E-commerce click-stream data and product catalogs offer critical user behavior insights and product knowledge. This paper propose a multi-modal transformer termed as PINCER, that leverages the above data sources to transform initial user queries into pseudo-product representations. By tapping into these external data sources, our model can infer users' potential purchase intent from their limited queries and capture query relevant product features. We demonstrate our model's superior performance over state-of-the-art alternatives on e-commerce online retrieval in both controlled and real-world experiments. Our ablation studies confirm that the proposed transformer architecture and integrated learning strategies enable the mining of key data sources to infer purchase intent, extract product features, and enhance the transformation pipeline from queries to more accurate pseudo-product representations.

Artificial intelligence is getting down in the weeds. An AI-powered robot that can distinguish weeds from crops and remove them could eventually be used as an alternative to chemical insecticides. Kevin Patel and Nihar Chaniyara at tech start-up AutoRoboCulture in Gandhinagar, India, have created a prototype of the device, called Nindamani, specifically for cauliflower crops. The robot is powered by a pre-existing image-recognition algorithm.

Artificial intelligence is getting down in the weeds. An AI-powered robot that can distinguish weeds from crops and remove them could eventually be used as an alternative to chemical insecticides. Kevin Patel and Nihar Chaniyara at tech start-up AutoRoboCulture in Gandhinagar, India, have created a prototype of the device, called Nindamani, specifically for cauliflower crops. The robot is powered by a pre-existing image-recognition algorithm.

Product design and development firm Cambridge Consultants created a medical robot capable of performing one of the world's most common but delicate operations: cataract surgery. Carried out around 20 million times per year, this life-changing surgery helps restore sight when a patient develops cataracts, turning their eye cloudy and making it hard for them to see. To counter this, surgeons slice a tiny hole in the eye's lens, remove the part which has clouded over and replace it with a plastic lens -- similar to a contact lens but inside, rather than outside, the eye. While cataract surgery is common, however, things can and do go wrong. The lens being operated on is just 10mm across and -- while surgeons are necessarily steady-handed -- they are performing a 15-20-minute procedure on a tiny surface, using little more than tweezers and a microscope.

A new surgical robot can make the micro-scale movements needed for a particularly delicate procedure: cataract surgery. Axsis, a system developed by Cambridge Consultants, is a small, teleoperated robot with two arms tipped with tiny pincers. It's designed to operate on the eye with greater accuracy than a human. Globally, 20 million people have cataract surgery every year, making it one of the most common surgeries in the world. Although complications are very rare, they still affect tens of thousands of people. Cataracts happen when the natural lens of the eye gets cloudy and obscures vision.