Español

Explorar

Noticias de IA

30585 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
Cognivia: A Cognitive Behavioral Therapy Copilot for Evidence-Based Mental Healthcare
arXiv cs.AI Research & Papers
Extended Reality as a Mediation Layer for Situated Human Control in Human-Robot Teaming
arXiv cs.AI Research & Papers
DecoEvo: Score-Decoupled Co-Evolution of Solver and Rubric-Generator Skills in Text Space
arXiv cs.AI Research & Papers
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
arXiv cs.AI Research & Papers
CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization
arXiv cs.AI Research & Papers
OrchBench: Evaluating Multi-Agent Orchestration Plans in Isolation via Deterministic Simu…
arXiv cs.AI Research & Papers
Reinforcement Learning for Code Optimization
arXiv cs.AI Research & Papers
Stemma: Induced Decision Regions Reveal LLM Provenance
arXiv cs.AI Research & Papers
Device Invariance using Domain Adaptation on Acoustic Scene Classification
arXiv cs.AI Research & Papers
MemLens: A Value-Aware Memory Management System with Interactive Analytics for LLM-based …
arXiv cs.AI Research & Papers
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
arXiv cs.AI Research & Papers
JobMatchAI-An Intelligent Job Matching Platform Using Knowledge Graphs, Semantic Search a…
arXiv cs.AI Research & Papers
On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Revie…
arXiv cs.AI Research & Papers
COMPOL: A Unified Neural Operator Framework for Scalable Multi-Physics Simulations
arXiv cs.AI Research & Papers
"We'll have to see how it works": An interview study to understand collaborative practice…
arXiv cs.AI Research & Papers
From Execution to Capability: Scientific Experience Consolidation via Procedural Knowledg…
arXiv cs.AI Research & Papers
LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory
arXiv cs.AI Research & Papers
Where Steering Signals Come From: Activation Source Selection in Activation Steering
arXiv cs.AI Research & Papers
Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM…
arXiv cs.AI Research & Papers
Multiclass Classification without Labels via Posterior Simplex Geometry
arXiv cs.AI Research & Papers
Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution …
arXiv cs.AI Research & Papers
LLM-generated personalized nudges for improving pro-environmental behavior: Field evidenc…
arXiv cs.AI Research & Papers
Real-time Spatial Retrieval Augmented Generation for Urban Environments
arXiv cs.AI Research & Papers
Automated Numerical Stability Analysis of Deep Learning Operators
arXiv cs.AI Research & Papers
Shared Voxel-Map-Based Cooperative Indoor UAV Guidance with a Multi-Agent Soft Actor-Crit…
arXiv cs.AI Research & Papers
Grounded in Consensus, In Step With Emerging Science: A Consensus-Anchored Multi-Corpus C…
arXiv cs.AI Research & Papers
DDSNet: Dual-domain Symmetry-aware Network for PCSEL Property Prediction
arXiv cs.AI Research & Papers
Three Sides of Retrieval: Factorial Evidence for Document-Side, Query-Side, and Answer-Si…
arXiv cs.AI Research & Papers
Verification Without Distrust: Reframing User-Side Oversight as Routine Epistemic Governa…
arXiv cs.AI Research & Papers
AnnoBench: A Benchmark for Visualization Annotation Generation