- Followers18
- Likes149
Marie-Leontine Wörgötter retweeted
We finally found the @ViennaNLP account details again 😅
Here’s a photo of some of the group at #ACL in San Diego a few weeks ago! (missing here is @sebschu, who'd already headed off for lunch!) #ACL2026 #nlproc
Marie-Leontine Wörgötter retweeted
On my way to San Diego for #acl2026nlp now!
My PhD Student @nedwards99 (along with BU colleagues @yukyunglee_ and @audreymao100
) will present our poster on evaluating Coding agents on novel research tasks on Tuesday at 9:00am.
Marie-Leontine Wörgötter retweeted
RExBench is now available in Terminal Bench (@harborframework)! 🎉
We integrate 2 tasks (cogs, othello) along with a local testing framework so you can test if your agents can autonomously implement novel AI research extensions.
Marie-Leontine Wörgötter retweeted
🧵 Do coding agents know when to ask for help?
Real-world coding tasks are rarely fully specified, yet most agents are optimized to execute autonomously rather than clarify.
Marie-Leontine Wörgötter retweeted
Diffusion LLMs can think EoS-by-EoS!
The higher the generation length, the better the performance of Masked Diffusion LLMs, even though they generate the same amount of words and only augment them with more and more EoS tokens 👀
Marie-Leontine Wörgötter retweeted
honestly surprising that you don’t see the linguists celebrating in the LLM era
they didn’t make much progress but at least they were studying the right thing
if i were a real linguist, i’d be bragging all the time about having modeled language for decades before LLMs
Marie-Leontine Wörgötter retweeted
Claim: gpt-5-pro can prove new interesting mathematics.
Proof: I took a convex optimization paper with a clean open problem in it and asked gpt-5-pro to work on it. It proved a better bound than what is in the paper, and I checked the proof it's correct.
Details below.
