Español

Explorar

Noticias de IA

27413 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
Fairness-Aware Mixture-of-Experts via Subgroup Reweighting and Gate Regularization
arXiv cs.AI Research & Papers
Enrich-Retrieve-Rank: Scaling Capability Discovery Beyond In-Context Routing
arXiv cs.AI Research & Papers
TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents
arXiv cs.AI Research & Papers
Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated Code
arXiv cs.AI Research & Papers
Hypergraph Embedding Indexing for Efficient Dense Vector Retrieval
arXiv cs.AI Research & Papers
SDoH-Aware Narrative Anchoring Bias in Medical LLMs for Trustworthy Clinical Decision Sup…
arXiv cs.AI Research & Papers
Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMs
arXiv cs.AI Research & Papers
Vision-Language Models for Occupational Physical Exposure Assessment: Estimating External…
arXiv cs.AI Research & Papers
Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted Programming
arXiv cs.AI Research & Papers
RACO: Reliability-Aware Coarse-Goal Optimization for Inspection-Oriented UAV Vision-Langu…
arXiv cs.AI Research & Papers
presto: Efficient, Training-free, and Open-world Object Placement via Imaginary Search
arXiv cs.AI Research & Papers
Length-Adaptive Decoding for Masked Diffusion Machine Translation
arXiv cs.AI Research & Papers
HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded …
arXiv cs.AI Research & Papers
STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Det…
arXiv cs.AI Research & Papers
Functional compatibility as a determinant of persistent neural learning
arXiv cs.AI Research & Papers
Pandora's AI Model Routing Box: Efficient Allocation with Costly Value Estimation
arXiv cs.AI Research & Papers
Multimodal examination answer data with expert-designed Outcome-Based Education rubrics f…
arXiv cs.AI Research & Papers
Hybrid Panels: Toward Human-AI Collaboration in Survey Research
arXiv cs.AI Research & Papers
Hierarchy-Aware Supervised Uncertainty Estimation for Black-box LLM Taxonomic Reasoning
arXiv cs.AI Research & Papers
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
arXiv cs.AI Research & Papers
TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders
arXiv cs.AI Research & Papers
SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models
arXiv cs.AI Research & Papers
LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT Model
arXiv cs.AI Research & Papers
Mitigating Reasoning-Induced Misalignment via Safety-Direction Penalty
arXiv cs.AI Research & Papers
The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action Prediction
arXiv cs.AI Research & Papers
FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain Generalization
arXiv cs.AI Research & Papers
LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
arXiv cs.AI Research & Papers
Training-Free VLM Personalization via Calibrated Residual Decoding
arXiv cs.AI Research & Papers
Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain Recordi…
arXiv cs.AI Research & Papers
Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quant…