Kolmogorov Arnold Networks (KANs) are neural architectures inspired by the Kolmogorov Arnold representation theorem that leverage B Spline parameterizations for flexible, locally adaptive function approximation. Although KANs can capture complex nonlinearities beyond those modeled by standard MultiLayer Perceptrons (MLPs), they frequently exhibit miscalibrated confidence estimates manifesting as overconfidence in dense data regions and underconfidence in sparse areas. In this work, we systematically examine the impact of four critical hyperparameters including Layer Width, Grid Order, Shortcut Function, and Grid Range on the calibration of KANs. Furthermore, we introduce a novel TemperatureScaled Loss (TSL) that integrates a temperature parameter directly into the training objective, dynamically adjusting the predictive distribution during learning. Both theoretical analysis and extensive empirical evaluations on standard benchmarks demonstrate that TSL significantly reduces calibration errors, thereby improving the reliability of probabilistic predictions. Overall, our study provides actionable insights into the design of spline based neural networks and establishes TSL as a robust loss solution for enhancing calibration.

We consider the challenging problem of estimating causal effects from purely observational data in the bi-directional Mendelian randomization (MR), where some invalid instruments, as well as unmeasured confounding, usually exist. To address this problem, most existing methods attempt to find proper valid instrumental variables (IVs) for the target causal effect by expert knowledge or by assuming that the causal model is a one-directional MR model. As such, in this paper, we first theoretically investigate the identification of the bi-directional MR from observational data. In particular, we provide necessary and sufficient conditions under which valid IV sets are correctly identified such that the bi-directional MR model is identifiable, including the causal directions of a pair of phenotypes (i.e., the treatment and outcome). Moreover, based on the identification theory, we develop a cluster fusion-like method to discover valid IV sets and estimate the causal effects of interest. We theoretically demonstrate the correctness of the proposed algorithm. Experimental results show the effectiveness of our method for estimating causal effects in bi-directional MR.

Formal representations of traffic scenarios can be used to generate test cases for the safety verification of autonomous driving. However, most existing methods are limited in highway or highly simplified intersection scenarios due to the intricacy and diversity of traffic scenarios. In response, we propose Traffic Scenario Logic (TSL), which is a spatial-temporal logic designed for modeling and reasoning of urban pedestrian-free traffic scenarios. TSL provides a formal representation of the urban road network that can be derived from OpenDRIVE, i.e., the de facto industry standard of high-definition maps for autonomous driving, enabling the representation of a broad range of traffic scenarios. We implemented the reasoning of TSL using Telingo, i.e., a solver for temporal programs based on the Answer Set Programming, and tested it on different urban road layouts. Demonstrations show the effectiveness of TSL in test scenario generation and its potential value in areas like decision-making and control verification of autonomous driving.

This paper presents an optimization approach for generating custom manipulator configurations using a proposed unconventional modular library. An end-to-end solution is presented in which the resulting optimal models of the modular compositions can be integrated directly with the Robot Operating System platform. The approach utilizes an unconventional modular library, which is adaptable to a wide range of parameters for customization including non-parallel and non-perpendicular joint axes, and the unified modeling technique for getting the custom modular configurations. The single objective function optimization problem is formulated based upon the discrete parameters of reconfiguration depending upon the available modular library such as, number of joint modules, skew-twist angle, intersecting-twist angle, connection ports of the module, module size, modular sub-assembly unit and curved links. Two case studies, including an application to the agricultural vertical farms, are presented to validate the results.

However, in many real applications, the assumption cannot be satisfied due to the existence of unknowns. A reliable classification model ought to own the ability to say "I do not know" to out-of-distribution (OOD) data that the model has not seen before, which is the key to deploying models safely in the real world [34, 45]. For example, a wildlife monitoring system with the ability to detect OOD data will not confidently regard unknown animal categories as known categories, which is essential to help humans discover new species [35]. In medical image recognition [12, 41], models with the ability to detect OOD data can help doctors discover rare and novel diseases and prevent patients missing the best treatment period. In autonomous driving, OOD detection enables cars to evoke human control of driving in an emergency or unknown scenarios [17, 36], which contributes to safer and more reliable autonomous driving. OOD detection has received much attention because of its significance, and plenty of methods have emerged. The existing OOD detection methods can be divided into two main categories: classification-based OOD detection methods and density-based OOD detection methods. The classification-based methods contain post-hoc based methods [18, 27] and fine-tuning based methods [19, 30].

Recommendation systems play an important role in many e-commerce applications as well as search and ranking services [6, 15, 21, 26, 30, 31, 41, 48]. There are two main strategies to perform recommendations: content and collaborative filtering. In content filtering the user creates a profile based on its interest, while human experts create a profile for the product. An algorithm matches the two profiles and recommends the closest matches to the user. For example, this approach is taken by the Pandora Music Genome Project [29]. In collaborative filtering, the recommendations are based only on user past behavior from which the future behavior is derived. The advantage of this approach is that it requires no external information and is not domain specific. The challenge is that in the beginning very few user-item interactions are available. For instance, this cold start problem is addressed by Netflix by asking the user for a few favorite movies when creating their profile for the first time [27].

Recently, in causal discovery, invariance properties such as the moment criterion which two-stage least square estimator leverage have been exploited for causal structure learning: e.g., in cases, where the causal parameter is not identifiable, some structure of the non-zero components may be identified, and coverage guarantees are available. Subsequently, anchor regression has been proposed to trade-off invariance and predictability. The resulting estimator is shown to have optimal predictive performance under bounded shift interventions. In this paper, we show that the concepts of anchor regression and K-class estimators are closely related. Establishing this connection comes with two benefits: (1) It enables us to prove robustness properties for existing K-class estimators when considering distributional shifts. And, (2), we propose a novel estimator in instrumental variable settings by minimizing the mean squared prediction error subject to the constraint that the estimator lies in an asymptotically valid confidence region of the causal parameter. We call this estimator PULSE (p-uncorrelated least squares estimator) and show that it can be computed efficiently, even though the underlying optimization problem is non-convex. We further prove that it is consistent. We perform simulation experiments illustrating that there are several settings including weak instrument settings, where PULSE outperforms other estimators and suffers from less variability.

The Workshop on Term Subsumption Languages in Knowledge Representation was held 18-20 October 1989 at the Inn at Thorn Hill, located in the White Mountain region of New Hampshire. The workshop was organized by Peter F. Patel-Schneider of AT&T Bell Laboratories, Murray Hill, New Jersey; Marc Vilain of MITRE, Bedford, Massachusetts; Ramesh S. Patil of the Massachusetts Institute of Technology (MIT); and Bill Mark of the Lockheed AI Center, Menlo Park, California. Support was provided by the American Association for Artificial Intelligence and AT&T Bell Laboratories. This workshop was the latest in a series in this area. Previous workshops have had a slightly narrower focus, being explicitly concerned with KL-One, the first knowledge representation system based on a term subsumption language (TSL), or its successor, NIKL.