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
Lane Change Trajectory Planning for Personalized Driving Comfort and Mobility Efficiency
arXiv cs.AI Research & Papers
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
arXiv cs.AI Research & Papers
Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harn…
arXiv cs.AI Research & Papers
Learning to Execute Graph Algorithms Exactly with Graph Neural Networks
arXiv cs.AI Security & Safety
Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in L…
arXiv cs.AI Research & Papers
When Does Multi-Agent Collaboration Help? An Entropy Perspective
arXiv cs.AI Research & Papers
Trading Engagement for Sustainability: Carbon-Aware Re-ranking for E-commerce Recommendat…
arXiv cs.AI Research & Papers
D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion …
arXiv cs.AI Research & Papers
Model Context Protocols in Adaptive Transport Systems: A Survey
arXiv cs.AI Research & Papers
DualGate-Net: A Prior-Gated Dual-Encoder Framework for Histopathology Cell Detection
arXiv cs.AI Research & Papers
Telling stories, making Hanzi: AI-assisted co-creation with elderly migrants in urban Chi…
arXiv cs.AI Security & Safety
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
arXiv cs.AI Research & Papers
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
arXiv cs.AI Research & Papers
E2Former-V2: On-the-Fly Equivariant Attention with Linear Activation Memory
arXiv cs.AI Research & Papers
Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypi…
arXiv cs.AI Research & Papers
To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
arXiv cs.AI Research & Papers
Attention Consistent Longitudinal Medical Visual Question Answering Guided by Vision Foun…
arXiv cs.AI Research & Papers
The Fine-Tuning Trap: Evaluating Negative Transfer and the Role of PEFT in Sub-1B Mathema…
arXiv cs.AI Research & Papers
REMEDI: A Benchmark for Retention and Unlearning Evaluation in Multi-label Clinical Disea…
arXiv cs.AI Research & Papers
Attention-Guided Autoencoder Fusion for Insulator Defect Detection Using UAV Transmission…
arXiv cs.AI Research & Papers
Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local T…
arXiv cs.AI Research & Papers
RePo: Language Models with Context Re-Positioning
arXiv cs.AI Research & Papers
Measuring Agents in Production
arXiv cs.AI Research & Papers
P-Cast Precision in FP8 Attention: Sink-Induced Collapse and the Optimality of S=2^8
arXiv cs.AI Research & Papers
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
arXiv cs.AI Research & Papers
On the importance of multiple training seeds for evaluating machine unlearning
arXiv cs.AI Research & Papers
LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis
arXiv cs.AI Research & Papers
Queen-Bee Agents: A BeeSpec-Centered Architecture for Governed Enterprise MCP Orchestrati…
arXiv cs.AI Research & Papers
Didact: A Cross-Domain Capability Discovery System for Defence
arXiv cs.AI Research & Papers
MatterDoor: Sampling Zero-shot Spatio-semantic Priors using Generative Models