Español

Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion
arXiv cs.AI Research & Papers
Path-Lock Expert: Separating Reasoning Mode in Hybrid Thinking via Architecture-Level Sep…
arXiv cs.AI Research & Papers
Culturally Situated AI Safety for Youth: Saudi Arabian Perspectives of Youth, Parents and…
arXiv cs.AI Research & Papers
SafeSceneReason: A Multimodal Reasoning Benchmark Connecting Industrial Hazards with Acci…
arXiv cs.AI Research & Papers
From Local to Cluster: A Unified Framework for Causal Discovery with Latent Variables
arXiv cs.AI Research & Papers
Hybrid Policy Distillation for LLMs
arXiv cs.AI Research & Papers
SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance
arXiv cs.AI Research & Papers
Controllable Video Object Insertion via Multi-View Priors
arXiv cs.AI Research & Papers
Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning
arXiv cs.AI Research & Papers
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
arXiv cs.AI Research & Papers
Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
arXiv cs.AI Research & Papers
Weather- and Location-Aware Agentic Dining Recommendation: Leveraging LLM World Knowledge…
arXiv cs.AI Research & Papers
Entropy-based Code Adversarial Translation for Real-world Repository Migration
arXiv cs.AI Research & Papers
Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Lo…
arXiv cs.AI Research & Papers
Open-World Semantic Segmentation with Sensitivity Modeling
arXiv cs.AI Research & Papers
P$^{3}$: Joint Program-and-Proof Planning for Verified Code Generation
arXiv cs.AI Research & Papers
MMArch: Benchmarking Multimodal Reasoning Grounded in Architectural Evidence
arXiv cs.AI Research & Papers
Enhanced Real-Time 6-DOF Extended Reality Catheter Tracking for Evaluating Potential Impr…
arXiv cs.AI Research & Papers
A foundation model of numerical intelligence with cross-disciplinary generalization
arXiv cs.AI Research & Papers
ConMem: Contribution-Aware Memory for Long-Horizon Manufacturing Inspection Logs
arXiv cs.AI Research & Papers
A Minimal $\kappa$--$\tau$ Logic for Risk-Sensitive Abduction
arXiv cs.AI Research & Papers
Hit Selection Using SSMD-Based Machine Learning Performance Metrics in High-Throughput Sc…
arXiv cs.AI Research & Papers
MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts
arXiv cs.AI Research & Papers
SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL
arXiv cs.AI Research & Papers
Frequency-Domain Dual-Branch Fusion for Medical Visual Question Answering
arXiv cs.AI Research & Papers
Do Evaluation Metrics Detect Errors in Classical Chinese to English Translations?
arXiv cs.AI Research & Papers
Layerwise goal-oriented adaptivity for neural ODEs: an optimal control perspective
arXiv cs.AI Research & Papers
Linearized 2-Simplicial Attention
arXiv cs.AI Research & Papers
A Unified Issue Resolution Benchmark for Requirement Clarification, Planning, and Code Ge…
arXiv cs.AI Research & Papers
When Confidence Fails: Overconfidence in LLMs under Uncertainty and Missing Clinical Info…