Addressing these challenges requires scale. To that end we introduce ProteinGym, a large-scale and holistic set of benchmarks specifically designed for protein fitness prediction and design.

Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models have achieved remarkable success, the underlying mechanisms driving their performance are not yet fully accounted for, with many unanswered questions surrounding what they learn, how they represent visual-semantic relationships, and why they sometimes fail to generalize.

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones. However, literature has conflicting findings on the effectiveness of probabilistic classifiers in comparison to deterministic ones. In this paper, we clarify the role of randomization in building adversarially robust classifiers.Given a base hypothesis set of deterministic classifiers, we show the conditions under which a randomized ensemble outperforms the hypothesis set in adversarial risk, extending previous results.Additionally, we show that for any probabilistic binary classifier (including randomized ensembles), there exists a deterministic classifier that outperforms it. Finally, we give an explicit description of the deterministic hypothesis set that contains such a deterministic classifier for many types of commonly used probabilistic classifiers, randomized ensembles and parametric/input noise injection.

Abstract--Orographic soaring can significantly extend the endurance of micro aerial vehicles (MA Vs), but circling behavior, arising from control conflicts between longitudinal and vertical axes, increases energy consumption and the risk of divergence. We propose a control switching method, named SAOS: Switched Control for Autonomous Orographic Soaring, which mitigates circling behavior by selectively controlling either the horizontal or vertical axis, effectively transforming the system from under-actuated to fully actuated during soaring. Additionally, the angle of attack is incorporated into the INDI controller to improve force estimation. Simulations with randomized initial positions and wind tunnel experiments on two MA Vs demonstrate that the SAOS improves position convergence, reduces throttle usage, and mitigates roll oscillations caused by pitch-roll coupling. These improvements enhance energy efficiency and flight stability in constrained soaring environments. The flight endurance of micro air vehicles (MA Vs) significantly constrains operational capabilities, limiting the scope of missions they can perform [1], [2]. This limitation is not solely due to inherently short flight durations, but also because take-off and landing procedures typically demand substantial time, energy, effort, and space. One potential solution to this problem lies in the advancement of battery technology, which could lead to improved efficiency. However, progress in this area has been relatively slow [3], [4]. Consequently, researchers have been exploring alternative solutions, such as using energy sources with higher energy densities or enabling mid-air refueling or recharging [5], [6]. Nevertheless, these approaches require considerable investment in hardware and system infrastructure, and often necessitate larger, heavier platforms--undermining the fundamental advantage of MA Vs being small. An alternative approach is to exploit soaring, a flight technique widely employed by birds [7]-[9] and human-piloted glider aircraft [10], [11]. Soaring takes advantage of wind energy, specifically upward vertical winds, to gain altitude or remain airborne with minimal energy expenditure. A key strength of soaring is its compatibility with existing systems: it can be integrated into any fixed-wing aircraft without requiring hardware modifications, making it a valuable complement to other endurance-enhancing strategies. V arious types of soaring techniques exist [12].

This work proposes PH-based metrics for benchmarking impedance control. A causality-consistent PH model is introduced for mass-spring-damper impedance in Cartesian space. Based on this model, a differentiable, force-torque sensing-independent, n-DoF passivity condition is derived, valid for time-varying references. An impedance fidelity metric is also defined from step-response power in free motion, capturing dynamic decoupling. The proposed metrics are validated in Gazebo simulations with a six-DoF manipulator and a quadruped leg. Results demonstrate the suitability of the PH framework for standardized impedance control benchmarking.

Language models depend on massive text corpora that are often filtered for quality, a process that can unintentionally exclude non-standard linguistic varieties, reduce model robustness and reinforce representational biases. In this paper, we argue that language models should aim to capture the full spectrum of language variation (dialectal, historical, informal, etc.) rather than relying solely on standardized text. Focusing on Basque, a morphologically rich and low-resource language, we construct new corpora combining standard, social media, and historical sources, and pre-train the BERnaT family of encoder-only models in three configurations: standard, diverse, and combined. We further propose an evaluation framework that separates Natural Language Understanding (NLU) tasks into standard and diverse subsets to assess linguistic generalization. Results show that models trained on both standard and diverse data consistently outperform those trained on standard corpora, improving performance across all task types without compromising standard benchmark accuracy. These findings highlight the importance of linguistic diversity in building inclusive, generalizable language models.

Abstract--Robotic grippers are increasingly deployed across industrial, collaborative, and aerial platforms, where each embodiment imposes distinct mechanical, energetic, and operational constraints. Established YCB and NIST benchmarks quantify grasp success, force, or timing on a single platform, but do not evaluate cross-embodiment transferability or energy-aware performance, capabilities essential for modern mobile and aerial manipulation. This letter introduces the Cross-Embodiment Gripper Benchmark (CEGB), a compact and reproducible benchmarking suite extending YCB and selected NIST metrics with three additional components: a transfer-time benchmark measuring the practical effort required to exchange embodiments, an energy-consumption benchmark evaluating grasping and holding efficiency, and an intent-specific ideal payload assessment reflecting design-dependent operational capability. T ogether, these metrics characterize both grasp performance and the suitability of reusing a single gripper across heterogeneous robotic systems. A lightweight self-locking gripper prototype is implemented as a reference case. Experiments demonstrate rapid embodiment transfer (median 17.6 s across user groups), low holding energy for gripper prototype ( 1.5 J per 10 s), and consistent grasp performance with cycle times of 3.2-3.9 CEGB thus provides a reproducible foundation for cross-platform, energy-aware evaluation of grippers in aerial and manipulators domains. Robotic grasping has been extensively investigated across industrial, collaborative, and aerial domains.

Deep neural networks are known to be vulnerable to small adversarial perturbations in test data. To defend against adversarial attacks, probabilistic classifiers have been proposed as an alternative to deterministic ones. However, literature has conflicting findings on the effectiveness of probabilistic classifiers in comparison to deterministic ones.

Despite considerable technological innovation, comprehensive reviews synthesizing the application and evolution of artificial intelligence (AI) in the field of music analysis remain scarce. Although early studies on computer-assisted composition and rule-based analysis established a foundation for the automated exploration of musical form and content Hiller (1959), there is still a limited body of literature addressing the complete progression from traditional algorithms to recent AI-driven models and hybrid systems. Pioneering work such as Miranda's Miranda (2021), underscores the influence of AI, supercomputing, and evolutionary computation in shaping the first computational tools for creation. Recent reviews (Wang et al. (2024); Lerch et al. (2025)) focus on intelligent music generation systems. However, a systematic integration of these historical advances with state-of-the-art AI methodologies and musical analysis is largely absent. In the last decade, deep learning frameworks--including convolutional neural networks, recurrent neural networks, and transformer architectures--have led to breakthroughs in music information retrieval.