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.

EvalMORAAL: Interpretable Chain-of-Thought and LLM-as-Judge Evaluation for Moral Alignment in Large Language Models

DACP: Domain-Adaptive Continual Pre-Training of Large Language Models for Phone Conversation Summarization

AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models

Progressive Gaussian Transformer with Anisotropy-aware Sampling for Open Vocabulary Occupancy Prediction

A Calibration-Free Fixed Point of Curved Boolean Logic Matching the Fine-Structure Constant

Epistemic Diversity and Knowledge Collapse in Large Language Models

PolyKAN: A Polyhedral Analysis Framework for Provable and Approximately Optimal KAN Compression

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

Longitudinal Flow Matching for Trajectory Modeling

Platonic Transformers: A Solid Choice For Equivariance

Unified Unsupervised Anomaly Detection via Matching Cost Filtering

Decipher the Modality Gap in Multimodal Contrastive Learning: From Convergent Representations to Pairwise Alignment

Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout

Spiral of Silence in Large Language Model Agents

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization

Autonomy-Aware Clustering: When Local Decisions Supersede Global Prescriptions

GPS-MTM: Capturing Pattern of Normalcy in GPS-Trajectories with self-supervised learning

PARL-MT: Learning to Call Functions in Multi-Turn Conversation with Progress Awareness

GRPO is Secretly a Process Reward Model

When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity

The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathology

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

SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models

TextMine: Data, Evaluation Framework and Ontology-guided LLM Pipeline for Humanitarian Mine Action

Intelligent Healthcare Imaging Platform: A VLM-Based Framework for Automated Medical Image Analysis and Clinical Report Generation

Sustainable LSTM-Based Precoding for RIS-Aided mmWave MIMO Systems with Implicit CSI

A Minimalist Bayesian Framework for Stochastic Optimization

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction

SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models

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

Community-Centered Spatial Intelligence for Climate Adaptation at Nova Scotia's Eastern Shore

Grounding the Ungrounded: A Spectral-Graph Framework for Quantifying Hallucinations in Multimodal LLMs

Membership Inference Attacks on LLM-based Recommender Systems

Consistent Opponent Modeling of Static Opponents in Imperfect-Information Games

On Task Vectors and Gradients

Enhancing GraphQL Security by Detecting Malicious Queries Using Large Language Models, Sentence Transformers, and Convolutional Neural Networks

Interpretable Robot Control via Structured Behavior Trees and Large Language Models

An Investigation of Robustness of LLMs in Mathematical Reasoning: Benchmarking with Mathematically-Equivalent Transformation of Advanced Mathematical Problems

Valid Inference with Imperfect Synthetic Data

Quasi-Clique Discovery via Energy Diffusion

CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment

ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation

GIIFT: Graph-guided Inductive Image-free Multimodal Machine Translation

Quantum Machine Learning in Multi-Qubit Phase-Space Part I: Foundations

Token-based Audio Inpainting via Discrete Diffusion

Enjoying Non-linearity in Multinomial Logistic Bandits

Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Network with Group Lasso Regularization

Real-Time Progress Prediction in Reasoning Language Models

Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories

Context Matters! Relaxing Goals with LLMs for Feasible 3D Scene Planning

Prefilled responses enhance zero-shot detection of AI-generated images

AutoMind: Adaptive Knowledgeable Agent for Automated Data Science

KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes

Learning to Recover: Dynamic Reward Shaping with Wheel-Leg Coordination for Fallen Robots

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale

Exchangeability in Neural Network and its Application to Dynamic Pruning

InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoning

Performance of machine-learning-assisted Monte Carlo in sampling from simple statistical physics models

The Unreasonable Effectiveness of Model Merging for Cross-Lingual Transfer in LLMs

FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models

SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

MoRE-Brain: Routed Mixture of Experts for Interpretable and Generalizable Cross-Subject fMRI Visual Decoding

AdaDim: Dimensionality Adaptation for SSL Representational Dynamics

AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs

MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices

Generative Pre-trained Autoregressive Diffusion Transformer

Efficient Flow Matching using Latent Variables

Weight Ensembling Improves Reasoning in Language Models

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

Optimizing Breast Cancer Detection in Mammograms: A Comprehensive Study of Transfer Learning, Resolution Reduction, and Multi-View Classification

NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks

Mitigating Cross-Modal Distraction and Ensuring Geometric Feasibility via Affordance-Guided and Self-Consistent MLLMs for Task Planning in Instruction-Following Manipulation

Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RL

Mind the (Belief) Gap: Group Identity in the World of LLMs

Lossy Neural Compression for Geospatial Analytics: A Review

MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks

LLM Unlearning via Neural Activation Redirection

Achieving Hyperbolic-Like Expressiveness with Arbitrary Euclidean Regions: A New Approach to Hierarchical Embeddings

A Dual-Agent Adversarial Framework for Robust Generalization in Deep Reinforcement Learning

FedAGHN: Personalized Federated Learning with Attentive Graph HyperNetworks

Generative AI for Cel-Animation: A Survey

Tempo: Compiled Dynamic Deep Learning with Symbolic Dependence Graphs

KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving

Towards a Multimodal Large Language Model with Pixel-Level Insight for Biomedicine

Evil twins are not that evil: Qualitative insights into machine-generated prompts

Sustainable Self-evolution Adversarial Training

Machine Learning and Multi-source Remote Sensing in Forest Aboveground Biomass Estimation: A Review

VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?

SuffixDecoding: Extreme Speculative Decoding for Emerging AI Applications

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs

NAR-*ICP: Neural Execution of Classical ICP-based Pointcloud Registration Algorithms

Approximately Aligned Decoding

Interpretable Clustering: A Survey

A Deep Learning System for Rapid and Accurate Warning of Acute Aortic Syndrome on Non-contrast CT in China

V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning

Empowering LLMs with Pseudo-Untrimmed Videos for Audio-Visual Temporal Understanding

ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent

Unlocking Dataset Distillation with Diffusion Models

Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometrics

Made with Slashpage