arXiv:2601.04198v1 Announce Type: new Abstract: Prediction error and maximum likelihood methods are powerful tools for identifying linear dynamical systems and, in particular, enable the joint estimation of model parameters and the Kalman filter used for state estimation. A key limitation, however, is that these methods require solving a generally non-convex optimization problem to global optimality. This paper analyzes the statistical behavior of local minimizers in the special case where only the Kalman gain is estimated. We prove that […]

Ver mais

arXiv:2601.12285v1 Announce Type: new Abstract: We introduce a novel representation for efficient classical rendering of photorealistic 3D face avatars. Leveraging recent advances in radiance fields anchored to parametric face models, our approach achieves controllable volumetric rendering of complex facial features, including hair, skin, and eyes. At enrollment time, we learn a set of radiance manifolds in 3D space to extract an explicit layered mesh, along with appearance and warp textures. During deployment, this allows us to control and […]

Ver mais

This work investigates a mechanism for topology-altering geometric behavior induced by angular group actions within the framework of the Alpha Group, demonstrating that a systematic angular sweep can drive spontaneous transitions between Riemannian-like and sub-Riemannian regimes. Motivated by the group-theoretic foundations of geometry established by the Göttingen school and by the central role of invariants in topology, we introduce a setting in which geometric organization emerges from the interplay between an invariant, idempotent operator µ and an angular […]

Ver mais

This paper presents a systematic comparison of neural architectures for English-to-Spanish machine translation. We implement and evaluate five model configurations ranging from vanilla LSTM encoder-decoders to Transformer models with pretrained embeddings. Using the OPUS-100 corpus (1M training pairs) and FLORES+ benchmark (2,009 test pairs), we evaluate translation quality using BLEU, chrF, and COMET metrics. Our best Transformer model achieves a BLEU score of 20.26, closing approximately 65% of the performance gap between our strongest LSTM baseline (BLEU 10.66) […]

Ver mais

Most RAG systems fail in production because “semantic similarity” isn’t the same as relevance, and retrieval breaks under real queries. This article outlines five escalating levels—naive RAG, smarter chunking with overlap and metadata, hybrid semantic + BM25 retrieval, cross-encoder reranking, and production guardrails that refuse or clarify when confidence is low—plus a testing approach to measure retrieval precision and answer accuracy. The core lesson: build, break, diagnose the failure mode, and level up until the system reliably grounds […]

Ver mais

Active learning (AL) strategies aim to train high-performance models with minimal labeling efforts, only selecting the most informative instances for annotation. Current approaches to evaluating data informativeness predominantly focus on the data’s distribution or intrinsic information content and do not directly correlate with downstream task performance, such as mean average precision (mAP) in object detection. Thus, we propose Performance-guided (i.e. mAP-guided) Reinforced Active Learning for Object Detection (MGRAL), a novel approach that leverages the concept of expected model […]

Ver mais

This paper presents an edge-reinforced learning platform that combines reinforcement learning, homomorphic encryption, and swarm intelligence to support ultra-low latency IoT sensing and cross-device communication. In conventional IoT architectures, cloud-centric processing and centralized coordination introduce significant delays and expose sensitive data to intermediate entities, making them unsuitable for time-critical and privacy-sensitive applications. The proposed platform relocates intelligence to the network edge, where edge nodes learn adaptive policies for sensing, routing, and computation offloading based on local conditions and […]

Ver mais