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
FedV-KGQA: Multi-Hop Question Answering over Vertically Partitioned Knowledge Graphs
arXiv cs.AI Research & Papers
CoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
arXiv cs.AI Research & Papers
From State to Action: OODA-Tool for Reliable Multi-Turn Tool Use
arXiv cs.AI Research & Papers
Method, Mind, and Morality: How People Make Sense of Artificial Intelligence
arXiv cs.AI Research & Papers
A Human-Factors Guided Cognitive Model of Visuospatial Complexity in Embodied Active Visi…
arXiv cs.AI Research & Papers
Ensemble of Convolutional Neural Networks for StrokePrediction: Towards Improved Diagnost…
arXiv cs.AI Research & Papers
Feedback That Backfires: Why Small Language Model Agents Repeat the Call They Just Watche…
arXiv cs.AI Research & Papers
Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation
arXiv cs.AI Research & Papers
Ad Insertion in LLM-Generated Responses
arXiv cs.AI Research & Papers
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
arXiv cs.AI Research & Papers
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Ba…
arXiv cs.AI Research & Papers
Discovering Adaptive Transmission Programs for Collective Innovation
arXiv cs.AI Research & Papers
ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory For…
arXiv cs.AI Research & Papers
Anytime Pretraining: Horizon-Free Learning-Rate Schedules with Weight Averaging
arXiv cs.AI Research & Papers
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
arXiv cs.AI Research & Papers
ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching
arXiv cs.AI Research & Papers
EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining an…
arXiv cs.AI Research & Papers
Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
arXiv cs.AI Research & Papers
CytoNet: A Foundation Model for the Human Cerebral Cortex at Cellular Resolution
arXiv cs.AI Research & Papers
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Le…
arXiv cs.AI Research & Papers
ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal
arXiv cs.AI Research & Papers
VGGT-DP: Generalizable Robot Control via Vision Foundation Models
arXiv cs.AI Research & Papers
VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference
arXiv cs.AI Research & Papers
msData: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Mod…
arXiv cs.AI Research & Papers
ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Hori…
arXiv cs.AI Research & Papers
ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Callin…
arXiv cs.AI Research & Papers
Towards Reproducibility in Predictive Process Mining: SPICE -- A Deep Learning Library
arXiv cs.AI Research & Papers
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understandi…
arXiv cs.AI Research & Papers
NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution
arXiv cs.AI Research & Papers
The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent Harnes…