Daily Arxiv

전 세계에서 발간되는 인공지능 관련 논문을 정리하는 페이지 입니다.
본 페이지는 Google Gemini를 활용해 요약 정리하며, 비영리로 운영 됩니다.
논문에 대한 저작권은 저자 및 해당 기관에 있으며, 요약본 공유 시 출처만 명기하면 됩니다.
This service is supported by Google Gemini.

Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach

TrainMover: An Interruption-Resilient Runtime for ML Training

Tube Loss: A Novel Approach for Prediction Interval Estimation

FlipAttack: Jailbreak LLMs via Flipping

RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition

FM-G-CAM: A Holistic Approach for Explainable AI in Computer Vision

Approximate and Weighted Data Reconstruction Attack in Federated Learning

Learning Developmental Scaffoldings to Guide Self-Organisation

Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems

$\pi$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

Falkor-IRAC: Graph-Constrained Generation for Verified Legal Reasoning in Indian Judicial AI

CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation

SimPersona: Learning Discrete Buyer Personas from Raw Clickstreams for Grounded E-Commerce Agents

Network-Aware Bilinear Tokenization for Brain Functional Connectivity Representation Learning

A Constraint Programming Approach for n-Day Lookahead Playoff Clinching in the NHL

A Cascaded Generative Approach for e-Commerce Recommendations

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning

Do Linear Probes Generalize Better in Persona Coordinates?

Towards a Virtual Neuroscientist: Autonomous Neuroimaging Analysis via Multi-Agent Collaboration

Automated alignment is harder than you think

ProCompNav: Proactive Instance Navigation with Comparative Judgment for Ambiguous User Queries

Rethinking Agentic Reinforcement Learning In Large Language Models

FutureWorld: A Live Reinforcement Learning Environment for Predictive Agents with Real-World Outcome Rewards

Mecha-nudges for Machines

MESD: A Risk-Sensitive Metric for Explanation Fairness Across Intersectional Subgroups

Opponent State Inference Under Partial Observability: An HMM-POMDP Framework for 2026 Formula 1 Energy Strategy

The Informational Cost of Agency: A Bounded Measure of Interaction Efficiency for Deployed Reinforcement Learning

Asking the Right Questions: Improving Reasoning with Generated Stepping Stones

When AI Persuades: Adversarial Explanation Attacks on Human Trust in AI-Assisted Decision Making

Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models

CodeDistiller: Automatically Generating Code Libraries for Scientific Coding Agents

AI Consciousness and Existential Risk

QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Systems

Quantum Artificial Intelligence for Mission-Critical Systems: Foundations, Architectural Elements, and Future Directions

Frontier Large Language Models Rival State-of-the-Art Planners

Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction

From Guidelines to Guarantees: A Graph-Based Evaluation Harness for Domain-Specific Evaluation of LLMs

Honey, I shrunk the hypothesis space (through logical preprocessing)

VideoGameBench: Can Vision-Language Models complete popular video games?

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

Designing Datacenter Power Delivery Hierarchies for the AI Era

A Generative AI Framework for Intelligent Utility Billing CO 2 Analytics and Sustainable Resource Optimisation

AI-Mediated Communication Can Steer Collective Opinion

Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

Layer Equivalence Is Not a Property of Layers Alone: How You Test Redundancy Changes What You Find

A Unified Generative-AI Framework for Smart Energy Infrastructure: Intelligent Gas Distribution, Utility Billing, Carbon Analytics, and Quantum-Inspired Optimisation

Evaluating Design Video Generation: Metrics for Compositional Fidelity

Argus: Evidence Assembly for Scalable Deep Research Agents

paper.json: A Coordination Convention for LLM-Agent-Actionable Papers

Second-Order Multi-Level Variance Correction for Modality Competition in Multimodal Models

Surrogate Neural Architecture Codesign Package (SNAC-Pack)

Navigating Potholes with Geometry-Aware Sharpness Minimization

Entropy Across the Bridge: Conditional-Marginal Discretization for Flow and Schr\"odinger Samplers

GenShield: Unified Detection and Artifact Correction for AI-Generated Images

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix

Federated Imputation under Heterogeneous Feature Spaces

GeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility Scenarios

Centralized vs Decentralized Federated Learning: A trade-off performance analysis

Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction

Towards Trustworthy and Explainable AI for Perception Models: From Concept to Prototype Vehicle Deployment

Towards Foundation Models for Relational Databases with Language Models and Graph Neural Networks

VideoSeeker: Incentivizing Instance-level Video Understanding via Native Agentic Tool Invocation

AgriMind: An Ensemble Deep Learning Framework for Multi-Class Plant Disease Classification

Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting

Misspecified Explore-then-Exploit Leads to Supra-Competitive Prices

Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making

Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification

XSearch: Explainable Code Search via Concept-to-Code Alignment

RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents

Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data

Who Owns This Agent? Tracing AI Agents Back to Their Owners

From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation

Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study

CitePrism: Human-in-the-Loop AI for Citation Auditing and Editorial Integrity

Constrained latent state modeling: A unifying perspective on representation learning under competing constraints

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues

Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports

Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective

When and Why Adversarial Training Improves PINNs: A Neural Tangent Kernel Perspective

Decomposed Vision-Language Alignment for Fine-Grained Open-Vocabulary Segmentation

LoCO: Low-rank Compositional Rotation Fine-tuning

SLIP & ETHICS: Graduated Intervention for AI Emotional Companions

Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation

RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations

Generative Long-term User Interest Modeling for Click-Through Rate Prediction

Uncertainty-Aware Wildfire Smoke Density Classification from Satellite Imagery via CBAM-Augmented EfficientNet with Evidential Deep Learning

CHoE: Cross-Domain Heterogeneous Graph Prompt Learning via Structure-Conditioned Experts

Symplectic Neural Operators for Learning Infinite Dimensional Hamiltonian Systems

FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?

Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education

RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades

GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

Modeling Music as a Time-Frequency Image: A 2D Tokenizer for Music Generation

Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets

A Topology-Aware Spatiotemporal Handover Framework for Continuous Multi-UAV Tracking

Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics

Enhancing Black-Litterman Portfolio via Hybrid Forecasting Model Combining Multivariate Decomposition and Noise Reduction

Created by

Haebom

저자

Ziye Yang, Ke Lu

개요

본 논문은 기존 평균-분산 모델의 입력 매개변수 민감도 및 유연성 부족 문제를 해결하기 위해, 시장 균형 수익률과 투자자의 주관적 견해를 통합하는 Black-Litterman 모델을 개선하는 새로운 하이브리드 딥러닝 모델을 제안합니다. 특히, 특이값 분해(SSA), 다변량 정렬 경험적 모드 분해(MA-EMD), 그리고 시간적 합성곱 신경망(TCN)을 결합하여 자산 가격 예측 정확도를 향상시키고, Black-Litterman 모델의 주관적 견해 생성 능력을 강화하는 것을 목표로 합니다. 실험 결과, 노이즈 감소 전처리가 모델 정확도를 향상시키며, 제안된 모델의 예측 성능이 세 가지 다변량 분해 기준 모델보다 훨씬 우수함을 보여줍니다. NASDAQ 100 지수의 20개 대표 주식을 사용하여 투자 포트폴리오를 구성하고, 하이브리드 예측 모델을 Black-Litterman 모델과 결합하여 단기 보유 기간 동안 평균-분산, 균등 가중, 시장 가중 모델보다 더 나은 수익률과 위험 관리 능력을 보이는 투자 포트폴리오를 생성합니다.