Inspecting bridges, creating digital twins, and making self-driving cars safer are just a few uses, but many different industries will find uses for AI models that reason about 3D space.

Rex-Omni is a 3B-parameter Multimodal Large Language Model (MLLM) that redefines object detection and a wide range of other visual perception tasks as a simple next-token prediction problem.

This repository contains the code related to ICLR 2024 paper "Reward Model Ensembles Help Mitigate Overoptimization". We hope you can find the code, models, and datasets provided helpful for your own ...