Interested in LLM for reasoning and planning? Here is an ongoing list of relevant resources: github.com/samkhur006/awe…

Matryoshka Representation Learning (MRL) is a super exciting approach to improving the quality and efficiency of embedding models and strategies ✨ MRL allows models to store more information in the earlier dimensions of their data vectors. This method not only boosts

Consider applying for this opportunity to help LatinX talent in AI of the future! Deadline: September 20, 2024

Early in your career? Consider applying for this opportunity to receive guidance from experts in the field to improve your skills and your LatinX network.

🗞️ Paper - "A Note on LoRA" from Microsoft For deploying LoRA at scale. 📌 Describe one approach to enable serving multiple LoRA models at once, which can support requests pointing to multiple LoRA models, without swapping the LoRA weights, while maintaining latency comparable

📢 Glad to share two accepted papers at EMNLP 2025 #EMNLP2024 🎉 "Learning to Route for Dynamic Adapter Composition in Lifelong Language Learning" with Tuytelaars Lab "Probing the Linguistic and Visual Knowledge of Pixel-based Language Models" with Kushal Tatariya Miryam de Lhoneux/ @mdlhx.bsky.social

Happy to share that this paper has been accepted for #NeurIPS2024 NeurIPS Conference 🎉  This was a very large collaborative work that tackles cultural diversity benchmarking on LLMs. Thanks for your hard work David Romero Haryo thamar | Chenyang Lyu 吕晨阳 Alham Fikri Aji 🙌

What kind of childhood makes a top scientist? Is it enough to have all the right traits (brilliance, grit, etc) or do you need the right family too? And why should we care? A 🧵 on our paper on the Nobel Laureates. A teaser: the income distribution of the laureates' fathers.1/N

Excited to share our work on assessing LLMs' episodic memory! We present a new task, dataset, and a reference point from 155 humans who read a whole book. We highlight issues with memory in current LLMs 👇 We hope this can help develop models with better long-term memory!

We partnered with @HuggingFace to teach you how to fine-tune LLMs with GRPO! Learn about: • Reward functions + creating them • GRPO Math + Free Reasoning training in Colab • Applying RL to real-world use cases Course: huggingface.co/reasoning-cour… Tutorial: docs.unsloth.ai/basics/reasoni…

Hands-On Large Language Models! This repository contains the complete code examples from the book Hands-On Large Language Models. It includes notebook examples that cover everything from the introduction to language models to fine-tuning them. 100% Open Source

Happy to announce that BRIGTHER, a large human-annotated dataset for emotion recognition, was accepted at ACL 2025 #ACL2025! 🎉 Huge kudos to Nedjma Ousidhoum نجمة أوسيدهم and Shamsuddeen Hassan Muhammad, PhD for leading this effort! #ACL #NLP #Dataset #AI

Our paper BRIGHTER received the Best Resource Paper Award! Congratulations to all collaborators! #ACL2025NLP Masakhane

🚀 It’s official: #SALA2026 (formerly #RIIAA) is coming to Quito, Ecuador, March 9–12, 2026! 🎓 Hosted at USFQ 💡 Applications (with travel grants!) are open — deadline Oct 1! Apply now to be part of Latin America’s top AI summit SALA AI

Pleased to announce our #NLProc shared task SemEval Task 7: Everyday Knowledge Across Diverse Languages & Cultures. We extend the BLEnD Benchmark to >30 language-culture pairs. [Our task is Junior-friendly, with live Q&A & tutorials.] codabench.org/competitions/1… 1/