In this post, we'll explore two multi-agent LLM libraries - Camel and Langroid!

In this article, which is part two, we'll be deep diving into LangChain's implementation of generative agents, to better understand what's changed in recent months.

A birds-eye view of in-context learning in LLMs.

In this article, I'll be improving LangChain's generative agents implementation.

Exploring what actually works in prompt engineering

Surveying a practical survey guide on LLMs from ChatGPT onward and understanding the directions of LLM research!

Belebele, a 122-language parallel evaluation benchmark for NLU & Qwen-VL a vision-language model fine-tuned on instructions!

Using tools with the Gorilla LLM family, generating higher quality images with SDXL and software engineering with MetaGPT!

A round-up of some of the biggest and most significant changes in the world of artificial intelligence in recent weeks — from LLaMA2 to Meta-Tranformer, and beyond.

Anthropic's new Claude model, LongNet & scaling to a billion tokens, and extracting information from unstructured data with Quivr!

Inflection AI, an artificial intelligence startup with just a couple years of existence, has raised $1.3B to fund their product, Pi, a ChatGPT competitor.

Meet AudioPaLM, a text-only decoder-based large language model (LLM) for speech translation and speech-to-text translation that uses text and audio tokens.

A Simple ViT with no bells and whistles.

The Open LLM Leaderboard's new rank #1 and DIDACT, a more capable code assistant.

Here's a round-up of the Tree of Thoughts, Second-order Clipped Stochastic Optimization (Sophia), GOod at Arithmetic Tasks( Goat), QLoRA, and other ML news.

From ChatGPT iOS to HuggingFace Agents, it's been a busy week in the world of machine learning. Here's a roundup of some of the latest developments in the field.

A round-up of Google's PaLM 2, a large language model to compete with OpenAI's GPT-4, MaMMUT, a vision encoder, and an upgrade to Anthropic's Claude model.

A hot new Python Language, Scaling up the context length of transformers, YOLO-NAS achieves SOTA, foundation models, and more!

Track-Anything applies SAM, XMem, and E2FGVI to videos, providing video inpainting capabilities, as well as video and multi-object tracking with segmentation masks.

Jarvis, Anthropic and more LLM and GPT news.

A general-purpose image segmentation model called Segment Anything Model (SAM) was just released from Meta AI. Here's my take.

In this article, I summarize the finding the in the March 31, 2023 paper "A Survey of Large Language Models".

Twitter's rec system (with W&B integration) uploaded to GitHub, HuggingGPT, Reflexion, and more. There's a lot going on in ML.

Google BARD just rolled out their own experimental site for their ChatGPT and GPT-4 rival, BARD.

PaLM but now with the ability to reason and understand images!

HuggingFace has launched support for ControlNet — imposing greater control (and speed) for the image synthesis process for diffusion models, such as Composer.

Up to 65-billion parameters, LLaMA is an open source model more performant than other other LLMs at certain tasks with much less computation.

Wildlife Protection Solutions (WPS) are a non-profit who are dedicated to utilizing AI — and, specifically, object detection — to protect endangered species.

Microsoft's new Bing AI can generate some interesting responses when prompted a certain way.

This paper is argues for a paradigm shift in text classification for online safety.

Token Merging: Your ViT But Faster.

GPTScore, a dynamic, multi-faceted approach to evaluating generative models on a variety of tasks and aspects.

Empirical study figuring out what methods best help a language model learn more languages.

Google today announced Bard, a potential ChatGPT's potential competitor with a potentially large impact on website publisher.

If you're one of the few using Bing, it just got a cool upgrade.

Improving the exchange in ML ideas via code with PyGlove.

Funding rounds, Google's OSS Vizier, and a ChatGPT open-source equivalent.

Google has recently released MusicML, a language model that can turn descriptive text about music into actual music!

Competing against diffusion models with GANs.

An AI tool was recently made to predict the age of mosquitoes.

Zorro a paper by DeepMind and University of Oxford VGG Department of Engineering Science introduce a unique approach to accounting for multiple modalities.

Microsoft confirmed they are investing upwards of $10 billion into OpenAI.

Much like Microsoft, twitter, Meta, and more, Google has unfortunately laid off thousands of workers. ChatGPT and Microsoft may rival Google's search engine.

InstructPix2Pix edits images via text instructions and boasts fast editing.

T2M-GPT simulates human motion from text descriptions.

Gigged.AI, a based in London, England raised £1.6m in funding recently!

HugginFace's GLM-130B is a bilingual model trained on Chinese and English.

Meropy, a startup specializing in an AI-centric approach to crop monitoring, developed a small robot called SentiV!

DeepL's recent funding round has raised over $100 million (USD)!

Microsoft is in negotiations with OpenAI, with an offer to invest $10 billion into the company for a 49% stake.

ChatGPT has taken the tech sector and a number of other industries by storm. What does it entail?

Google and Intel introduce the 4th Gen Intel Xeon Processor, optimizing matrix multiplication.