Cute robots, lightweight EVs and a surprisingly quiet leaf blower are among the tech that stood out as the show winds down. Two OlloBots -- one with a long furry purple neck, making it about two feet taller than the other -- are pictured on a light purple floor, in front of a screen displaying a closeup of a child playing with blocks. Even as CES 2026 wraps up soon, there's no shortage of standout hardware hiding in plain sight. From genuinely quieter yard tools to ultra-light EVs and companion robots that want to remember your family, Day 3 was all about tech that felt a little more considered -- and in some cases, refreshingly practical. If you can't get enough of CES, be sure to check out our picks for best of CES 2026, which highlights the most impressive new tech we've seen in Las Vegas.

Unobserved confounding arises when an unmeasured feature influences both the treatment and the outcome, leading to biased causal effect estimates. This issue undermines observational studies in fields like economics, medicine, ecology or epidemiology. Recommender systems leveraging fully observed data seem not to be vulnerable to this problem. However many standard practices in recommender systems result in observed features being ignored, resulting in effectively the same problem. This paper will show that numerous common practices such as feature engineering, A/B testing and modularization can in fact introduce confounding into recommendation systems and hamper their performance. Several illustrations of the phenomena are provided, supported by simulation studies with practical suggestions about how practitioners may reduce or avoid the affects of confounding in real systems.

It can be difficult to interpret a coefficient of an uncertain model. A slope coefficient of a regression model may change as covariates are added or removed from the model. In the context of high-dimensional data, there are too many model extensions to check. However, as we show here, it is possible to efficiently search, with a branch and bound algorithm, for maximum and minimum values of that adjusted slope coefficient over a discrete space of regularized regression models. Here we introduce our algorithm, along with supporting mathematical results, an example application, and a link to our computer code, to help researchers summarize high-dimensional data and assess the stability of regression coefficients in uncertain models.

In this paper, we present a computer vision-based approach to measure the sizes and growth rates of apple fruitlets. Measuring the growth rates of apple fruitlets is important because it allows apple growers to determine when to apply chemical thinners to their crops in order to optimize yield. The current practice of obtaining growth rates involves using calipers to record sizes of fruitlets across multiple days. Due to the number of fruitlets needed to be sized, this method is laborious, time-consuming, and prone to human error. With images collected by a hand-held stereo camera, our system, segments, clusters, and fits ellipses to fruitlets to measure their diameters. The growth rates are then calculated by temporally associating clustered fruitlets across days. We provide quantitative results on data collected in an apple orchard, and demonstrate that our system is able to predict abscise rates within 3.5% of the current method with a 6 times improvement in speed, while requiring significantly less manual effort. Moreover, we provide results on images captured by a robotic system in the field, and discuss the next steps required to make the process fully autonomous.

Article: AI robot Kashef with today's World Cup 2022 predictions – Day 3 - Al Jazeera An artificial intelligence program called Kashef has been taking in historical and other data to attempt to predict who will win matches in the World Cup of 2022. Read the article above to see who it thinks will win on Day 3. Come back here for all the latest on Artificial Intelligence News and to learn how to use Artificial Art Tools.

Some humans would say a football match is impossible to predict with any great certainty, but Kashef, our Artificial Intelligence (AI) predictor, would disagree. Kashef has been playing with historical data and performance to predict the results of each game all the way to the final. No surprise that Kashef is backing Lionel Messi and his team to beat the Green Falcons in today's first fixture. Kashef is siding with the Danish Dynamite on this one. However, Tunisia still stands an almost 50 percent chance of picking up at least a point.

This week I'm targeting to finish at-least day 7 of Deep learning in my free time post work and over the weekend.

This work describes the development and validation of a fully automated deep learning model, iDAScore v2.0, for the evaluation of embryos incubated for 2, 3, and 5 or more days. The model is trained and evaluated on an extensive and diverse dataset including 181,428 embryos from 22 IVF clinics across the world. For discriminating transferred embryos with known outcome (KID), we show AUCs ranging from 0.621 to 0.708 depending on the day of transfer. Predictive performance increased over time and showed a strong correlation with morphokinetic parameters. The model has equivalent performance to KIDScore D3 on day 3 embryos while significantly surpassing the performance of KIDScore D5 v3 on day 5+ embryos. This model provides an analysis of time-lapse sequences without the need for user input, and provides a reliable method for ranking embryos for likelihood to implant, at both cleavage and blastocyst stages. This greatly improves embryo grading consistency and saves time compared to traditional embryo evaluation methods.

Deep Learning Indaba is currently taking place in Tunis, Tunisia. Find out what the participants and organisers have been up to in this round-up of tweets from attendees. This has me really thinking about how humans do this so seamlessly and the effort required from a deep learning perspective. Gabriela Csurka is delivering a powerful keynote speech on "Visual Domain Adaptation in the Deep Learning Era" at the @DeepIndaba #DLIndaba2022. Follow us to get the most recent updates of the #DLIndaba2022.

We may have lost the company payroll on the casino floor but that doesn't mean we don't still have a day of great events coming live from the CNET stage. You'll find us outside of the Tech West area at the Sands Expo Center. Can't join us here in Las Vegas? No problem: We're bringing our final day of live programming to you right here. Be sure to catch up on the highlights from the show floor while you're here and head over to our dedicated CES homepage to find out about everything that happened here in Sin City.