I just edited my lecture - Beginner's Guide to RAG - and posted to YouTube. I gave this lecture last May. Do you like it? If so, I will edit and post more lectures like this, whenever I have some free time. Link is in the comment below. 👇

Wow, congratulations 🎉! A team achieved a performance of 24.68% on Spider 2.0-Snow. Are there any better methods out there? 🧐 spider2-sql.github.io

Wow Mistral has released its new model tailor-made for AI code assistants Codestral 25.01 (that's its name) is debuting at #1 on the LMsys copilot arena leaderboard 🔥 You can already use it for free in Continue (100% open-source) for VS Code

Alphaxiv is an awesome way to discuss ML papers -- often with the authors themselves. Here's an intro and demo by Raj Palleti at #neurips2024 .

Combine RAG with reasoning models like o1. Search-o1 modifies the RAG to work with reasoning models like OpenAI o1 or QwQ o,utperforming traditional RAG systems by integrating retrieved information into the Chain of Thought! 👀 Implementation 1️⃣ Choose a Reasoning LLM, e.g.

Excited to teach Advanced NLP at CMU this semester! Slides are on the course page as the course proceeds: cmu-l3.github.io/anlp-spring202… Lectures will be uploaded to Youtube: youtube.com/playlist?list=…

Foundations of LLMs This amazing new LLM book just dropped on arXiv. 200+ pages! It covers areas such as pre-training, prompting, and alignment methods. It looks like a great intro to LLMs for devs and researchers.

7). Enhancing RAG - systematically explores the factors and methods that improve RAG systems such as retrieval strategies, query expansion, contrastive in-context learning, prompt design, and chunking. x.com/omarsar0/statu…

I taught Lesson 1 - Agent yesterday. I am so glad to receive so many submissions from people all over the world! Here are some of their beautiful drawings! Join the course 👉 byhand.ai/p/introduction…

NEW: Google DeepMind just introduced Gemma 3 Gemma 3 looks like a strong open long-context and multimodal model. Gemma 3 is a lightweight open model family (1B–27B parameters) that integrates vision understanding, multilingual coverage, and extended context windows (up to 128K

Fully local multi-agent systems with LangGraph With the release of OpenAI agent SDK, there's high interest in multi-agent systems. We review Swarm and Supervisor based multi-agent systems and run both locally w/ ollama + LangGraph. 📽️: youtu.be/4oC1ZKa9-Hs

Paper: alphaxiv.org/abs/2503.19470

Universal RAG RAG is dead, they said. Then you see papers like this and it gives you a better understanding of the opportunities and challenges ahead. Lots of great ideas in this paper. I've summarized a few below:

Want to 𝐜𝐮𝐭 𝐑𝐅𝐓 𝐭𝐫𝐚𝐢𝐧𝐢𝐧𝐠 𝐭𝐢𝐦𝐞 𝐛𝐲 𝐮𝐩 𝐭𝐨 𝟐× and boost performance? 🚀 Meet 𝑨𝒅𝒂𝑹𝑭𝑻 — a lightweight, plug-and-play curriculum learning method you can drop into any mainstream RFT algorithms (PPO, GRPO, REINFORCE). Less compute. Better results. 🧵 1/n

📢 A reminder that the NeurIPS deadline for full paper submission is May 15th (Anywhere on Earth, AOE). We look forward to receiving your work, good luck to all submitting authors!

Our paper, Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries, has been accepted to #ACL2025NLP Findings! Thanks to the co-authors, Yusuke Ide , Justin, yusuke_sakai , Yingtao Tian , Hidetaka Kamigaito , tarowatanabe !

Super thrilled to share GMMLU is accepted to #ACL2025 main conference 🎉 It was also recently recognised by Stanford HAI as one of the significant AI releases of 2024 🚀 I had a blast collaborating on this closely with Beyza Ermiş and all our collaborators! Huge congrats!💙

I am pleased to announce a new version of my RL tutorial. Major update to the LLM chapter (eg DPO, GRPO, thinking), minor updates to the MARL and MBRL chapters and various sections (eg offline RL, DPG, etc). Enjoy! arxiv.org/abs/2412.05265

abs: arxiv.org/abs/2505.12082

A 24-trillion-token web dataset with document-level metadata just dropped on Hugging Face License: apache-2.0 ESSENTIAL-WEB v1.0 collects 24 trillion tokens from Common Crawl. Each document is labeled with a 12-field taxonomy covering topic, page type, complexity, and quality