technocracy

arXiv:2601.16999v1 Announce Type: cross Abstract: Named Entity Recognition (NER) serves as a foundational component in many natural language processing (NLP) pipelines. However, current NER models typically output a single predicted label sequence without any accompanying measure of uncertainty, leaving downstream applications vulnerable to cascading errors. In this paper, we introduce a general framework for adapting sequence-labeling-based NER models to produce uncertainty-aware prediction sets. These prediction sets are collections of full-sentence labelings that are guaranteed to contain the correct […]

Ver mais

arXiv:2603.02344v1 Announce Type: new Abstract: We present a passivity-agnostic framework for distributed adaptive synchronization under position-only communication, bounded disturbances, and unknown leader dynamics. By passivity-agnostic we mean the design does not require the closed loop system to be strictly positive real (SPR) a priori: it certifies SPR when present and recovers it by frequency shaping when absent. Followers are heterogeneous second-order systems with unknown (possibly unstable) dynamics. In the SPR regime, a structured reparameterization yields gradient-based adaptive error […]

Ver mais

The debate between reading physically or digitally is never-ending; both have their pros and cons. However, for those who like reading digitally, a great service to use is Marvel Unlimited. It’s Marvel’s own subscription service that allows you to read a ton of old and new comics. It does seem, though, that a lot of people either have never heard of Marvel Unlimited or have completely forgotten about it. There are others who know about it but don’t […]

Ver mais

arXiv:2603.02368v1 Announce Type: new Abstract: We introduce RO-N3WS, a benchmark Romanian speech dataset designed to improve generalization in automatic speech recognition (ASR), particularly in low-resource and out-of-distribution (OOD) conditions. RO-N3WS comprises over 126 hours of transcribed audio collected from broadcast news, literary audiobooks, film dialogue, children’s stories, and conversational podcast speech. This diversity enables robust training and fine-tuning across stylistically distinct domains. We evaluate several state-of-the-art ASR systems (Whisper, Wav2Vec 2.0) in both zero-shot and fine-tuned settings, and […]

Ver mais

arXiv:2602.03911v1 Announce Type: cross Abstract: The target network update frequency (TUF) is a central stabilization mechanism in (deep) Q-learning. However, their selection remains poorly understood and is often treated merely as another tunable hyperparameter rather than as a principled design decision. This work provides a theoretical analysis of target fixing in tabular Q-learning through the lens of approximate dynamic programming. We formulate periodic target updates as a nested optimization scheme in which each outer iteration applies an inexact […]

Ver mais

arXiv:2505.13614v3 Announce Type: replace-cross Abstract: The high-dimensional parameter space of deep neural networks — the neuromanifold — is endowed with a unique metric tensor defined by the Fisher information. Reliable and scalable computation of this metric tensor is valuable for theorists and practitioners. Focusing on neural classifiers, we return to a low-dimensional space of probability distributions, which we call the core space, and examine the spectrum and envelopes of its Fisher information matrix. We extend our discoveries there […]

Ver mais

arXiv:2602.10253v1 Announce Type: new Abstract: We investigate the parameterized complexity of Bayesian Network Structure Learning (BNSL), a classical problem that has received significant attention in empirical but also purely theoretical studies. We follow up on previous works that have analyzed the complexity of BNSL w.r.t. the so-called superstructure of the input. While known results imply that BNSL is unlikely to be fixed-parameter tractable even when parameterized by the size of a vertex cover in the superstructure, here we […]

Ver mais

arXiv:2603.12361v1 Announce Type: new Abstract: Motion planning through narrow passages remains a core challenge: sampling-based planners rarely place samples inside these narrow but critical regions, and even when samples land inside a passage, the straight-line connections between them run close to obstacle boundaries and are frequently rejected by collision checking. Decomposition-based planners resolve both issues by partitioning free space into convex cells — every passage is captured exactly as a cell boundary, and any path within a cell […]

Ver mais