Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event Cameras
arXiv cs.AI Research & Papers
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persi…
arXiv cs.AI Research & Papers
Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portugue…
arXiv cs.AI Research & Papers
From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation Models
arXiv cs.AI Research & Papers
Constrained Online Learning with Noisy Constraint Values
arXiv cs.AI Research & Papers
Steering Interference Reflects the Model's Defaults, Not the Behavior Directions
arXiv cs.AI Research & Papers
MEMOBench: A Process Level Memory Benchmark for Robotic Manipulation
arXiv cs.AI Research & Papers
Leveraging Cardiac Imaging to Improve ECG-Based Detection of Chagas Disease in Resource-C…
arXiv cs.AI Research & Papers
You Are What You Read: Misalignment via In-Context Persona Induction
arXiv cs.AI Research & Papers
MVFA: A Multi-View Text-Guided Multimodal Fusion LLM Adapter for Sentiment Analysis and E…
arXiv cs.AI Research & Papers
Procedural Graphs: Self-Evolving Execution Structures for LLM Agents
arXiv cs.AI Research & Papers
Data-driven rational function neural networks: a new method for generating analytical mod…
arXiv cs.AI Research & Papers
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
arXiv cs.AI Research & Papers
ProToMEx: Rapid, Interpretable Explanations via Structured Representations
arXiv cs.AI Research & Papers
Novel Methods for Catheter and Guidewire Segmentation in X-ray Fluoroscopy under a Federa…
arXiv cs.AI Research & Papers
XYBench: Can LLMs Respond Pragmatically to Queries with Misconceptions?
arXiv cs.AI Research & Papers
AutoLexSteer: Automatic Contrast Construction for Lexical Activation Steering
arXiv cs.AI Research & Papers
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
arXiv cs.AI Research & Papers
Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval
arXiv cs.AI Research & Papers
Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval
arXiv cs.AI Research & Papers
DrugReason: Dynamic Multi-View Reasoning over Knowledge Graph and Language Evidence for D…
arXiv cs.AI Research & Papers
AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genr…
arXiv cs.AI Research & Papers
Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction
arXiv cs.AI Research & Papers
Companion-style QA Assistance in Ego-Vision
arXiv cs.AI Research & Papers
Attention-Enhanced Deep Features with Heterogeneous Ensemble Learning for Glaucoma Detect…
arXiv cs.AI Research & Papers
ECOKV: Geometry-Aware KV Cache Eviction via Complementary Diversity Metrics
arXiv cs.AI Research & Papers
Counterfactual Tests for Measuring Chain-of-Thought Faithfulness in Visual Language Models
arXiv cs.AI Research & Papers
Assessing Covariate-Informed Grid Load Forecasting with a Time-Series Foundation Model
arXiv cs.AI Research & Papers
FSAN: Flow State Attention Network for Aerodynamic Prediction
arXiv cs.AI Research & Papers
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content