Constrained autoencoders (cAE) provide a successful path towards interpretable dimensionality reduction by enforcing geometric structure on latent spaces. However, standard cAEs cannot adapt to varying physical parameters or environmental conditions without conflating these contextual shifts with the primary input. To address this, we integrated a neuromodulatory mechanism into the cAE framework to allow for context-dependent manifold learning. This paper introduces the Neuromodulated Constrained Autoencoder (NcAE), which adaptively parameterizes geometric constraints via gain and bias tuning conditioned on static […]

Ver mais

Background: Automated visual field testing is fundamental in ophthalmology, but differences in stimulus scaling and luminance between devices hinder direct comparison of sensitivity values. Virtual reality (VR)–based perimetry has emerged as a portable alternative, yet its relationship with conventional perimetry requires clarification. Methods: This prospective cross-sectional study included 60 healthy participants stratified into younger (< 50 years) and older (≥ 50 years) groups. Differential light sensitivity was assessed in the right eye using Humphrey Automated Perimetry (HFA 30-2) […]

Ver mais

Bitcoin miners are producing every coin at a loss. The average cost to mine one BTC sits at $88,000 while the market price holds near $70,853, meaning every block costs $19,000 more than it earns. Mining difficulty just dropped 7.8% and hashrate has fallen to 920 EH/s, well below the 1.1 ZH/s peak from 2025. When the people who create Bitcoin cannot afford to produce it, the market is sitting at a price floor that preceded every major […]

Ver mais

Complex prediction problems often lead to ensembles because combining multiple models improves accuracy by reducing variance and capturing diverse patterns. However, these ensembles are impractical in production due to latency constraints and operational complexity. Instead of discarding them, Knowledge Distillation offers a smarter approach: keep the ensemble as a teacher and train a smaller student model using its soft probability outputs. This allows the student to inherit much of the ensemble’s performance while being lightweight and fast enough […]

Ver mais

arXiv:2604.08612v1 Announce Type: new Abstract: This study aims to enhance the bidirectional authentication capability of ML-KEM (Module-Lattice-Based Key-Encapsulation Mechanism) by proposing the post-quantum cryptography-based (PQC-based) bidirectional authentication key exchange protocol. Furthermore, it introduces dual-usage certificates combining PQC-based DSA (Digital Signature Algorithm) and PQC-based KEM, which include composite schemes, catalyst schemes, and chameleon schemes. These dual-usage certificates utilize the PQC-based DSA public key and PQC-based KEM public key within the certificate to meet the requirements for bidirectional authentication and […]

Ver mais

arXiv:2510.15669v2 Announce Type: replace Abstract: Variational autoencoders (VAEs) are among leading approaches to address the problem of learning disentangled representations. Typically a single VAE is used and disentangled representations are sought within its single continuous latent space. In this paper, we propose and provide a proof of concept for a novel Multi-Stream Variational Autoencoder (MS-VAE) that achieves disentanglement of sources by combining discrete and continuous latents. The discrete latents are used in an explicit source combination model, that […]

Ver mais

arXiv:2604.16893v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has demonstrated remarkable effectiveness in improving the reasoning capabilities of large language models. As models evolve into natively multimodal architectures, extending RLVR to video understanding becomes increasingly important yet remains largely unexplored, due to the diversity of video task types, the computational overhead of repeatedly decoding and preprocessing high-dimensional visual inputs, and the difficulty of reproducible evaluation across numerous sensitive hyperparameters. Existing open-source RL training frameworks provide […]

Ver mais

arXiv:2602.16843v1 Announce Type: new Abstract: Evaluating factual consistency is essential for reliable text summarization, particularly in high-stakes domains such as healthcare and news. However, most existing evaluation metrics overlook Bangla, a widely spoken yet under-resourced language, and often depend on reference summaries. We introduce BanglaSummEval, a reference-free, question-answering-based framework for evaluating factual consistency in Bangla summarization. The proposed method assesses both factual accuracy and content coverage through automatically generated questions and answers derived from the source document and […]

Ver mais