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.

Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play

E2E-AFG: An End-to-End Model with Adaptive Filtering for Retrieval-Augmented Generation

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

CATCH: Channel-Aware multivariate Time Series Anomaly Detection via Frequency Patching

Learning to Compare Hardware Designs for High-Level Synthesis

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning

Automated detection of underdiagnosed medical conditions via opportunistic imaging

Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant

On Synthetic Texture Datasets: Challenges, Creation, and Curation

Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding

XG-NID: Dual-Modality Network Intrusion Detection using a Heterogeneous Graph Neural Network and Large Language Model

Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon

Enhancing Differential Testing With LLMs For Testing Deep Learning Libraries

HORAE: A Domain-Agnostic Language for Automated Service Regulation

DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying

Analyzing Consumer IoT Traffic from Security and Privacy Perspectives: a Comprehensive Survey

DyCE: Dynamically Configurable Exiting for Deep Learning Compression and Real-time Scaling

The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets

Connecting NTK and NNGP: A Unified Theoretical Framework for Wide Neural Network Learning Dynamics

An automated end-to-end deep learning-based framework for lung cancer diagnosis by detecting and classifying the lung nodules

Label-Efficient Deep Learning in Medical Image Analysis: Challenges and Future Directions

Transformer-based assignment decision network for multiple object tracking

An alignment safety case sketch based on debate

The Power of Stories: Narrative Priming Shapes How LLM Agents Collaborate and Compete

A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law

Agentic Neurodivergence as a Contingent Solution to the AI Alignment Problem

Theoretical Foundations for Semantic Cognition in Artificial Intelligence

Approximate Lifted Model Construction

MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind

Advancing Embodied Agent Security: From Safety Benchmarks to Input Moderation

Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute

Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems

Generating Symbolic World Models via Test-time Scaling of Large Language Models

Imagining and building wise machines: The centrality of AI metacognition

Public Perceptions of Fairness Metrics Across Borders

Combating Confirmation Bias: A Unified Pseudo-Labeling Framework for Entity Alignment

Flow-GRPO: Training Flow Matching Models via Online RL

StreamBridge: Turning Your Offline Video Large Language Model into a Proactive Streaming Assistant

ComPO: Preference Alignment via Comparison Oracles

TransProQA: an LLM-based literary Translation evaluation metric with Professional Question Answering

TokLIP: Marry Visual Tokens to CLIP for Multimodal Comprehension and Generation

Reasoning Models Don't Always Say What They Think

Crosslingual Reasoning through Test-Time Scaling

CART-ELC: Oblique Decision Tree Induction via Exhaustive Search

Threshold Modulation for Online Test-Time Adaptation of Spiking Neural Networks

Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields

High-fidelity Grain Growth Modeling: Leveraging Deep Learning for Fast Computations

Feature-Augmented Deep Networks for Multiscale Building Segmentation in High-Resolution UAV and Satellite Imagery

Mapping User Trust in Vision Language Models: Research Landscape, Challenges, and Prospects

Scalable Chain of Thoughts via Elastic Reasoning

Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes

Software Development Life Cycle Perspective: A Survey of Benchmarks for CodeLLMs and Agents

T-T: Table Transformer for Tagging-based Aspect Sentiment Triplet Extraction

Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration

Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning

Incentive-Aware Machine Learning; Robustness, Fairness, Improvement & Causality

LAPSO: A Unified Optimization View for Learning-Augmented Power System Operations

Concept-Based Unsupervised Domain Adaptation

Revealing Weaknesses in Text Watermarking Through Self-Information Rewrite Attacks

Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language Models

Stochastic Variational Propagation: Local, Scalable and Efficient Alternative to Backpropagation

Dukawalla: Voice Interfaces for Small Businesses in Africa

Understanding In-context Learning of Addition via Activation Subspaces

Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators

Beyond Low-rank Decomposition: A Shortcut Approach for Efficient On-Device Learning

