We present Lotus, a diffusion-based visual foundation model for dense geometry prediction. With minimal training data, Lotus achieves SoTA performance in two key geometry perception tasks, i.e., ...
This repository contains code for training a reinforcement learning (RL) agent to drive autonomously in Trackmania Nations Forever. The agent learns to race on a track by interacting with the game ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results