arXiv:2602.11305v1 Announce Type: new Abstract: Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a real-world query. Existing misalignment benchmarks-such as INSECURE CODE (safety-centric), VALUEACTIONLENS (value-centric), and CULTURALHERITAGE (culture centric)-rely on evaluating misalignment along individual dimensions, preventing simultaneous evaluation. To address this gap, we introduce Mis-Align Bench, a unified benchmark for analyzing misalignment across safety, […]

Ver mais

Imitation Learning (IL) enables robots to learn complex skills from demonstrations without explicit task modeling, but it typically requires large amounts of demonstrations, creating significant collection costs. Prior work has investigated using flow as an intermediate representation to enable the use of human videos as a substitute, thereby reducing the amount of required robot demonstrations. However, most prior work has focused on the flow, either on the object or on specific points of the robot/hand, which cannot describe […]

Ver mais

Accurate on-orbit reliability prediction for satellite electronics is often hindered by limited data availability, varying operational conditions, and considerable unit-to-unit variability. To overcome these obstacles, this paper proposes a novel integrated online reliability prediction framework. The main contributions are twofold. First, a Wiener process-based degradation model is developed, incorporating a generalized Arrhenius link function, individual random effects, and spatial correlations among adjacent units. A customized maximum likelihood estimation method is further devised to facilitate efficient and accurate parameter […]

Ver mais

arXiv:2601.05404v1 Announce Type: new Abstract: Optimal damping aims at determining a vector of damping coefficients $nu$ that maximizes the decay rate of a mechanical system’s response. This problem can be formulated as the minimization of the trace of the solution of a Lyapunov equation whose coefficient matrix depends on $nu$. For physical relevance, the damping coefficients must be nonnegative and the resulting system must be asymptotically stable. We identify conditions under which the system is never stable or […]

Ver mais

The crux of information systems is efficient storage and access to useful data by users. This paper is an overview of work that has advanced the use of such systems in recent years, primarily in machine learning, and specifically deep learning methods. Situating progress in terms of classical pattern recognition techniques for text, we review computational methods to process spoken and written data. Digital assistants such as Siri, Cortana, and Google Now exploit large language models and encoder-only […]

Ver mais

arXiv:2601.14267v1 Announce Type: new Abstract: Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded in complex scientific PDFs that make manual abstraction time-consuming and difficult to scale. Existing document AI systems remain limited by OCR errors, long-document fragmentation, constrained throughput, and insufficient auditability for high-stakes synthesis. We present a schema-constrained AI extraction system that transforms full-text biomedical PDFs into structured, analysis-ready records by explicitly restricting […]

Ver mais

If i were to zap myself everytime i got under 190ms reaction time and kept lowering the threshold and made a program do the zaping would i increase my reaction time. if so i would also like to do that with data processing so showing a certain amount of numbers on a screen for a quarter second and trying to memorize all of the numbers increasing the amount of number gradually and zapping myself for every wrong number […]

Ver mais