Twitter Beğeni Hilesi

This 76-page paper on Prompting Techniques has become quite popular. A nice read for your weekend. - "The Prompt Report: A Systematic Survey of Prompting Techniques": ✨ Explores structured understanding and taxonomy of 58 text-only prompting techniques, and 40 techniques for

The paper we have been waiting for essentially shows that #timeseries #llms do not work in forecasting. Back in 2022, paper “Are Transformers Effective for Time Series Forecasting?“ challenged the appearing narrative that transformers are useful for forecasting. By removing

Looks like an exhaustive work here, a 103 page long Synthetic Data Generation paper. "Comprehensive Exploration of Synthetic Data Generation: A Survey" 👨‍🔧 Surveys 417 Synthetic Data Generation (SDG) models over the last decade. 📌 Covers 20 distinct model types, further

I am excited to be giving a 4-hour tutorial on "Pretraining and Finetuning LLMs from the Ground Up" at the SciPyConf conference in 5 days! This tutorial is aimed at coders interested in understanding the building blocks of large language models (LLMs), how LLMs work, and how to

Understanding Deep Learning Impressive new book on understanding deep learning concepts. Topics include fundamental building blocks, Transformers, GNNs, RL, diffusion models, and more. Probably one of the most comprehensive and up-to-date overviews of deep learning that exist

Blog post on DSPy

The "Multi-token Prediction" paper (April-2024) from AI at Meta and behind the Chameleon family of models is such an innovative idea. 👨‍🔧 Original Problem it solves Most LLMs have a simple training objective: predicting the next word. While this approach is simple and scalable,

In this work, we propose a combination of RAG and synthetic data generation -- retrieval-augmented dataset generation. We find that this generates higher-quality data and significantly improves downstream performance.

Ever wondered about the most effective and cost-efficient way to use LLMs for your astronomical research? In collaboration with colleagues from Oak Ridge, Argonne National Labs and ADS, the AstroMLab is proud to present the first comprehensive review (45 pages) benchmarking

A Survey of Prompt Engineering Methods in LLMs Huge collection of prompt engineering methods for all sorts of NLP tasks.

Great paper! I think the answer to the perennial question "is scale all you need?" is now rather obviously "you need scale, but scale is not all you need." This paper convincingly summarizes evidence for this.

One of the best resources on Time Series Forecasting in Python

Launching the 1st Arena for Embedding Models: MTEB Arena🏟️ Vote @ hf.co/spaces/mteb/ar… ⚔️ 15 Models: OpenAI Google cohere Voyage AI Jina AI Salesforce AI Research Nomic AI E5 GritLM BGE.. 3 Tasks: Retrieval/Clustering/STS Deep dive with me on embeddings & the arena👇 🧵1/13

Transformer Explainer Really cool interactive tool to learn about the inner workings of a Transformer model. Apparently, it runs a GPT-2 instance locally in the user's browser and allows you to experiment with your own inputs. This is a nice tool to learn more about the

I don’t post video tutorials (that) often, but hey, I just saw that I got 30k subs on YouTube! If you’re looking to learn something new this weekend, I recently made video on how LLMs work, breaking down the development stages step by step: youtube.com/watch?v=kPGTx4…

We believe this project is the beginning of an exciting journey to explore the full potential of AI-driven research, including AI-driven AI research. github.com/SakanaAI/AI-Sc… We’re happy to open-source The AI Scientist, and continue developing this technology with the community.

📝 Check out the proceedings: aclanthology.org/volumes/2024.s… 🔗Get all the details about the program: sdproc.org/2024/program.h… 🙌 This workshop is organized by​​ Tirthankar Ghosal, Philipp Mayr, Anita de Waard, Aakanksha Naik ✈️ NAACL 2024, Amanpreet Singh, Orion Weller, Shannon Shen, Yanxia Qin, Yoonjoo Lee

I recently wrote a blog post on embedding models for RAG. As a follow-up, here's a notebook on how to quickly compare embedding models on _your_ unstructured data with synthetically generated eval dataset and metrics like recall and MRR: colab.research.google.com/drive/132oXSGS…

Absolute banger of a blogpost: Omar Khattab's "project-first" research mindset distilled into one succinct post.

Incredible LLM Creation Visualization in this Site. Click on each section, like Embedding, LayerNorm, Self Attention, and it will show you the mechanics of that section. (link in comment)