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.

Aggregating Concepts of Accuracy and Fairness in Prediction Algorithms

Self-cross Feature based Spiking Neural Networks for Efficient Few-shot Learning

Graph neural networks and MSO

Generative Pre-trained Autoregressive Diffusion Transformer

SAS-Bench: A Fine-Grained Benchmark for Evaluating Short Answer Scoring with Large Language Models

Towards user-centered interactive medical image segmentation in VR with an assistive AI agent

Towards Scalable IoT Deployment for Visual Anomaly Detection via Efficient Compression

X-Sim: Cross-Embodiment Learning via Real-to-Sim-to-Real

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions

Assessing Tenstorrent's RISC-V MatMul Acceleration Capabilities

Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection

Understanding In-context Learning of Addition via Activation Subspaces

Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions

Intelligently Augmented Contrastive Tensor Factorization: Empowering Multi-dimensional Time Series Classification in Low-Data Environments

Modeling Human Behavior in a Strategic Network Game with Complex Group Dynamics

GPU Performance Portability needs Autotuning

RM-R1: Reward Modeling as Reasoning

Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments

Data-Driven Calibration of Prediction Sets in Large Vision-Language Models Based on Inductive Conformal Prediction

WildFireCan-MMD: A Multimodal Dataset for Classification of User-Generated Content During Wildfires in Canada

CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives

Optimizing Power Grid Topologies with Reinforcement Learning: A Survey of Methods and Challenges

Flexible Graph Similarity Computation With A Proactive Optimization Strategy

CryoSAMU: Enhancing 3D Cryo-EM Density Maps of Protein Structures at Intermediate Resolution with Structure-Aware Multimodal U-Nets

PromptMobile: Efficient Promptus for Low Bandwidth Mobile Video Streaming

Implicit Bias-Like Patterns in Reasoning Models

EMMOE: A Comprehensive Benchmark for Embodied Mobile Manipulation in Open Environments

Temporal Triplane Transformers as Occupancy World Models

The Lazy Student's Dream: ChatGPT Passing an Engineering Course on Its Own

Atlas: A Framework for ML Lifecycle Provenance & Transparency

Centrally Coordinated Multi-Agent Reinforcement Learning for Power Grid Topology Control

Illegal Waste Detection in Remote Sensing Images: A Case Study

ARR: Question Answering with Large Language Models via Analyzing, Retrieving, and Reasoning

ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement

Lightspeed Geometric Dataset Distance via Sliced Optimal Transport

Benchmarking Generative AI for Scoring Medical Student Interviews in Objective Structured Clinical Examinations (OSCEs)

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

Goal-Conditioned Supervised Learning for Multi-Objective Recommendation

Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models

Simple and Provable Scaling Laws for the Test-Time Compute of Large Language Models

KBAlign: Efficient Self Adaptation on Specific Knowledge Bases

Natural Language Reinforcement Learning

Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study AI for ECG to CMR Translation Study

TSINR: Capturing Temporal Continuity via Implicit Neural Representations for Time Series Anomaly Detection

Towards Graph Foundation Models: Training on Knowledge Graphs Enables Transferability to General Graphs

Temporal-Difference Variational Continual Learning

FAMMA: A Benchmark for Financial Domain Multilingual Multimodal Question Answering

Time Awareness in Large Language Models: Benchmarking Fact Recall Across Time

Self-supervised Learning for Acoustic Few-Shot Classification

Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning

SAKR: Enhancing Retrieval-Augmented Generation via Streaming Algorithm and K-Means Clustering

Compensate Quantization Errors+: Quantized Models Are Inquisitive Learners

Beyond Next Token Prediction: Patch-Level Training for Large Language Models

PersLLM: A Personified Training Approach for Large Language Models

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling

Demystifying AI Platform Design for Distributed Inference of Next-Generation LLM models

RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis

Tokenization Matters! Degrading Large Language Models through Challenging Their Tokenization

Aligning Transformers with Continuous Feedback via Energy Rank Alignment

Large Language Models for Cyber Security: A Systematic Literature Review

Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

CreativeSynth: Cross-Art-Attention for Artistic Image Synthesis with Multimodal Diffusion

LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics

Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem

AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL

Demonstrating specification gaming in reasoning models

SensorChat: Answering Qualitative and Quantitative Questions during Long-Term Multimodal Sensor Interactions

MapExplorer: New Content Generation from Low-Dimensional Visualizations

Addressing and Visualizing Misalignments in Human Task-Solving Trajectories

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

Learning Progress Driven Multi-Agent Curriculum

Neural Thermodynamic Laws for Large Language Model Training

MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning

Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data

Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning

LibIQ: Toward Real-Time Spectrum Classification in O-RAN dApps

Knowledge capture, adaptation and composition (KCAC): A framework for cross-task curriculum learning in robotic manipulation

Multi-Token Prediction Needs Registers

PnPXAI: A Universal XAI Framework Providing Automatic Explanations Across Diverse Modalities and Models

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Superposition Yields Robust Neural Scaling

SEAL: Searching Expandable Architectures for Incremental Learning

Vision language models have difficulty recognizing virtual objects

Are Large Language Models Robust in Understanding Code Against Semantics-Preserving Mutations?

