Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Bridging the Semantic-Utility Gap in Multimodal RAG via Generator-in-the-Loop Alignment
arXiv cs.AI Security & Safety
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
arXiv cs.AI Research & Papers
When Can One Obtain Certificates of Optimality Using Positivstellensaetze?
arXiv cs.AI Research & Papers
Tensor network representations of discrete maximum entropy distributions via mean polytop…
arXiv cs.AI Research & Papers
WorldAgen: Unified State-Action Prediction with Test-Time World Model Training
arXiv cs.AI Research & Papers
Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering
arXiv cs.AI Research & Papers
RevalExo: A Functional Daily-Activity Benchmark for Inertial and Visual Locomotion Mode R…
arXiv cs.AI Research & Papers
OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?
arXiv cs.AI Research & Papers
Neptune: An AI model for Global Ocean Subseasonal Prediction
arXiv cs.AI Research & Papers
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video
arXiv cs.AI Research & Papers
A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM
arXiv cs.AI Research & Papers
IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multili…
arXiv cs.AI Research & Papers
CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning
arXiv cs.AI Research & Papers
Tracing Stereotypes from Representation to Output in Multilingual LLMs
arXiv cs.AI Research & Papers
A Layered Analysis of Disagreement And Answer Quality in Multi-Agent LLM Debate
arXiv cs.AI Research & Papers
ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Dele…
arXiv cs.AI Research & Papers
Inference-Time Nash Alignment
arXiv cs.AI Research & Papers
Closing the Consistency Gap: Self-Evolving Agents That Learn to Stay on Course
arXiv cs.AI Research & Papers
From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process Mining
arXiv cs.AI Research & Papers
Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case Study
arXiv cs.AI Research & Papers
From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI …
arXiv cs.AI Research & Papers
PRIMUS: Identity, Governance, and Verification for Multi-Agent Federations
arXiv cs.AI Research & Papers
Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Servi…
arXiv cs.AI Research & Papers
CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference Workflows
arXiv cs.AI Research & Papers
Support Topology and Gradient Mixing in Sinkhorn Layers
arXiv cs.AI Research & Papers
Automated Design of Inventory Policy with Large Language Models: An Exploratory Study
arXiv cs.AI Research & Papers
SkillAdam: Stable and Efficient Skill Evolution for Agents
arXiv cs.AI Research & Papers
Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Mat…
arXiv cs.AI Research & Papers
We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe Translation
arXiv cs.AI Research & Papers
Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliabi…