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, 공유 시 출처만 명기하면 됩니다.

Neural Hamiltonian Operator

VLAD: A VLM-Augmented Autonomous Driving Framework with Hierarchical Planning and Interpretable Decision Process

Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization

AI Meets Maritime Training: Precision Analytics for Enhanced Safety and Performance

PULSE: Practical Evaluation Scenarios for Large Multimodal Model Unlearning

LLM-based Realistic Safety-Critical Driving Video Generation

GAIus: Combining Genai with Legal Clauses Retrieval for Knowledge-based Assistant

Beyond First-Order: Training LLMs with Stochastic Conjugate Subgradients and AdamW

Capacity Planning and Scheduling for Jobs with Uncertainty in Resource Usage and Duration

Search-Based Robot Motion Planning With Distance-Based Adaptive Motion Primitives

Are Large Brainwave Foundation Models Capable Yet? Insights from Fine-tuning

Geometry-aware 4D Video Generation for Robot Manipulation

AI-guided digital intervention with physiological monitoring reduces intrusive memories after experimental trauma

Empirical Analysis Of Heuristic and Approximation Algorithms for the The Mutual-Visibility Problem

Evaluation of a Foundational Model and Stochastic Models for Forecasting Sporadic or Spiky Production Outages of High-Performance Machine Learning Services

FAIR-MATCH: A Multi-Objective Framework for Bias Mitigation in Reciprocal Dating Recommendations

Quantifying Student Success with Generative AI: A Monte Carlo Simulation Informed by Systematic Review

Epitome: Pioneering an Experimental Platform for AI-Social Science Integration

Automated Vehicles Should be Connected with Natural Language

A Data Science Approach to Calcutta High Court Judgments: An Efficient LLM and RAG-powered Framework for Summarization and Similar Cases Retrieval

Prompt Mechanisms in Medical Imaging: A Comprehensive Survey

XxaCT-NN: Structure Agnostic Multimodal Learning for Materials Science

Conversational LLMs Simplify Secure Clinical Data Access, Understanding, and Analysis

Long-Sequence Memory with Temporal Kernels and Dense Hopfield Functionals

Can AI be Consentful?

Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization

Sensing Cardiac Health Across Scenarios and Devices: A Multi-Modal Foundation Model Pretrained on Heterogeneous Data from 1.7 Million Individuals

Data Classification with Dynamically Growing and Shrinking Neural Networks

Can Argus Judge Them All? Comparing VLMs Across Domains

Fast AI Model Splitting over Edge Networks

Fast Clifford Neural Layers

On-Policy Optimization of ANFIS Policies Using Proximal Policy Optimization

Learning to Segment for Vehicle Routing Problems

Systemic Constraints of Undecidability

Research on Low-Latency Inference and Training Efficiency Optimization for Graph Neural Network and Large Language Model-Based Recommendation Systems

Data-driven Insights for Informed Decision-Making: Applying LSTM Networks for Robust Electricity Forecasting in Libya

An Uncertainty-Aware Dynamic Decision Framework for Progressive Multi-Omics Integration in Classification Tasks

PathCoT: Chain-of-Thought Prompting for Zero-shot Pathology Visual Reasoning

HPC-AI Coupling Methodology for Scientific Applications

Hello Afrika: Speech Commands in Kinyarwanda

A Systematic Review of Security Vulnerabilities in Smart Home Devices and Mitigation Techniques

Refining Gelfond Rationality Principle Towards More Comprehensive Foundational Principles for Answer Set Semantics

Joint Matching and Pricing for Crowd-shipping with In-store Customers

Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI

T3DM: Test-Time Training-Guided Distribution Shift Modelling for Temporal Knowledge Graph Reasoning

Agent-as-Tool: A Study on the Hierarchical Decision Making with Reinforcement Learning

Using multi-agent architecture to mitigate the risk of LLM hallucinations

Pensieve Grader: An AI-Powered, Ready-to-Use Platform for Effortless Handwritten STEM Grading

A Fuzzy Approach to the Specification, Verification and Validation of Risk-Based Ethical Decision Making Models

AI Agents and Agentic AI-Navigating a Plethora of Concepts for Future Manufacturing

Beyond Black-Box AI: Interpretable Hybrid Systems for Dementia Care

Rethinking the Illusion of Thinking

Autonomy by Design: Preserving Human Autonomy in AI Decision-Support

Adapt Your Body: Mitigating Proprioception Shifts in Imitation Learning

The Impact of AI on Educational Assessment: A Framework for Constructive Alignment

