Español

Explorar

Noticias de IA

22104 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
WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing
arXiv cs.AI Research & Papers
Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward …
arXiv cs.AI Research & Papers
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Resear…
arXiv cs.AI Research & Papers
Evaluation Cards: An Interpretive Layer for AI Evaluation Reporting
arXiv cs.AI Research & Papers
BRAIN: Bayesian Reasoning via Active Inference for Agentic and Embodied Intelligence in M…
arXiv cs.AI Research & Papers
From `May' to `Is': Certainty Distortion in Language Model Rewriting
arXiv cs.AI Research & Papers
Bidirectional Small-Granularity Search between Code and Text
arXiv cs.AI Research & Papers
ABLE: Representing and Mapping LLMs via Attribution-Based Large-model Embedding
arXiv cs.AI Research & Papers
Post-training is (Massive) Supervised Learning
arXiv cs.AI Research & Papers
mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Langua…
arXiv cs.AI Research & Papers
Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Langua…
arXiv cs.AI Research & Papers
Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable…
arXiv cs.AI Research & Papers
Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects
arXiv cs.AI Research & Papers
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Effici…
arXiv cs.AI Research & Papers
Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models
arXiv cs.AI Research & Papers
Quantum-Enhanced Similarity Measures for Polarimetric Materials Classification
arXiv cs.AI Research & Papers
Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retriev…
arXiv cs.AI Research & Papers
Summarization is Not Dead Yet
arXiv cs.AI Research & Papers
Human-Centered Benchmarking of Driver Monitoring Models
arXiv cs.AI Research & Papers
Few-shot Class-variable Incremental Audio Classification via Prototype Adaptation and Pse…
arXiv cs.AI Research & Papers
Constrained Paraphrase Consistency for LLM Hallucination Detection
arXiv cs.AI Research & Papers
CLASP: Language-Driven Robot Skill Selection and Composition using Task-Parameterized Lea…
arXiv cs.AI Research & Papers
GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large A…
arXiv cs.AI Research & Papers
How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Composition…
arXiv cs.AI Research & Papers
More Yap Less Meaning: Uncovering Self-Improvement Behavior in SLMs
arXiv cs.AI Research & Papers
TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medi…
arXiv cs.AI Research & Papers
Failure-Aware Refinement of Vision-Language Model for Lithography Defect Detection
arXiv cs.AI Research & Papers
PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detecti…
arXiv cs.AI Research & Papers
PACT: Learning Diverse Diagnostic Strategies via Privileged Synthesis and Branch Consensus
arXiv cs.AI Research & Papers
NutriMLLM: Multimodal Large Language Models for Dietary Micronutrient Analysis