PCWorld tested the $1,500 Narwal Flow 2 robot vacuum/mop against eight challenging messes including raw egg, olive oil, coffee spills, and mud to evaluate its premium cleaning capabilities. The device excelled at tough stains by intelligently switching between vacuum and mop modes, effectively cleaning most spills with minimal residue remaining. Despite strong overall performance, the Flow 2 struggles with grout cleaning and requires weekly maintenance to prevent odors from improper drying. If a job is worth doing, it's worth doing right--and if a robot is going to clean up my place, it better do a good job. That's the stance I took when Narwal sent me its luxury Flow 2 robot vacuum/mop.

Narwal's first mattress vacuum heats, taps, UV-blasts and sucks up all the ick living in your bed At CES, the robotic cleaning brand also showed off its new flagship mop vac than can track down your pets. The Narwal U50 series mattress vac held aloft on the CES Unveiled floor. Narwal brought new cleaning robots with it to CES this year, including the Narwal Flow 2, it's latest flagship robo mop-vac, and the Narwal U50, an automatic mattress vac designed for "deep mite removal." While I'd hoped the latter vac was an automatic crawler that could navigate your mattress top, the U50 is a handheld device. Still, no one likes to think about what filters down into their mattress as they sleep -- and there are lots of opinions on how and why to remove those dead skin cells, dust, oils and the mites that arrive to dine on those things.

Robotic manipulation in unstructured environments requires the generation of robust and long-horizon trajectory-level policy with conditions of perceptual observations and benefits from the advantages of SE(3)-equivariant diffusion models that are data-efficient. However, these models suffer from the inference time costs. Inspired by the inference efficiency of rectified flows, we introduce the rectification to the SE(3)-diffusion models and propose the ReSeFlow, i.e., Rectifying SE(3)-Equivariant Policy Learning Flows, providing fast, geodesic-consistent, least-computational policy generation. Crucially, both components employ SE(3)-equivariant networks to preserve rotational and translational symmetry, enabling robust generalization under rigid-body motions. With the verification on the simulated benchmarks, we find that the proposed ReSeFlow with only one inference step can achieve better performance with lower geodesic distance than the baseline methods, achieving up to a 48.5% error reduction on the painting task and a 21.9% reduction on the rotating triangle task compared to the baseline's 100-step inference. This method takes advantages of both SE(3) equivariance and rectified flow and puts it forward for the real-world application of generative policy learning models with the data and inference efficiency.

The increasing demand for democratizing machine learning algorithms for general software developers calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters, which can cause a large variation in the training cost. But this effect is largely ignored in existing HPO methods, which are incapable to properly control cost during the optimization process. To address this problem, we develop a cost effective HPO solution. The core of our solution is a new randomized direct-search method. We prove a convergence rate of $O(\frac{\sqrt{d}}{\sqrt{K}})$ and provide an analysis on how it can be used to control evaluation cost under reasonable assumptions. Extensive evaluation using a latest AutoML benchmark shows a strong any time performance of the proposed HPO method when tuning cost-related hyperparameters.