FG-CLIP: Fine-Grained Visual and Textual Alignment

Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations

Direct Image Classification from Fourier Ptychographic Microscopy Measurements without Reconstruction

Image-Text Relation Prediction for Multilingual Tweets

Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints

An Agent-Based Modeling Approach to Free-Text Keyboard Dynamics for Continuous Authentication

StabStitch++: Unsupervised Online Video Stitching with Spatiotemporal Bidirectional Warps

Rethinking Invariance in In-context Learning

Decomposition of Probabilities of Causation with Two Mediators

ChainMarks: Securing DNN Watermark with Cryptographic Chain

AI and Vision based Autonomous Navigation of Nano-Drones in Partially-Known Environments

Moments of Causal Effects

ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators

Graffe: Graph Representation Learning via Diffusion Probabilistic Models

Chain-of-Thought Tokens are Computer Program Variables

T2VTextBench: A Human Evaluation Benchmark for Textual Control in Video Generation Models

Structural Alignment in Link Prediction

Fair Uncertainty Quantification for Depression Prediction

Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction

An Open-Source Dual-Loss Embedding Model for Semantic Retrieval in Higher Education

SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models

Precise gradient descent training dynamics for finite-width multi-layer neural networks

Clustering with Communication: A Variational Framework for Single Cell Representation Learning

Cross-Branch Orthogonality for Improved Generalization in Face Deepfake Detection

QBR: A Question-Bank-Based Approach to Fine-Grained Legal Knowledge Retrieval for the General Public

ConCISE: Confidence-guided Compression in Step-by-step Efficient Reasoning

GroverGPT-2: Simulating Grover's Algorithm via Chain-of-Thought Reasoning and Quantum-Native Tokenization

Learning from Loss Landscape: Generalizable Mixed-Precision Quantization via Adaptive Sharpness-Aware Gradient Aligning

Federated Learning for Cyber Physical Systems: A Comprehensive Survey

Auto-regressive transformation for image alignment

D-CODA: Diffusion for Coordinated Dual-Arm Data Augmentation

PR2: Peephole Raw Pointer Rewriting with LLMs for Translating C to Safer Rust

Benchmarking LLM Faithfulness in RAG with Evolving Leaderboards

Threshold Crossings as Tail Events for Catastrophic AI Risk

Created by

Haebom

저자

Elija Perrier

개요

본 논문은 인공지능 시스템에서 분기(bifurcation)에 의한 급격한 변화가 극단적인(heavy-tailed) 결과 분포와 어떻게 관련되는지를 분석합니다. 특히, 제어 매개변수의 임계값 근처에서의 무작위 변동이 극단적인 결과를 생성하는 과정을 분석하여, 갑작스럽고 대규모의 전이 확률이 결과 손실 분포의 꼬리 확률과 얼마나 잘 일치하는지를 보여줍니다. 이 연구는 잠재적으로 치명적인 AI 위험을 관리하기 위한 AI 시스템의 모니터링, 완화 및 제어 연구에 기여합니다.

시사점, 한계점

•

시사점:

◦

AI 시스템의 급격한 변화(catastrophic transition)와 극단적인 결과 분포 간의 관계를 규명하여, AI 위험 관리에 대한 새로운 통찰력을 제공합니다.

◦

제어 매개변수의 작은 변화가 시스템에 큰 영향을 미칠 수 있음을 보여주어, AI 시스템 모니터링 및 제어의 중요성을 강조합니다.

◦

잠재적으로 치명적인 AI 위험을 관리하기 위한 새로운 모니터링 및 완화 전략 개발에 기여할 수 있습니다.

•

한계점:

◦

특정 유형의 AI 시스템 및 제어 매개변수에 대한 분석에 국한될 수 있습니다.

◦

실제 AI 시스템에 대한 실험적 검증이 부족할 수 있습니다.

◦

분석 결과를 실제 AI 위험 관리에 적용하는 방법에 대한 추가 연구가 필요합니다.

Made with Slashpage