Safe reinforcement learning (RL) requires the agent to finish a given task while obeying specific constraints.

The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content.

Unsupervised Graph Domain Adaptation (UGDA) involves the transfer of knowledge from a label-rich source graph to an unlabeled target graph under domain discrepancies. Despite the proliferation of methods designed for this emerging task, the lack of standard experimental settings and fair performance comparisons makes it challenging to understand which and when models perform well across different scenarios.

In this work, we ask the question of whether pre-trained transformer models of chemical structures encode representations that are aligned with human olfactory perception, i.e., can transformers smell like humans?

To this end, we propose SpatialPIN, a framework that utilizes progressive prompting and interactions between VLMs and 2D/3D foundation models as "free lunch" to enhance spatial reasoning capabilities