[On agents using CLI tools in place of REST APIs] To save on context window, yes, but moreso to improve accuracy and success rate when multiple tool calls are involved, particularly when calls must be correctly chained e.g. for pagination, rate-limit backoff, and recognizing authentication failures. Other major factor: which models can wield the skill? Using the CLI lowers the bar so cheap, fast models (gpt-5-nano, haiku-4.5) can reliably succeed. Using the raw APl is something only the […]

Ver mais

arXiv:2601.15363v1 Announce Type: new Abstract: Functional bilevel optimization (FBO) provides a powerful framework for hierarchical learning in function spaces, yet current methods are limited to static offline settings and perform suboptimally in online, non-stationary scenarios. We propose SmoothFBO, the first algorithm for non-stationary FBO with both theoretical guarantees and practical scalability. SmoothFBO introduces a time-smoothed stochastic hypergradient estimator that reduces variance through a window parameter, enabling stable outer-loop updates with sublinear regret. Importantly, the classical parametric bilevel case […]

Ver mais

Latent space models are widely used for analyzing high-dimensional discrete data matrices, such as patient-feature matrices in electronic health records (EHRs), by capturing complex dependence structures through low-dimensional embeddings. However, estimation becomes challenging in the imbalanced regime, where one matrix dimension is much larger than the other. In EHR applications, cohort sizes are often limited by disease prevalence or data availability, whereas the feature space remains extremely large due to the breadth of medical coding system. Motivated by […]

Ver mais

When capability scales faster than interpretation, trust erodes before anyone notices The Failure Most Teams Don’t Instrument Most system failures don’t start with broken tools. n They startwhen capability scales faster than interpretation. AI ships output faster than teams can review or debug. n Startups ship demos faster than users can integrate or rely on. n Markets ship leverage faster than anyone can trace where risk actually sits. Throughput goes up. Latency is ignored. Confidence stays green. But […]

Ver mais

The theory of physical degrees of freedom (DoF) developed by Franceschetti–Migliore– Minero (FMM) establishes a fundamental phase transition in the singular-value spectrum of electromagnetic radiation operators under maximal rotational symmetry. In this work, we revisit this result from a symmetry-explicit operator-theoretic perspective and extend it to scenarios with reduced and controllable symmetries, with particular emphasis on reconfigurable intelligent surfaces (RIS). We model the radiation process as a compact operator acting between admissible source and observation spaces and characterize […]

Ver mais

arXiv:2601.19969v1 Announce Type: new Abstract: Human-in-the-loop guidance has emerged as an effective approach for enabling faster convergence in online reinforcement learning (RL) of complex real-world manipulation tasks. However, existing human-in-the-loop RL (HiL-RL) frameworks often suffer from low sample efficiency, requiring substantial human interventions to achieve convergence and thereby leading to high labor costs. To address this, we propose a sample-efficient real-world human-in-the-loop RL framework named method, which requires fewer human intervention by actively selecting informative samples. Specifically, stable […]

Ver mais

In the first part, I talked about what Data Quality, Anomaly Detection and Outliers Detection are and what’s the difference between outliers detection and novelty detection. In this part, I will talk about a very known and easy method to detect outliers called Interquartile Range. Introduction The Interquartile Range method, also known as IQR, was developed by John Widler Turky, an American mathematician best known for development of the FFT algorithm and box plot.

Ver mais

arXiv:2601.18971v1 Announce Type: new Abstract: For active intervention tasks in underwater environments, the use of autonomous vehicles is just now emerging as an active area of research. During operation, for various reasons, the robot might find itself on a collision course with an obstacle in its environment. In this paper, a switching Nonlinear Model Predictive Control (NMPC) strategy is proposed to safely handle collisions for an Underwater Vehicle-Manipulator System (UVMS). When avoiding the collision is impossible, the control […]

Ver mais

A founder recently asked me how to stop caring what other people think. I didn’t have an answer, and after reflecting on it more, I think it’s the wrong question. Almost everyone cares what someone thinks (though caring what everyone thinks is definitely a mistake), and it’s probably important. Caring too much makes you a sheep. But you need to be at least a little in tune with others to do something useful for them. It seems like […]

Ver mais