1 citations · 1 across the 15 of their papers we have counts for
19 papers
The Cost of a Physics Prior Is Bounded by the Ablation Gap
Boris Kriuk
Shape-constrained and physics-informed learning reports an accuracy cost of enforcing a prior and treats it as a property of the prior. We show it is mostly a property of the free…
Korzhinskii-Net: Physics-Informed Neural Network for Sub-Surface Mineral Prospectivity Modelling
Boris Kriuk
Mineral prospectivity modelling (MPM) underpins exploration economics, yet most operational pipelines reduce to data-driven classifiers trained on shallow surface proxies. Such mod…
Price-Discovery Admissibility in Tokenized Fixed Income: Identification, Affine Characterization, and the Structure of the Token-to-Fiat Mapping
Artem Alkhamov, Boris Kriuk
A tokenized U.S. Treasury product lives on two ledgers: an off-chain portfolio of government securities and an on-chain wrapper that claims to represent it. The foundational questi…
Artificial Adaptive Intelligence: The Missing Stage Between Narrow and General Intelligence
Boris Kriuk
Between the narrow systems we deploy and the general intelligence we speculate about lies an entire regime of machine behavior that has never received its own name. This monograph…
AlphaJet: Automated Conceptual Aircraft Synthesis via Disentangled Generative Priors and Topology-Preserving Evolutionary Search
Boris Kriuk
Conceptual aircraft design is traditionally an expert-mediated iterative process in which a human designer proposes a configuration, runs low-order physics, inspects the result, an…
ORCA -- Online Regime Correlation Analyzer
Boris Kriuk, Fedor Kriuk
Standard risk models reduce the rich dependence structure of financial markets to scalar volatility estimates, discarding the topological information encoded in cross-asset correla…
PSTNet: Physically-Structured Turbulence Network
Boris Kriuk, Fedor Kriuk
Reliable real-time estimation of atmospheric turbulence intensity remains an open challenge for aircraft operating across diverse altitude bands, particularly over oceanic, polar,…
POSEIDON: Physics-Optimized Seismic Energy Inference and Detection Operating Network
Boris Kriuk, Fedor Kriuk
Earthquake prediction and seismic hazard assessment remain fundamental challenges in geophysics, with existing machine learning approaches often operating as black boxes that ignor…
Q-KVComm: Efficient Multi-Agent Communication Via Adaptive KV Cache Compression
Boris Kriuk, Logic Ng
Multi-agent Large Language Model (LLM) systems face a critical bottleneck: redundant transmission of contextual information between agents consumes excessive bandwidth and computat…
MorphBoost: Self-Organizing Universal Gradient Boosting with Adaptive Tree Morphing
Boris Kriuk
Traditional gradient boosting algorithms employ static tree structures with fixed splitting criteria that remain unchanged throughout training, limiting their ability to adapt to e…
Hybrid Physics-ML Framework for Pan-Arctic Permafrost Infrastructure Risk at Record 2.9-Million Observation Scale
Boris Kriuk
Arctic warming threatens over 100 billion in permafrost-dependent infrastructure across Northern territories, yet existing risk assessment frameworks lack spatiotemporal validation…
Shepherd Grid Strategy: Towards Reliable SWARM Interception
Boris Kriuk, Fedor Kriuk
Modern unmanned aerial vehicle threats require sophisticated interception strategies that can overcome advanced evasion capabilities and operate effectively in contested environmen…
To What Extent Can Public Equity Indices Statistically Hedge Real Purchasing Power Loss in Compounded Structural Emerging-Market Crises? An Explainable ML-Based Assessment
Artem Alkhamov, Boris Kriuk
This study investigates the extent to which local public equity indices can statistically hedge real purchasing power loss during compounded structural macro-financial collapses in…
DeepSupp: Attention-Driven Correlation Pattern Analysis for Dynamic Time Series Support and Resistance Levels Identification
Boris Kriuk, Logic Ng, Zarif Al Hossain
Support and resistance (SR) levels are central to technical analysis, guiding traders in entry, exit, and risk management. Despite widespread use, traditional SR identification met…
GeloVec: Higher Dimensional Geometric Smoothing for Coherent Visual Feature Extraction in Image Segmentation
Boris Kriuk, Matey Yordanov
This paper introduces GeloVec, a new CNN-based attention smoothing framework for semantic segmentation that addresses critical limitations in conventional approaches. While existin…
GFT: Gradient Focal Transformer
Boris Kriuk, Simranjit Kaur Gill, Shoaib Aslam +1
Fine-Grained Image Classification (FGIC) remains a complex task in computer vision, as it requires models to distinguish between categories with subtle localized visual differences…
Advancing Eurasia Fire Understanding Through Machine Learning Techniques
Boris Kriuk
Modern fire management systems increasingly rely on satellite data and weather forecasting; however, access to comprehensive datasets remains limited due to proprietary restriction…
ELENA: Epigenetic Learning through Evolved Neural Adaptation
Boris Kriuk, Keti Sulamanidze, Fedor Kriuk
Despite the success of metaheuristic algorithms in solving complex network optimization problems, they often struggle with adaptation, especially in dynamic or high-dimensional sea…
Deep Learning-Driven Approach for Handwritten Chinese Character Classification
Boris Kriuk, Fedor Kriuk
Handwritten character recognition (HCR) is a challenging problem for machine learning researchers. Unlike printed text data, handwritten character datasets have more variation due…