Español

Explorar

Noticias de IA

30637 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
Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
arXiv cs.AI Research & Papers
AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems
arXiv cs.AI Research & Papers
Probing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoenco…
arXiv cs.AI Research & Papers
AI4PLE: A Methodology for Integrating AI into Product Line Engineering
arXiv cs.AI Research & Papers
A Roadmap to Impactful Pluralistic Alignment Research
arXiv cs.AI Research & Papers
Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforce…
arXiv cs.AI Research & Papers
Reasoning Denoiser: Denoising Reasoning Traces for Hallucination Detection in Large Reaso…
arXiv cs.AI Research & Papers
Industrial Tokenization for LLM-Based Health Intelligence: A Federated Architecture for I…
arXiv cs.AI Research & Papers
Learning on the Job: Continual Learning from Deployment Feedback for Frozen-Weights Agents
arXiv cs.AI Research & Papers
Multi-Agent System-driven Digital Twins for predictive maintenance: architectures, techno…
arXiv cs.AI Research & Papers
TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized…
arXiv cs.AI Research & Papers
Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement…
arXiv cs.AI Research & Papers
When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual…
arXiv cs.AI Research & Papers
Semiotic logical hexagon theory for LLM logical reasoning
arXiv cs.AI Research & Papers
DAGForge: Auditable Causal DAG Authoring with Biomedical Literature
arXiv cs.AI Research & Papers
Co-design of LLM-based preference agents: participation may drive overtrust
arXiv cs.AI Research & Papers
What AI Red-Team Evaluations Can and Cannot Prove
arXiv cs.AI Research & Papers
From Seasonality to Semantics: Benchmarking a Hybrid Probabilistic Forecasting System for…
arXiv cs.AI Research & Papers
QLPO: Quadrant-weighted Sampling for Length-aware Policy Optimization
arXiv cs.AI Research & Papers
Persistent Computational State: A Session-Centric Runtime for Generative World Models
arXiv cs.AI Research & Papers
FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs
arXiv cs.AI Research & Papers
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
arXiv cs.AI Research & Papers
Trajectory-Aware Retrieval Agents for Temporal Decision- Making
arXiv cs.AI Research & Papers
Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translat…
arXiv cs.AI Research & Papers
Lost in Context: Addressing Context Anxiety in Large Language Models
arXiv cs.AI Research & Papers
Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models
arXiv cs.AI Research & Papers
FrED: External Data Influence Estimation via Domain Knowledge Graph Grounding
arXiv cs.AI Research & Papers
LeafData: An Agentic System for Data Migration
arXiv cs.AI Research & Papers
Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code
arXiv cs.AI Research & Papers
Discrete Action Space as a Prerequisite for GRPO Convergence in Small-Model Continuous Co…