A.2.5 Loss Function and Optimizer For all the experiments except N-MNIST in this work, we use cross entropy and stochastic gradient

In total we have 1200 comparisons, and each comparison is rated by 3 raters. In total we have 2400 comparisons, and each comparison is rated by 3 raters. These were: 1. Coherence: Is the system's generation aligned in meaning and topic with the prompt? We sampled 100 prompts randomly from the corpus, and then evaluated 19 different algorithms. HITs was 2.2K, and the total number of ratings was 6.6K.

As explained in Section-4.1 of the Main Paper, we propose to utilize a curriculum schedule for training

Open-vocabulary 3D object detection has recently attracted considerable attention due to its broad applications in autonomous driving and robotics, which aims to effectively recognize novel classes in previously unseen domains. However, existing point cloud-based open-vocabulary 3D detection models are limited by their high deployment costs. In this work, we propose a novel open-vocabulary monocular 3D object detection framework, dubbed OVM3D-Det, which trains detectors using only RGB images, making it both cost-effective and scalable to publicly available data. Unlike traditional methods, OVM3D-Det does not require high-precision LiDAR or 3D sensor data for either input or generating 3D bounding boxes. Instead, it employs open-vocabulary 2D models and pseudo-LiDAR to automatically label 3D objects in RGB images, fostering the learning of open-vocabulary monocular 3D detectors. However, training 3D models with labels directly derived from pseudo-LiDAR is inadequate due to imprecise boxes estimated from noisy point clouds and severely occluded objects.

Partner diversity is known to be crucial for training a robust generalist cooperative agent. In this paper, we show that partner specialization, in addition to diversity, is crucial for the robustness of a downstream generalist agent. We propose a principled method for quantifying both the diversity and specialization of a partner population based on the concept of mutual information. Then, we observe that the recently proposed cross-play minimization (XP-min) technique produces diverse and specialized partners. However, the generated partners are overfit, reducing their usefulness as training partners.