🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Super excited that Croissant was accepted as a 🌟spotlight paper at NeurIPS Conference! Croissant is a community-built vocabulary for ML datasets, making them easily discoverable & usable across tools & platforms. Huge credit to the entire MLCommons Croissant community! 1/3

Fully funded PhD opportunities at Munich Center for Machine Learning! Applications open on 15 October 2024. Feel free to reach out if you're interested in research topics at CIS, LMU Munich. Our Principal Investigators: hinrich schuetze, Barbara Plank, and Michael A. Hedderich.

🎭Recent work shows that models’ inductive biases for 'simpler' features may lead to shortcut learning. What do 'simple' vs 'complex' features look like? What roles do they play in generalization? Our new paper explores these questions. arxiv.org/pdf/2407.06076 #Neurips2024

Fine-tuning for document relation extraction (DocRE) with factual datasets? Beware of inconsistent model performance! No worries, we've got you CovEReD! A dataset generation pipeline for consistency evaluation and training robust RE models while staying performant. (1/4) 🧵

Happening soon at West #5005 #NeurIPS2024 Come for one, stay for two CRL posters :)

Excited to announce that we are establishing my team at Sabancı! My project on LLM Privacy just got funded by Tübitak. We will recruit a postdoctoral researcher and a PhD student. Come join our team and let’s do exciting research that will help people! dilarakkl.github.io/posts/2025-02-…

Are LLMs linguistically productive and systematic in morphologically-rich languages as good as humans? No 🤨 Our new NAACL 2025 paper (arxiv.org/abs/2410.12656) reveals a significant performance gap between LLMs and humans in linguistic creativity and morphological generalization.

‘Forgive me, mother. This is the path I chose—to help people.’ These were the last words of Rifaat Radwan, who filmed his own murder in Rafah. He was part of a Red Crescent convoy aiding wounded civilians. The convoy—clearly marked, unarmed, with flashing lights—was attacked on

I’ll be presenting MemLLM, our recently TMLR-published paper 🎉, at the New Frontiers in Associative Memory Workshop @ ICLR 2025 (Oral)! 📍 Hall 4 #5 📅 Sun, Apr 27 | ⏰ 11:30–11:45AM Happy to grab a coffee and chat about research (memory, long-context, LLMs…) or anything else!

I'm at NAACL HLT 2025 this week, presenting our work on multilinguality. I'm currently looking for research positions and would love to connect and chat about multilinguality and LLMs. Looking forward to seeing many of you there!

Gutted to miss #NAACL2025 😭 but Miles Miles Williams will be there presenting the following papers: 📄 Main: Self-Calibration for Language Model Quantization and Pruning 📄 RepL4NLP: Vocabulary-Level Memory Efficiency for LM Fine-Tuning Check them out!