Español

Explorar

Noticias de IA

21031 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
Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
arXiv cs.AI Research & Papers
Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversi…
arXiv cs.AI Research & Papers
C2L-Net: A Data-Driven Model for State-of-Charge Estimation of Lithium-Ion Batteries Duri…
arXiv cs.AI Research & Papers
Time Present and Time Past: Benchmarking Large Language Models on Temporally Evolving Doc…
arXiv cs.AI Research & Papers
Evidence-RL: Towards Evidence-intensive Visual Reasoning
arXiv cs.AI Research & Papers
Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Wa…
arXiv cs.AI Research & Papers
EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference
arXiv cs.AI Research & Papers
MathShikkha: A Controlled Study of Answer-Only and Chain-of-Thought Supervision for Bangl…
arXiv cs.AI Research & Papers
Thinking Hard, Not Smart: Reasoning Models Fail to Ration Test-Time Compute Across Questi…
arXiv cs.AI Research & Papers
iLTM: Integrated Large Tabular Model
arXiv cs.AI Research & Papers
Private Anytime Selective-Risk Certification for Federated Retrieval-Augmented Generation…
arXiv cs.AI Research & Papers
ScaleSense: Cost-Intelligent Scaling Framework via Learned Resource Estimation in Alibaba…
arXiv cs.AI Research & Papers
TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
arXiv cs.AI Research & Papers
Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States
arXiv cs.AI Research & Papers
FoMoH: A clinically meaningful foundation model evaluation for structured electronic heal…
arXiv cs.AI Research & Papers
Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence
arXiv cs.AI Research & Papers
Vision-Language Grounding as Bidirectional Concept Correspondence
arXiv cs.AI Research & Papers
The Anatomy of a Prompt Injection: A Component Model for Structured Analysis
arXiv cs.AI Research & Papers
Efficient Cross-View Localization in 6G Space-Air-Ground Integrated Network
arXiv cs.AI Research & Papers
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
arXiv cs.AI Research & Papers
Tabular Numeric Stretch Transformation
arXiv cs.AI Research & Papers
Router Sensitivity Under Lightweight Fine-Tuning Identifies Prunable Experts in Mixture-o…
arXiv cs.AI Research & Papers
On the Robustness of LLMs' Internal Representation of Code Correctness
arXiv cs.AI Research & Papers
Spectral Outliers Reveal Dominant Learned Structure in Transformer Attention
arXiv cs.AI Research & Papers
Ouroboros: A Self-Developing Frontier Coding Agent with Reviewed Core Evolution
arXiv cs.AI Research & Papers
Shape Mutating Expert Compression:LorExperts and BTExperts
arXiv cs.AI Research & Papers
LoRSA: Toward Generalizable Parameter-Efficient Fine-Tuning for Biomedical Downstream Tas…
arXiv cs.AI Research & Papers
CFD-Guided Detection of Concept Drift in Multimodal Physiologic Signals
arXiv cs.AI Research & Papers
Distilling CT Foundation Models into Editable Concept Bottlenecks for Lung Nodule Maligna…
arXiv cs.AI Research & Papers
HugSelect: An Explainable Multi-Criteria Decision-Support Framework for foundation-model …