Are lasers the future of anti-drone warfare? A drone appears on the grainy, gray-scaled image of the thermal camera. This is the type of drone used by groups such as Hezbollah, Hamas and the Yemeni Houthis. Seconds later, the wing of the drone snaps off, sending it tumbling down, exploding when it hits the ground. This is a video shared by the Israeli Ministry of Defence and arms producer Rafael, a hint towards the future of anti-drone warfare.

The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate images and specify their preferences. Using this web app we build Pick-a-Pic, a large, open dataset of text-to-image prompts and real users'

We show our framework's flexibility by providing a comprehensive

Our theoretical analysis reveals that in this setting, in-context learning is more about identifying the task than about learning it, a result which is in line with a series of recent empirical findings.

Neural Information Processing Systems http://nips.cc/

This paper discusses one of the most fundamental issues about point processes that what is the best sampling method for point processes. We propose thinning as a downsampling method for accelerating the learning of point processes.

This raises a challenging research question: How can we keep improving the systems when their capabilities have surpassed the levels of humans?

Neural Information Processing Systems http://nips.cc/