When safety is formulated as a limit of cumulative cost, safe reinforcement learning (RL) aims to learn policies that maximize return subject to the cost constraint in data collection and deployment. Off-policy safe RL methods, although offering high sample efficiency, suffer from constraint violations due to cost-agnostic exploration and estimation bias in cumulative cost. To address this issue, we propose Constrained Optimistic eXploration Q-learning (COX-Q), an off-policy safe RL algorithm that integrates cost-bounded online exploration and conservative offline […]

Ver mais

Cardiac blood flow patterns contain rich information about disease severity and clinical interventions, yet current imaging and computational methods fail to capture underlying relational structures of coherent flow features. We propose a physics-informed, latent relational framework to model cardiac vortices as interacting nodes in a graph. Our model combines a neural relational inference architecture with physics-inspired interaction energy and birth-death dynamics, yielding a latent graph sensitive to disease severity and intervention level. We first apply this to computational […]

Ver mais

arXiv:2604.07466v1 Announce Type: new Abstract: Cross-tokenizer distillation (CTD), the transfer of knowledge from a teacher to a student language model when the two use different tokenizers, remains a largely unsolved problem. Existing approaches rely on heuristic strategies to align mismatched vocabularies, introducing considerable complexity. In this paper, we propose a simple but effective baseline called Byte-Level Distillation (BLD) which enables CTD by operating at a common interface across tokenizers: the byte level. In more detail, we convert the […]

Ver mais

arXiv:2604.14258v1 Announce Type: new Abstract: Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we provide a training-dynamics analysis showing that SFT can be interpreted as a special case of policy gradient optimization with an extremely sparse implicit reward and unstable inverse-probability weighting, which together lead to single-path dependency, entropy collapse, and gradient explosion. Motivated by this diagnosis, we […]

Ver mais

arXiv:2604.06266v1 Announce Type: new Abstract: Software-Defined Networking (SDN) improves network flexibility but also increases the need for reliable and interpretable intrusion detection. Large Language Models (LLMs) have recently been explored for cybersecurity tasks due to their strong representation learning capabilities; however, their lack of transparency limits their practical adoption in security-critical environments. Understanding how LLMs make decisions is therefore essential. This paper presents an attribution-driven analysis of encoder-based LLMs for network intrusion detection using flow-level traffic features. Attribution […]

Ver mais

arXiv:2505.13660v2 Announce Type: replace-cross Abstract: This paper introduces a new constraint-free concave dual formulation for the Wasserstein barycenter. Tailoring the vanilla dual gradient ascent algorithm to the Sobolev geometry, we derive a scalable Sobolev gradient ascent (SGA) algorithm to compute the barycenter for input distributions discretized over a regular grid. Despite the algorithmic simplicity, we provide a global convergence analysis that achieves the same rate as the classical subgradient descent methods for minimizing nonsmooth convex functions in the […]

Ver mais

arXiv:2603.06650v1 Announce Type: new Abstract: Whole-slide image classification for invasive lung adenocarcinoma subtyping remains vulnerable to real-world imaging perturbations that undermine model reliability at the decision boundary. We propose a margin consistency framework evaluated on 203,226 patches from 143 whole-slide images spanning five adenocarcinoma subtypes in the BMIRDS-LUAD dataset. By combining attention-weighted patch aggregation with margin-aware training, our approach achieves robust feature-logit space alignment measured by Kendall correlations of 0.88 during training and 0.64 during validation. Contrastive regularization, […]

Ver mais

Welcome to HackerNoon’s Meet the Writer Interview series, where we learn a bit more about the contributors that have written some of our favorite stories. So let’s start! Tell us a bit about yourself. For example, name, profession, and personal interests. My name is Marius Eugen Vomir. I’m from Romania, and I created Smart Home Cinema, a local-first voice-controlled movie system for Windows. I’m interested in technology that removes everyday friction in a simple and reliable way. Most […]

Ver mais

arXiv:2603.26554v1 Announce Type: cross Abstract: Spectral optimizers such as Muon have recently shown strong empirical performance in large-scale language model training, but the source and extent of their advantage remain poorly understood. We study this question through the linear associative memory problem, a tractable model for factual recall in transformer-based models. In particular, we go beyond orthogonal embeddings and consider Gaussian inputs and outputs, which allows the number of stored associations to greatly exceed the embedding dimension. Our […]

Ver mais