KOINEU

HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting

1. 연구 배경 및 동기 다변량 시계열 예측 은 각 채널(변수) 간 상호작용을 어떻게 모델링하느냐가 핵심이다. 채널‑독립 모델 은 파라미터 수가 적어 과적합 위험이 낮지만, 변수 간 유용한 정보를 놓친다. 채널‑종속 모델 은 복잡한 상호작용을 포착하지만, 파라미터 폭증으로 일반화가 어려워진다. 이러한 딜레마를 해소하기 위해 하이퍼네트워크 를 활용해 데이터‑특화 가중치를 동적으로 생성함으로써, 파라미터 효율성을 유지하면서도 채널 간 관계를 반영하고자 함. 2. 핵심 아이디어 1. 학습 가능한 임베딩 행렬 각 시계열 변수에 대한 고정

HN-MVTS: HyperNetwork-based Multivariate Time Series Forecasting

How Similar Are Grokipedia and Wikipedia? A Multi-Dimensional Textual and Structural Comparison

HyperD: Hybrid Periodicity Decoupling Framework for Traffic Forecasting

Instability of two-pulse periodic waves with long wavelength in some Hamiltonian PDEs

Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning

Inter-Agent Trust Models: A Comparative Study of Brief, Claim, Proof, Stake, Reputation and Constraint in Agentic Web Protocol Design-A2A, AP2, ERC-8004, and Beyond

Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training

Introducing the b-value: combining unbiased and biased estimators from a sensitivity analysis perspective

Investigating Intra-Abstraction Policies For Non-exact Abstraction Algorithms

Invisible Triggers, Visible Threats! Road-Style Adversarial Creation Attack for Visual 3D Detection in Autonomous Driving

Is there a relationship between Mean Opinion Score (MOS) and Just Noticeable Difference (JND)?

Iterated mutations of symmetric periodic algebras

Joint beamforming and mode optimization for multi-functional STAR-RIS-aided integrated sensing and communication networks

LacaDM: A Latent Causal Diffusion Model for Multiobjective Reinforcement Learning

Learning Geometry: A Framework for Building Adaptive Manifold Models through Metric Optimization

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data

Learning with Locally Private Examples by Inverse Weierstrass Private Stochastic Gradient Descent

Localized kernel gradient correction for SPH simulations of water wave propagation

LongCat-Flash-Omni Technical Report

Lyapunov Function-guided Reinforcement Learning for Flight Control

Machine-Learning Accelerated Calculations of Reduced Density Matrices

MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning

Measuring Chain-of-Thought Monitorability Through Faithfulness and Verbosity

MedRECT: A Medical Reasoning Benchmark for Error Correction in Clinical Texts

MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models

MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs

Modeling and Topology Estimation of Low Rank Dynamical Networks

Multi-Channel Replay Speech Detection using Acoustic Maps

Multitask Multimodal Self-Supervised Learning for Medical Images

NeuroFlex: Column-Exact ANN-SNN Co-Execution Accelerator with Cost-Guided Scheduling

Nonlinear Predictive Control of the Continuum and Hybrid Dynamics of a Suspended Deformable Cable for Aerial Pick and Place

Nonparametric Kernel Regression for Coordinated Energy Storage Peak Shaving with Stacked Services

OKBench: Democratizing LLM Evaluation with Fully Automated, On-Demand, Open Knowledge Benchmarking

On Sharpened Convergence Rate of Generalized Sliced Inverse Regression for Nonlinear Sufficient Dimension Reduction

On the classical Reinforcement problem and Optimisation

On the Value of Base Station Motion Knowledge for Goal-Oriented Remote Monitoring with Energy-Harvesting Sensors

Open diffusion MRI and connectivity data for epilepsy and surgery: The IDEAS II release

Optimal control of stochastic Volterra integral equations with completely monotone kernels and stochastic differential equations on Hilbert spaces with unbounded control and diffusion operators

Optimized Many-Hypercube Codes toward Lower Logical Error Rates and Earlier Realization

Orthogonal parametrisations of Extreme-Value distributions

PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork

Parameter Interpolation Adversarial Training for Robust Image Classification

Parameter-free representations outperform single-cell foundation models on downstream benchmarks

PECL: A Heterogeneous Parallel Multi-Domain Network for Radar-Based Human Activity Recognition

Power weight inequalities for spherical maximal functions

Probing the Probes: Methods and Metrics for Concept Alignment

Proof of Concept: Local TX Real-Time Phase Calibration in MIMO Systems

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

Quantifying and Mitigating Socially Desirable Responding in LLMs: A Desirability-Matched Graded Forced-Choice Psychometric Study

Random Wavelet Features for Graph Kernel Machines

< Category Statistics (Total: 5073) >

Start searching

No results found