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.

Neural Policy Composition from Free Energy Minimization

HAI-Eval: Measuring Human-AI Synergy in Collaborative Coding

Two-Dimensional Quantization for Geometry-Aware Audio Coding

Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves

LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Sufficient Explanations in Databases and their Connections to Database Repairs

Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity

SemanticOpt: Towards LLM-Based Semantic Black-Box Optimization

Monotone and Separable Set Functions: Characterizations and Neural Models

SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery

A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking

UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization

SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations

How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models

NoiseShift: Resolution-Aware Noise Recalibration for Better Low-Resolution Image Generation

BioBlobs: Unsupervised Discovery of Functional Substructures for Protein Function Prediction

Dynamic-TreeRPO: Breaking the Independent Trajectory Bottleneck with Structured Sampling

Painless Activation Steering: An Automated, Lightweight Approach for Post-Training Large Language Models

Logic of Hypotheses: from Zero to Full Knowledge in Neurosymbolic Integration

Autoguided Online Data Curation for Diffusion Model Training

CUBE: Contrastive Understanding by Balanced Experiments

Generalized Policy Gradient with History-Aware Decision Transformer for Reliable Routing over Graph Signals

Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty

CIS-BWE: Chaos-Informed Speech Bandwidth Extension

A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement

Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling

Deep Double Q-learning

The Hardness of Achieving Impact in AI for Social Impact Research: A Ground-Level View of Challenges & Opportunities

FAR: Function-preserving Attention Replacement for IMC-friendly Inference

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations

Optimizing LLM Inference: Fluid-Guided Online Scheduling with Memory Constraints

Large Language Models Could Be Rote Learners

Do Chinese models speak Chinese languages?

TokenButler: Token Importance is Predictable

Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs

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

Advancing Software Security and Reliability in Cloud Platforms through AI-based Anomaly Detection

Created by

Haebom

저자

Sabbir M. Saleh, Ibrahim Mohammed Sayem, Nazim Madhavji, John Steinbacher

개요

본 논문은 AI 기반의 이상 탐지를 통해 CI/CD 파이프라인의 보안을 강화하는 연구를 다룹니다. 기존의 정적 보안 테스트 및 CI/CD 관행 연구와 달리, 네트워크 트래픽 패턴 분석을 통해 사이버 공격을 탐지하는 데 초점을 맞춥니다. CNN과 LSTM을 결합한 모델을 사용하여 CSE-CIC-IDS2018 및 CSE-CIC-IDS2017 데이터셋으로 실험을 진행, 98.69%와 98.30%의 정확도를 달성했습니다. CI/CD 파이프라인의 각 단계에서 네트워크 이상 현상을 반영하는 로그 파일을 생성하여 현대 DevOps 관행의 보안 문제 해결에 기여합니다.