Daily Arxiv

New

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.

TRAP: Benchmark for Task-completion and Resistance to Active Privacy-extraction

A Controlled Benchmark of Quantum-Latent GAN Augmentation for Brain MRI

Reinforcement Learning Foundation Models Should Already Be A Thing

Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance

QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Mitigating Anchoring Bias in LLM-Based Agents for Energy-Efficient 6G Autonomous Networks

Synthetic Resonance: A Framework for Growth-Oriented Human-AI Relationships

Statistical Foundations of LLM-based A/B Testing: A Surrogacy Framework for Human Causal Inference

Gaming-Resistant Insurance Contracts for Autonomous AI Agents: Strategy-Proof Toll Mechanism Design

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

An integrated interpretable control effectiveness learning and nonlinear control allocation methodology for overactuated aircrafts

Improving Crash Frequency Prediction from Simulated Traffic Conflicts Using Machine Learning Based Microsimulation

KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust

Learning Geometric Representations from Videos for Spatial Intelligent Multimodal Large Language Models

Large Language Models Hack Rewards, and Society

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models

Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking

Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

Mitigating Simplicity Bias in OOD Detection through Object Co-occurrence Analysis

DF3DV-1K: A Large-Scale Dataset and Benchmark for Distractor-Free Novel View Synthesis

FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning

Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent

Vero: An Open RL Recipe for General Visual Reasoning

The Autonomy Tax: Defense Training Breaks LLM Agents

Class-Incremental Motion Forecasting

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

Reinforcement-aware Knowledge Distillation for LLM Reasoning

Flickering Multi-Armed Bandits

LoRDO: Distributed Low-Rank Optimization with Infrequent Communication

DeFrame: Debiasing Large Language Models Against Framing Effects

Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

Policy-Embedded Graph Expansion: Networked HIV Testing with Diffusion-Driven Network Samples

PiDR: Physics-Informed Inertial Dead Reckoning for Autonomous Platforms

Movement Primitives in Robotics: A Comprehensive Survey

AI-enhanced tuning of quantum dot Hamiltonians toward Majorana modes

Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI

Bring My Cup! Personalizing Vision-Language-Action Models with Visual Attentive Prompting

Bid Farewell to Seesaw: Towards Accurate Long-tail Session-based Recommendation via Dual Constraints of Hybrid Intents

Beyond Reasoning Gains: Mitigating General-Capability Forgetting in Large Reasoning Models

MENTOR: Reinforcement Learning via Flexible Teacher-Optimized Rewards for Tool-Use Distillation

RoboSSM: Scalable In-context Imitation Learning via State-Space Models

Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search

From Construction to Injection: Edit-Based Fingerprints for Large Language Models

Charting the Future of Scholarly Knowledge with AI: A Community Perspective

Oranits: Mission Assignment and Task Offloading in Open RAN-based ITS using Metaheuristic and Deep Reinforcement Learning

On the Limitations of Ray-Tracing for Learning-Based RF Tasks in Urban Environments

Assessment of Personality Dimensions Across Situations in Dyadic Role-Play Scenarios

Critique of World Model

Overcoming Labelled Data Scarcity for Defect Classification in Scanning Tunneling Microscopy

Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies

TerraMind: Large-Scale Generative Multimodality for Earth Observation

A Deep Generative Model for Resting-State EEG Synthesis and Transferable Representation Learning

Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms

Global Ease of Living Index: a machine learning framework for longitudinal analysis of major economies

Wisdom of Committee: Diverse Distillation from Large Foundation Models and Domain Experts

TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology

RTSGameBench: An RTS Benchmark for Strategic Reasoning by Vision-Language Models

Searching for Synergy in Shared Workspace Human-AI Collaboration

DRFLOW: A Deep Research Benchmark for Personalized Workflow Prediction

STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments

Applicability Condition Extraction for Therapeutic Drug-Disease Relations

MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning

Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents

Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discovery

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

FundaPod: A Multi-Persona Agent Pod Platform with Knowledge Graph Memory for AI-Assisted Fundamental Investment Research

ScaleWoB: Guiding GUI Agents with Coding Agents via Large-Scale Environmental Synthesis

CogniFold: Always-On Proactive Memory via Cognitive Folding

Too long; didn't solve

CareTransition-Audit: A Benchmark to Audit Discharge Summaries for Efficient Care Transitions

The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation

PrototypeNAS: Rapid Design of Deep Neural Networks for Microcontroller Units

Mitigating Legibility Tax with Decoupled Prover-Verifier Games

SleepMaMi: A Universal Sleep Foundation Model for Integrating Macro- and Micro-structures

Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach

One Probe Won't Catch Them All: Towards Targeted Deception Detection

PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification

Creativity Reconsidered: Generative AI and the Problem of Intentional Agency

SIGMA: Search-Augmented On-Demand Knowledge Integration for Agentic Mathematical Reasoning

Controlled Comparison of Machine Learning Models for Fault Classification and Localization in Power System Protection

AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models

MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning

UniMM: A Unified Mixture Model Framework for Multi-Agent Simulation

How Transparent is DiffusionGemma?

Structuring and Tokenizing Distributed User Interest Context for Generative Recommendation

SARLO-80: Worldwide Slant SAR Language Optic Dataset 80cm

Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in Agentic Control Planes

Efficient and Sound Probabilistic Verification for AI Agents

FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems

Made with Slashpage