Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
When Features Become Instances: Inverted Contrastive Learning for Unsupervised Feature Se…
arXiv cs.AI Research & Papers
Drift-Aware LLM Routing with Sparse Contexts and Shared Budgets
arXiv cs.AI Research & Papers
Text-guided flow matching enables sample-efficient crystal structure generation
arXiv cs.AI Research & Papers
Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets
arXiv cs.AI Research & Papers
Authority Bias in Conversational Search Engines for Academic Paper Recommendation
arXiv cs.AI Research & Papers
Provably Safe Sim-to-Real Transfer
arXiv cs.AI Research & Papers
A Stable Aggregation Method for Quantum Federated Learning
arXiv cs.AI Research & Papers
StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions
arXiv cs.AI Research & Papers
Embedded Conditional Independence Tests for Large Language Model Generated Text with an A…
arXiv cs.AI Research & Papers
Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and D…
arXiv cs.AI Research & Papers
Vision-Language-Guided Pseudo-Labels for Unsupervised Domain Adaptation in Semantic Segme…
arXiv cs.AI Research & Papers
Towards reliable multimodal disaster severity assessment through preference optimization …
arXiv cs.AI Research & Papers
A Checklist to assess the energy and carbon impacts of ML/AI applications in Earth System…
arXiv cs.AI Research & Papers
Analog-DB: An Agent-First Analog Integrated Circuit Database, From Blocks to Systems
arXiv cs.AI Research & Papers
Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant…
arXiv cs.AI Research & Papers
Semi-Supervised Virtual Staining via Morphology Preservation and Histopathological Realis…
arXiv cs.AI Research & Papers
Dr. Claw: An AI Scientist Workspace for Vibe Research
arXiv cs.AI Research & Papers
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
arXiv cs.AI Research & Papers
Don't Let the Model Write the YAML: Deterministic, Minimal-Diff GitOps Remediation from L…
arXiv cs.AI Research & Papers
Calibration is the Bottleneck: An Action-Class Diagnostic of Multi-Turn Tool-Calling
arXiv cs.AI Research & Papers
Same Request, Different Boundary: Evaluating Cybersecurity Assistance across Conversation…
arXiv cs.AI Models & Releases
Instella-MoE Technical Report
arXiv cs.AI Research & Papers
Asymmetries in Spontaneous and Instructed Deception
arXiv cs.AI Research & Papers
Solaris: Towards Interfaces That Are Generated, Not Coded
arXiv cs.AI Research & Papers
Attention Sensitivity Is Not Enough: Dissociating Attention-Level and Behavioural In-Cont…
arXiv cs.AI Research & Papers
Agentic programs: an emerging form of scientific software in computational materials scie…
arXiv cs.AI Research & Papers
EDRAC: Benchmarking Arabic Dialect Reading Comprehension
arXiv cs.AI Research & Papers
Visual Framing for News Stance Detection via Image Generation
arXiv cs.AI Research & Papers
A Study of Hidden-State Optimization Order in Predictive Coding Networks
arXiv cs.AI Research & Papers
Towards Effective Structured Context Modeling for Conversational Recommender Systems via …