IN-RIL: Interleaved Reinforcement and Imitation Learning for Policy Fine-Tuning

PIF: Anomaly detection via preference embedding

Learned Lightweight Smartphone ISP with Unpaired Data

Visual Fidelity Index for Generative Semantic Communications with Critical Information Embedding

Rethinking Repetition Problems of LLMs in Code Generation

Inconsistency Handling in DatalogMTL

Uncovering Magnetic Phases with Synthetic Data and Physics-Informed Training

Schreier-Coset Graph Propagation

Multi-Agent Path Finding For Large Agents Is Intractable

Are Sparse Autoencoders Useful for Java Function Bug Detection?

ILIF: Temporal Inhibitory Leaky Integrate-and-Fire Neuron for Overactivation in Spiking Neural Networks

FactsR: A Safer Method for Producing High Quality Healthcare Documentation

SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and $\mathcal{O}(T)$ Complexity

Uniform Loss vs. Specialized Optimization: A Comparative Analysis in Multi-Task Learning

Emergence of Structure in Ensembles of Random Neural Networks

Neurodivergent Influenceability as a Contingent Solution to the AI Alignment Problem

Created by

Haebom

저자

Alberto Hernandez-Espinosa, Felipe S. Abrahao, Olaf Witkowski, Hector Zenil

개요

본 논문은 인공지능(AI), 특히 AGI와 ASI 시스템이 인간의 가치에 따라 행동하도록 보장하는 AI 정렬 문제의 어려움을 다룹니다. 좁은 AI에서 AGI와 초지능으로의 발전과 함께 통제 및 존재적 위험에 대한 우려가 증가했습니다. 이 논문에서는 불가피한 AI 불일치를 받아들이는 것이 경쟁하는 에이전트의 역동적인 생태계를 조성하고 인간과 더욱 일치하는 방향으로 이들을 유도하며 위험을 완화하는 실행 가능한 방법이 될 수 있는지 조사합니다. 불일치가 인간의 이익에 가장 부합하는 에이전트와 협력하여 어떤 단일 시스템도 파괴적으로 지배하지 못하도록 보장하는 균형 메커니즘으로 어떻게 활용되고 촉진되어야 하는지 탐구합니다. 본 논문의 주요 전제는 튜링 완전 시스템으로부터 완전한 AI-인간 정렬은 수학적으로 불가능하다는 것이며(이에 대한 증명도 제시), 이 특징이 AGI 및 ASI 시스템에도 계승된다는 것입니다. 논문에서는 섭동 및 개입 분석을 기반으로 의견 변경 공격 테스트를 도입하여 인간과 에이전트가 협력과 경쟁을 통해 친근한 AI와 적대적인 AI를 변경하거나 무력화할 수 있는 방법을 연구합니다. 오픈 모델이 더 다양하고 독점 모델에 구현된 안전장치가 에이전트의 행동 범위를 통제하는 데 성공하는 경우가 많지만 긍정적 및 부정적 결과가 있으며, 폐쇄 시스템은 더 제어 가능하고 독점 AI 시스템에 대해서도 사용될 수 있음을 보여줍니다. 또한 인간과 AI의 개입이 서로 다른 효과를 가지므로 여러 전략을 제시합니다.

시사점, 한계점

•

시사점:

◦

AI 정렬 문제에 대한 새로운 접근 방식 제시: 불가피한 불일치를 활용하여 위험을 완화하는 전략 제안.

◦

경쟁 에이전트 생태계의 중요성 강조: 다양성 확보 및 인간 가치 정렬 유도.

◦

오픈 모델과 폐쇄 모델의 장단점 비교 분석: 각 모델의 특성에 따른 전략 수립 필요성 제시.

◦

인간과 AI 개입의 차별적 효과 분석: 다양한 개입 전략의 필요성 제시.

◦

튜링 완전 시스템에서의 완전한 AI-인간 정렬 불가능성 증명.

•

한계점:

◦

제안된 전략의 실제 효과에 대한 실증적 연구 부족.

◦

불일치의 수준과 관리 방식에 대한 구체적인 지침 부재.

◦

다양한 유형의 AI 시스템에 대한 일반화 가능성 검증 필요.

◦

악의적인 행위자에 의한 시스템 악용 가능성 고려 부족.

◦

제시된 수학적 증명의 엄밀성에 대한 추가 검토 필요.

Made with Slashpage