Objective functions with sharp ridge shapes are known to be difficult to optimize because they frequently lead to premature convergence near the ridges. To address this, local supremum transformations (LST) have been proposed as a method to mitigate sharpness by replacing the objective function value with the supremum over a local neighborhood. However, LST faces several challenges, including evaluation costs that increase linearly with the number of dimensions and failure when optimizing high-dimensional sharp functions. Therefore, as an efficient method for high-dimensional sharp functions, this paper proposes a hierarchical optimization method that utilizes two optimizers: an inner optimizer prone to premature convergence near the ridges, and a meta-optimizer that utilizes the result of the inner optimizer. The proposed method leverages the best solution found by the inner optimizer to update the meta-optimizer, which transforms problems with sharp shapes into a smooth objective function. Furthermore, by applying LST specifically in the evaluation of the best solution from the inner optimizer, the impact of sharp function shapes is mitigated. The experimental evaluation using (1+1)-CMA-ES as both inner and meta-optimizers demonstrates that the proposed method is effective for high-dimensional benchmark functions with sharp ridges compared to LST.

Human-Robot collaboration in surgery represents a significant area of research, driven by the increasing capability of autonomous robotic systems to assist surgeons in complex procedures. This systematic review examines the advancements and persistent challenges in the development of autonomous surgical robotic assistants (ASARs), focusing specifically on scenarios where robots provide meaningful and active support to human surgeons. Adhering to the PRISMA guidelines, a comprehensive literature search was conducted across the IEEE Xplore, Scopus, and Web of Science databases, resulting in the selection of 32 studies for detailed analysis. Two primary collaborative setups were identified: teleoperation-based assistance and direct hands-on interaction. The findings reveal a growing research emphasis on ASARs, with predominant applications currently in endoscope guidance, alongside emerging progress in autonomous tool manipulation. Several key challenges hinder wider adoption, including the alignment of robotic actions with human surgeon preferences, the necessity for procedural awareness within autonomous systems, the establishment of seamless human-robot information exchange, and the complexities of skill acquisition in shared workspaces. This review synthesizes current trends, identifies critical limitations, and outlines future research directions essential to improve the reliability, safety, and effectiveness of human-robot collaboration in surgical environments.

Large-scale vision-language models such as CLIP have shown impressive performance on zero-shot image classification and image-totext retrieval.However, such performance does not realize in tasks that require a finergrained correspondence between vision and language, such as Visual Question Answering (VQA).As a potential cause of the difficulty of applying these models to VQA and similar tasks, we report an interesting phenomenon of vision-language models, which we call the Concept Association Bias (CAB).We find that models with CAB tend to treat input as a bag of concepts and attempt to fill in the other missing concept crossmodally, leading to an unexpected zero-shot prediction.We demonstrate CAB by showing that CLIP's zeroshot classification performance greatly suffers when there is a strong concept association between an object (e.g.eggplant) and an attribute (e.g.color purple).We also show that the strength of CAB predicts the performance on VQA.We observe that CAB is prevalent in vision-language models trained with contrastive losses, even when autoregressive losses are jointly employed.However, a model that solely relies on autoregressive loss seems to exhibit minimal or no signs of CAB. * Equal contribution.CLIP: "In this picture, the color of the lemon is purple."

As clean ImageNet accuracy nears its ceiling, the re-search community is increasingly more concerned about ro-bust accuracy under distributional shifts. While a variety of methods have been proposed to robustify neural networks, these techniques often target models trained on ImageNet classification. At the same time, it is a common practice to use ImageNet pretrained backbones for downstream tasks such as object detection, semantic segmentation, and image classification from different domains. This raises a question: Can these robust image classifiers transfer robustness to downstream tasks? For object detection and semantic segmentation, we find that a vanilla Swin Transformer, a variant of Vision Transformer tailored for dense prediction tasks, transfers robustness better than Convolutional Neu-ral Networks that are trained to be robust to the corrupted version of ImageNet. For CIFAR10 classification, we find that models that are robustified for ImageNet do not re-tain robustness when fully fine-tuned. These findings sug-gest that current robustification techniques tend to empha-size ImageNet evaluations. Moreover, network architecture is a strong source of robustness when we consider transfer learning.

Feature selection problems have been extensively studied in the setting of linear estimation (e.g. LASSO), but less emphasis has been placed on feature selection for non-linear functions. In this study, we propose a method for feature selection in neural network estimation problems. The new procedure is based on probabilistic relaxation of the $\ell_0$ norm of features, or the count of the number of selected features. Our $\ell_0$-based regularization relies on a continuous relaxation of the Bernoulli distribution; such relaxation allows our model to learn the parameters of the approximate Bernoulli distributions via gradient descent. The proposed framework simultaneously learns either a nonlinear regression or classification function while selecting a small subset of features. We provide an information-theoretic justification for incorporating Bernoulli distribution into feature selection. Furthermore, we evaluate our method using synthetic and real-life data to demonstrate that our approach outperforms other commonly used methods in both predictive performance and feature selection.

In Japan, which has become a very aged society, the increasing burden of nursing care is an issue. Services and systems related to automatic recording of healthcare management of elderly people have been proposed in order to reduce the burden of nursing care. Water intake is one of the items necessary for healthcare management of elderly people. However, it is not currently automated, which is a burden on caregivers. In the case of the conventional method, the swallowing sound is used for estimating the water intake. However, the estimation error for each subject is large. Accuracy of estimated water intake is improved by using deep learning. Specifically, three features, namely, mel frequency cepstral coefficient (MFCC), duration of water intake, and a RASTA filter auditory spectrum, are extracted from a subject's swallowing sound (which is thought to be highly correlated with water intake). A method of estimating water intake, which considers abstract features that are difficult for people to find, is proposed and verified. It is experimentally shown that RMSE of water intake estimated by the proposed method using deep learning is reduced compared with that estimated by conventional methods.