visual agents

AGENT: A Benchmark for Core Psychological Reasoning

In this seminar, I talk about the recently released paper “AGENT: A Benchmark for Core Psychological Reasoning. @misc{agent2021shu, doi = {10.48550/ARXIV.2102.12321}, url = {https://arxiv.org/abs/2102.12321}, author = {Shu, Tianmin and Bhandwaldar, Abhishek and Gan, Chuang and Smith, Kevin A.

Differentiable Rendering and Adversarial Learning

SAILenv: Learning in Virtual VisualEnvironments Made Simple

Recently, researchers in Machine Learning algorithms, Computer Vision scientists, engineers, and others, showed a growing interest in 3D simulators as a mean to artificially create experimental settings that are remarkably close to those in the real …

Learning in Virtual Environments

Recently, there have been many breakthroughs in computer vision thanks to Deep Learning. The availability of huge annotated datasets was one of the reasons of this success, if not the most important. However, these datasets have usually been static …