arXiv:2602.11174v1 Announce Type: new Abstract: Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical linguistic content. Across mBERT and XLM-R, the higher-fragmentation orthography shows a ~3.4x increase in fertility (6.73-6.85 vs. 2.10-2.35 tokens/word), leading to a 16.5x inference slowdown (0.23 vs. 3.8 sentences/second) on identical hardware. Using bits per character (BPC) to avoid the […]

Ver mais

Hi everyone — I’m Aleksandr Hebultіvskiy, COO at Sabai Protocol, where we help businesses tokenize real-world assets. I usually start working with projects at the point where the presentations end and the real numbers begin. When the goal is no longer to “explain how it works,” but to figure out whether it makes sense to get into this at all. I wrote this article from that perspective: what tokenization really costs, how long it takes to build an […]

Ver mais

arXiv:2603.12388v1 Announce Type: new Abstract: Practical webcam gaze tracking is constrained not only by error, but also by calibration burden, robustness to head motion and session drift, runtime footprint, and browser use. We therefore target a deployment-oriented operating point rather than the image large-backbone regime. We cast landmark-based point-of-regard estimation as session-wise adaptation: a shared geometric encoder produces embeddings that can be aligned to a new session from a small calibration set. We present Equivariant Meta-Calibrated Gaze (EMC-Gaze), […]

Ver mais

arXiv:2602.12311v1 Announce Type: new Abstract: We present a multi-agent framework for generating physics simulation code from natural language descriptions, featuring a novel perceptual self-reflection mechanism for validation. The system employs four specialized agents: a natural language interpreter that converts user requests into physics-based descriptions; a technical requirements generator that produces scaled simulation parameters; a physics code generator with automated self-correction; and a physics validator that implements perceptual self-reflection. The key innovation is perceptual validation, which analyzes rendered animation […]

Ver mais

We consider the problem of learning the optimal policy for Markov decision processes with safety constraints. We formulate the problem in a reach-avoid setup. Our goal is to design online reinforcement learning algorithms that ensure safety constraints with arbitrarily high probability during the learning phase. To this end, we first propose an algorithm based on the optimism in the face of uncertainty (OFU) principle. Based on the first algorithm, we propose our main algorithm, which utilizes entropy regularization. […]

Ver mais

arXiv:2601.09035v1 Announce Type: new Abstract: The parallel evolution of Large Language Models (LLMs) with advanced code-understanding capabilities and the increasing sophistication of malware presents a new frontier for cybersecurity research. This paper evaluates the efficacy of state-of-the-art LLMs in classifying executable code as either benign or malicious. We introduce an automated pipeline that first decompiles Windows executable into a C code using Ghidra disassembler and then leverages LLMs to perform the classification. Our evaluation reveals that while standard […]

Ver mais

arXiv:2602.21160v2 Announce Type: replace Abstract: In safety-critical classification, the cost of failure is often asymmetric, yet Bayesian deep learning summarises epistemic uncertainty with a single scalar, mutual information (MI), that cannot distinguish whether a model’s ignorance involves a benign or safety-critical class. We decompose MI into a per-class vector $C_k(x)=sigma_k^{2}/(2mu_k)$, with $mu_k{=}mathbb{E}[p_k]$ and $sigma_k^2{=}mathrm{Var}[p_k]$ across posterior samples. The decomposition follows from a second-order Taylor expansion of the entropy; the $1/mu_k$ weighting corrects boundary suppression and makes $C_k$ comparable […]

Ver mais

arXiv:2603.16969v1 Announce Type: new Abstract: This paper presents DeepStage, a deep reinforcement learning (DRL) framework for adaptive, stage-aware defense against Advanced Persistent Threats (APTs). The enterprise environment is modeled as a partially observable Markov decision process (POMDP), where host provenance and network telemetry are fused into unified provenance graphs. Building on our prior work, StageFinder, a graph neural encoder and an LSTM-based stage estimator infer probabilistic attacker stages aligned with the MITRE ATT&CK framework. These stage beliefs, combined […]

Ver mais

arXiv:2506.19461v3 Announce Type: replace-cross Abstract: Quantum machine learning models that leverage quantum circuits as quantum feature maps (QFMs) are recognized for their enhanced expressive power in learning tasks. Such models have demonstrated rigorous end-to-end quantum speedups for specific families of classification problems. However, deploying deep QFMs on real quantum hardware remains challenging due to circuit noise and hardware constraints. Additionally, variational quantum algorithms often suffer from computational bottlenecks, particularly in accurate gradient estimation, which significantly increases quantum resource […]

Ver mais