GitHub - cliangyu/Cola: [NeurIPS2023] Official implementation of the paper "Large Language Models are Visual Reasoning Coordinators"

1. Meta Quietly Unveils Llama 2 Long AI That Beats GPT-3.5 Turbo and Claude 2 on Some Tasks

Meta is releasing Llama 2 Long, an enhanced version of Llama 2 that underwent continual pretraining with longer training sequences and upsampled long texts. By adding 400 billion tokens and making minor changes to the Rotary Positional Embedding (RoPE), Llama... See more

LLaVA v1.5, a new open-source multimodal model stepping onto the scene as a contender against GPT-4 with multimodal capabilities. It uses a simple projection matrix to connect the pre-trained CLIP ViT-L/14 vision encoder with Vicuna LLM, resulting in a robust model that can handle images and text. The model is trained in two stages: first, updated ... See more

Our extensive test over 25 LLMs (including APIs and open-sourced models) shows that, while top commercial LLMs present a strong ability of acting as agents in complex environments, there is a significant disparity in performance between them and open-sourced competitors.

Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration

1 2 Chenyang Lyu, 3 Minghao Wu, 1 * Longyue Wang, 1 Xinting Huang,

1 Bingshuai Liu, 1 Zefeng Du, 1 Shuming Shi, 1 Zhaopeng Tu

1 Tencent AI Lab, 2 Dublin City University, 3 Monash University

* Longyue Wang is the corresponding author: vinnlywang@tencent.com

Macaw... See more