haebom
Sign In
Daily Arxiv
世界中で発行される人工知能関連の論文をまとめるページです。
このページはGoogle Geminiを活用して要約し、非営利で運営しています。
論文の著作権は著者および関連機関にあり、共有する際は出典を明記してください。
WRAP++: Web discoveRy Amplified Pretraining
The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?
Blockchain and AI: Securing Intelligent Networks for the Future
Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook
DQA: Diagnostic Question Answering for IT Support
Training Transformers in Cosine Coefficient Space
Justified or Just Convincing? Error Verifiability as a Dimension of LLM Quality
Parent Selection Mechanisms in Elitist Crossover-Based Algorithms
Quantum-Inspired Geometric Classification with Correlation Group Structures and VQC Decision Modeling
Continued AI Scaling Requires Repeated Efficiency Doublings
TBayes-MICE: A Bayesian Approach to Multiple Imputation for Time Series Data
MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
HiCI: Hierarchical Construction-Integration for Long-Context Attention
WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior
Quine: Realizing LLM Agents as Native POSIX Processes
BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
OrgForge: A Multi-Agent Simulation Framework for Verifiable Synthetic Corporate Corpora
Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Diagnostic Reasoning
Learning to Negotiate: Multi-Agent Deliberation for Collective Value Alignment in LLMs
Hardware Efficient Approximate Convolution with Tunable Error Tolerance for CNNs
Reinforced Generation of Combinatorial Structures: Ramsey Numbers
Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark
Stacked from One: Multi-Scale Self-Injection for Context Window Extension
ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails
SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses
Interpretable Tau-PET Synthesis from Multimodal T1-Weighted and FLAIR MRI Using Partial Information Decomposition Guided Disentangled Quantized Half-UNet
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
AI-PACE: A Framework for Integrating AI into Medical Education
Rethinking the Value of Agent-Generated Tests for LLM-Based Software Engineering Agents
PANC: Prior-Aware Normalized Cut via Anchor-Augmented Token Graphs
SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
Adversarial Evasion Attacks on Computer Vision using SHAP Values
DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs
Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models
TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL
ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation
Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis
RDSplat: Robust Watermarking for 3D Gaussian Splatting Against 2D and 3D Diffusion Editing
Human-computer interactions predict mental health
Action Without Interaction: Probing the Physical Foundations of Video LMMs via Contact-Release Detection
NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields
Evaluating Low-Light Image Enhancement Across Multiple Intensity Levels
The Persistence of Cultural Memory: Investigating Multimodal Iconicity in Diffusion Models
How Do Data Owners Say No? A Case Study of Data Consent Mechanisms in Web-Scraped Vision-Language AI Training Datasets
ATLAS: Adaptive Trading with LLM AgentS Through Dynamic Prompt Optimization and Multi-Agent Coordination
Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software
E2Edev: Benchmarking Large Language Models in End-to-End Software Development Task
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection
CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs
Fast and Interpretable Protein Substructure Alignment via Optimal Transport
Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
Search-R3: Unifying Reasoning and Embedding in Large Language Models
SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
AudioMoG: Guiding Audio Generation with Mixture-of-Guidance
MARCH: Evaluating the Intersection of Ambiguity Interpretation and Multi-hop Inference
Diffusion Language Models Know the Answer Before Decoding
Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
Mitigating Domain Drift in Multi Species Segmentation with DINOv2: A Cross-Domain Evaluation in Herbicide Research Trials
Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
Part$^{2}$GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting
BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook
"I Said Things I Needed to Hear Myself": Peer Support as an Emotional, Organisational, and Sociotechnical Practice in Singapore
"Is This Really a Human Peer Supporter?": Misalignments Between Peer Supporters and Experts in LLM-Supported Interactions
Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
Employing Deep Neural Operators for PDE control by decoupling training and optimization
SpecBranch: Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism
SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
RQR3D: Reparametrizing the regression targets for BEV-based 3D object detection
LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
Are Sparse Autoencoders Useful for Java Function Bug Detection?
ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation
Distilling Specialized Orders for Visual Generation
OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research
スプリット! Flexible Sociocultural Linguistic Investigation at Scale
Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios
Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding
RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
Transforming the Voice of the Customer: Large Language Models for Identifying Customer Needs
$\Texttt{SEM-CTRL}$: Semantically Controlled Decoding
OpenGLT: A Comprehensive Benchmark of Graph Neural Networks for Graph-Level Tasks
MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
DMin: Scalable Training Data Influence Estimation for Diffusion Models
AdaProb: Efficient Machine Unlearning via Adaptive Probability
A systematic framework for generating novel experimental hypotheses from language models
Causal Discovery in Linear Models with Unobserved Variables and Measurement Error
Seeing Like an AI: How LLMs Apply (and Misapply) Wikipedia Neutrality Norms
NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks
NaviSplit: Dynamic Multi-Branch Split DNNs for Efficient Distributed Autonomous Navigation
MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data
Improving Image Coding for Machines through Optimizing Encoder via Auxiliary Loss
An Automated Survey of Generative Artificial Intelligence: Large Language Models, Architectures, Protocols, and Applications
Tractable Uncertainty-Aware Meta-Learning
Why we need an AI-resilient society
Load more
Made with Slashpage