Español

Explorar

Noticias de IA

37834 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
SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quali…
arXiv cs.AI Research & Papers
EffGen: Enabling Small Language Models as Capable Autonomous Agents
arXiv cs.AI Research & Papers
When RAG Hurts: Diagnosing and Mitigating Attention Distraction in Retrieval-Augmented LV…
arXiv cs.AI Research & Papers
Your Agent Has a Genome: Sequence-Level Behavioral Analysis and Runtime Governance of LLM…
arXiv cs.AI Research & Papers
Do we have the knowledge we need? Rethinking human-AI decision-making in corporations
arXiv cs.AI Research & Papers
Sustainable Materials Discovery in the Era of Artificial Intelligence
arXiv cs.AI Research & Papers
A Self Consistency Based Reranking for Narrative Question Answering
arXiv cs.AI Research & Papers
EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering …
arXiv cs.AI Research & Papers
FasterPy: An LLM-based Code Execution Efficiency Optimization Framework
arXiv cs.AI Research & Papers
RollArt: Disaggregated Multi-Task Agentic RL Training at Scale
arXiv cs.AI Research & Papers
Nightjar: Dynamic Adaptive Speculative Decoding for Large Language Models Serving
arXiv cs.AI Research & Papers
Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelin…
arXiv cs.AI Research & Papers
AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learning
arXiv cs.AI Research & Papers
CycliST: A Video Language Model Benchmark for Reasoning on Cyclical State Transitions
arXiv cs.AI Security & Safety
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query …
arXiv cs.AI Research & Papers
SPI: Query-Depth-Adaptive Indexing for Streaming RAG in Vector Databases
arXiv cs.AI Research & Papers
Can Artificial Intelligence Accelerate Technological Progress? Researchers' Perspectives …
arXiv cs.AI Research & Papers
Utility-Diversity Aware Online Batch Selection for LLM Supervised Fine-tuning
arXiv cs.AI Research & Papers
K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation Mo…
arXiv cs.AI Research & Papers
Minimal Oversight: Uncertainty-Aware Governance for Delegated AI Systems
arXiv cs.AI Research & Papers
Prototyping an AI-powered Tool for Energy Efficiency in New Zealand Homes
arXiv cs.AI Research & Papers
Skill-to-LoRA: From Using Skills to Learning Behaviors for Token-Efficient LLM Agents
arXiv cs.AI Research & Papers
Medical world models: representing medical states, modelling clinical dynamics and guidin…
arXiv cs.AI Research & Papers
User as Code: Executable Memory for Personalized Agents
arXiv cs.AI Research & Papers
Odds Law: The Decomposition Algebra On How Intelligence Organizes Itself to Solve Difficu…
arXiv cs.AI Research & Papers
When Generator Replay Degrades: Projected Rehearsal Orchestration for Heterogeneous Feder…
arXiv cs.AI Research & Papers
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
arXiv cs.AI Research & Papers
Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distrib…
arXiv cs.AI Research & Papers
Surprise-Guided MergeSort: Budget-Efficient Human-in-the-Loop Ranking via Adaptive Compar…
arXiv cs.AI Research & Papers
Token Reduction Should Go Beyond Efficiency in Generative Models -- From Vision, Language…