RT @CisLmu: 🥳 We are happy to share that CIS will be presenting 26 papers at #ACL2025! . We've organized them by date, time, and location,….

I'm at the @aclmeeting to present our papers on multilingual evaluation, programming languages, and translation! #ACL2025 .Feel free to stop by to exchange ideas and discuss!. I’m also on the job market. If you think there’s a potential fit, I’d love to hear from you.

RT @emrecanacikgoz: I'll be @aclmeeting in Vienna to present our recent agent papers SMART and CoALM! 🇦🇹🤖 #acl2025 . Feel free to stop by o….

RT @MeltWorkshop: ⏰ Reminder: Conference Track Deadline is July 25!. Have a paper accepted to @COLM_conf that aligns with linguistic & cult….

I'll be presenting two papers at ACL 2025 - Hall 4/5 :.- "MEXA: Multilingual LLM Evaluation" — Monday, July 28, 18:00-19:30 . - "How Programming Concepts and Neurons Are Shared in Code LLMs" — Wednesday, July 30, 11:00-12:30.

I'll be on the job market in Fall 2025, looking for opportunities in research or applied NLP (postdoc or industry). If you think there’s a potential fit, I’d love to connect!.Website: CV: I'll also be attending ACL 2025.

RT @gui_penedo: FineWeb2 🥂 has been accepted to @COLM_conf . See you in October 🇨🇦

RT @gui_penedo: We have finally released the 📝paper for 🥂FineWeb2, our large multilingual pre-training dataset. Along with general (and ex….

RT @MeltWorkshop: 🧑‍💻 Call for Reviewers – Melt Workshop @COLM_conf 2025 🌍. We're looking for researchers passionate about multilingual, m….

RT @HaneulYoo13: Are you working on multilingual, multicultural #LLM? Interested in diverse & inclusive language modeling?. 😎 Stay tuned at….

This work has been accepted as a Findings paper at ACL 2025 (@aclmeeting), in collaboration with @yhLiu96, François Yvon, and @HinrichSchuetze. Code available at:

We observe both similarities and differences in how LLMs represent natural languages versus prgramming langauges.

New paper: How does pretraining on programming languages + English shape LLMs' concept space?.🔍Do LLMs use English or a programming language as a kind of pivot language?.🧠Are neurons language-specific or shared across programming languages and English?.🔗

Consider submitting your multilingual NLP work to the MELT workshop @ COLM 2025: Deadline: June 23.

RT @HEI: Tracing Multilingual Factual Knowledge Acquisition in Pretraining.

#overleafdown is up now!

I really wanted to see the review details. It's clearly above the acceptance threshold of findings for me. When you fall into the cycle of rejection from ARR, it's hard to come out.

RT @DBahdanau: I'm embarassed to admit that I have just grokked how amazing Python coroutines and asyncio are. I want to rewrite every si….

It’s probably just a bug for Qwen3-30B-A3B. But for Gemma 3, another similar issue exists — since it uses a bidirectional architecture and doesn’t yet support fast attention kernels, most implementations fall back to PyTorch’s SDPA, which is slower by default.

I'm using Qwen3-30B-A3B with the Hugging Face library. It's very slow, and GPU utilization is quite low. I thought I was the only one experiencing this issue, but even @ollama seems to have the same problem: @lmstudio seems fine though.