We draw parallels between the behavior of LLMs and the evolution of human culture, as the latter has been extensively studied by cognitive scientists for decades.

Recent text-to-image (T2I) generation models have demonstrated impressive capabilities in creating images from text descriptions.

Large language models (LLMs) are trained on a deluge of text data with limited quality control. As a result, LLMs can exhibit unintended or even harmful behaviours, such as leaking information, fake news or hate speech.

Robotics tasks are highly compositional by nature.

This work focuses on the active learning in video captioning.

One-shot pruning techniques offer a way to alleviate these burdens by removing redundant weights without the need for retraining. Y et, the massive scale of LLMs often forces current pruning approaches to rely on heuristics instead of optimization-based techniques, potentially resulting in suboptimal compression.

Multiple Sequence Alignment (MSA) plays a pivotal role in unveiling the evolutionary trajectories of protein families.