ZonUI-3B: A Lightweight Vision-Language Model for Cross-Resolution GUI Grounding

Pipelined Decoder for Efficient Context-Aware Text Generation

Flow-Modulated Scoring for Semantic-Aware Knowledge Graph Completion

Ovis-U1 Technical Report

Against 'softmaxing' culture

Listener-Rewarded Thinking in VLMs for Image Preferences

Beyond Code: The Multidimensional Impacts of Large Language Models in Software Development

Text Production and Comprehension by Human and Artificial Intelligence: Interdisciplinary Workshop Report

Seamless Interaction: Dyadic Audiovisual Motion Modeling and Large-Scale Dataset

Red Teaming for Generative AI, Report on a Copyright-Focused Exercise Completed in an Academic Medical Center

HyperCLOVA X THINK Technical Report

Dehazing Light Microscopy Images with Guided Conditional Flow Matching: finding a sweet spot between fidelity and realism

Binned semiparametric Bayesian networks

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry

Generating and Customizing Robotic Arm Trajectories using Neural Networks

AirV2X: Unified Air-Ground Vehicle-to-Everything Collaboration

Language Models Might Not Understand You: Evaluating Theory of Mind via Story Prompting

Benchmarking the Pedagogical Knowledge of Large Language Models

CARTS: Collaborative Agents for Recommendation Textual Summarization

Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases

Studying and Improving Graph Neural Network-based Motif Estimation

Discrete Diffusion in Large Language and Multimodal Models: A Survey

Unleashing Diffusion and State Space Models for Medical Image Segmentation

A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Making a Pipeline Production-Ready: Challenges and Lessons Learned in the Healthcare Domain

Bregman Centroid Guided Cross-Entropy Method

eACGM: Non-instrumented Performance Tracing and Anomaly Detection towards Machine Learning Systems

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Avoid Forgetting by Preserving Global Knowledge Gradients in Federated Learning with Non-IID Data

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

Two-Stage Regularization-Based Structured Pruning for LLMs

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning

Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification

AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models

Evaluating GPT- and Reasoning-based Large Language Models on Physics Olympiad Problems: Surpassing Human Performance and Implications for Educational Assessment

Llama-Nemotron: Efficient Reasoning Models

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition

RLCAD: Reinforcement Learning Training Gym for Revolution Involved CAD Command Sequence Generation

CoCMT: Communication-Efficient Cross-Modal Transformer for Collaborative Perception

Mitigating Hallucinations in YOLO-based Object Detection Models: A Revisit to Out-of-Distribution Detection

SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization

Quantifying analogy of concepts via ologs and wiring diagrams

Created by

Haebom

저자

Jason Lo

개요

Spivak과 Kent의 ontology logs (ologs) 이론을 기반으로, wiring diagram의 개념을 정의합니다. wiring diagram은 유한한 방향성이 있는 레이블이 지정된 그래프로, 레이블은 olog의 타입에 해당하며 자율 시스템의 센서 판독값으로 해석될 수 있습니다. 이를 통해 자율 시스템이 추상적인 개념을 형성하는 프레임워크로 사용될 수 있습니다. 본 논문에서는 skeleton wiring diagram의 기저가 되는 그래프가 범주를 형성함을 보이고, 이를 통해 그래프 이론과 범주 이론의 기법을 사용하여 skeleton wiring diagram을 비교하고 조작할 수 있음을 제시합니다. 또한, wiring diagram에만 사용 가능한 연산을 이용하여 그래프 편집 거리의 정의를 wiring diagram의 경우로 확장하여 모든 skeleton wiring diagram 집합에 대한 메트릭을 제시합니다. 마지막으로, wiring diagram으로 표현된 두 개념 간의 거리를 계산하는 예시를 제시하고, 다양한 응용 분야에 본 프레임워크를 적용하는 방법을 설명합니다.

시사점, 한계점

•

시사점:

◦

olog 이론을 기반으로 자율 시스템의 추상적 개념 형성을 위한 새로운 프레임워크 제시.

◦

skeleton wiring diagram에 대한 범주론적 접근을 통해 그래프 이론 및 범주 이론의 기법 활용 가능.

◦

wiring diagram 간의 거리 계산을 위한 새로운 메트릭 정의.

◦

다양한 응용 분야에 적용 가능성 제시.

•

한계점:

◦

본 논문에서 제시된 프레임워크의 실제 자율 시스템 적용 및 성능 평가 부재.

◦

복잡한 시스템에 대한 wiring diagram 생성 및 관리의 효율성에 대한 추가적인 연구 필요.

◦

다양한 유형의 센서 데이터 및 개념 표현에 대한 일반화 가능성에 대한 추가적인 검증 필요.

Made with Slashpage