Explorar

Noticias de IA

30934 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
RUFNet: Query-Guided Support Mask Refinement and Uncertainty Fusion based on Hybrid Mamba…
arXiv cs.AI Security & Safety
Agent Data Injection Attacks are Realistic Threats to AI Agents
arXiv cs.AI Research & Papers
Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Mode…
arXiv cs.AI Research & Papers
Evaluating Generative Agents with Actions Grounded in Socially Distributed Task Environme…
arXiv cs.AI Models & Releases
Unified Audio Intelligence Without Regressing on Text Intelligence
arXiv cs.AI Research & Papers
A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent P…
arXiv cs.AI Research & Papers
Simple-to-Complex Structured Demonstrations for Vision-Language-Action Learning
arXiv cs.AI Research & Papers
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-…
arXiv cs.AI Research & Papers
SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing
arXiv cs.AI Research & Papers
Multi-Turn On-Policy Distillation with Prefix Replay
arXiv cs.AI Research & Papers
Machine Learning for Depression Screening and Intervention: an Original Circadian Rhythm …
arXiv cs.AI Research & Papers
Privacy-Preserving Robustness Verification for Neural Networks
arXiv cs.AI Research & Papers
Shifting from Discrete to Continuous Reference Data: QSM-Derived Horizontal Tree Biomass …
arXiv cs.AI Research & Papers
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Dist…
arXiv cs.AI Research & Papers
URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment
arXiv cs.AI Research & Papers
Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards
arXiv cs.AI Research & Papers
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
arXiv cs.AI Research & Papers
Predicting Drafted Deck Strength for "Magic: the Gathering"
arXiv cs.AI Research & Papers
Pretraining Curricula Enable Selective Fine-tuning
arXiv cs.AI Research & Papers
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language…
arXiv cs.AI Research & Papers
From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
arXiv cs.AI Research & Papers
LLM for the development of FCM
arXiv cs.AI Research & Papers
The Map Behind the Flow: Finite-Step Gradient Descent as a Dynamical System
arXiv cs.AI Research & Papers
Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation…
arXiv cs.AI Research & Papers
ImputeECG: Deep Learning Reconstruction of Complete 12-Lead Electrocardiograms from Incom…
arXiv cs.AI Research & Papers
Insect-inspired Visual Point-goal Navigation
arXiv cs.AI Research & Papers
Serious Games: Human-AI Interaction, Evolution, and Coevolution
arXiv cs.AI Research & Papers
Policy Improvement with Style-Specific Demonstrations
arXiv cs.AI Research & Papers
Correlation-Weighted Multi-Reward Optimization for Compositional Generation
arXiv cs.AI Research & Papers
Evolutionary Guided Decoding: Iterative Value Refinement for LLMs