Español

Explorar

Noticias de IA

30308 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
Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-…
arXiv cs.AI Research & Papers
ADWIN: Adaptive Windows for Horizon-Aware On-Policy Distillation
arXiv cs.AI Research & Papers
BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classif…
arXiv cs.AI Research & Papers
Functional Entropy: Predicting Functional Correctness in LLM-Generated Code with Uncertai…
arXiv cs.AI Research & Papers
The Principles of Diffusion Models
arXiv cs.AI Research & Papers
EAGer: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling
arXiv cs.AI Research & Papers
Visualizing Latent Phase Structures in Locomotion Policies: A Multi-Environment Study wit…
arXiv cs.AI Research & Papers
Do LLMs Favor Their Providers? Measuring Vertical Integration Bias in Code Generation
arXiv cs.AI Research & Papers
Token Optimization Strategies for LLM-Based Oracle-to-PostgreSQL Migration
arXiv cs.AI Research & Papers
SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for…
arXiv cs.AI Security & Safety
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding Agents
arXiv cs.AI Research & Papers
Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Sy…
arXiv cs.AI Security & Safety
MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Conte…
arXiv cs.AI Research & Papers
Online Irregular Multivariate Time Series Forecasting via Uncertainty-Driven Dual-Expert …
arXiv cs.AI Research & Papers
Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images
arXiv cs.AI Research & Papers
Beyond Binary Moral Judgment: Modeling Ethical Pluralism in AI
arXiv cs.AI Research & Papers
PromptEmbedder:: Efficient and Transferable Text Embedding via Dual-LLM Soft Prompting
arXiv cs.AI Research & Papers
On the Learnability of Test-Time Adaptation: A Recovery Complexity Perspective
arXiv cs.AI Research & Papers
Multi-Adapter Representation Interventions via Energy Calibration
arXiv cs.AI Research & Papers
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
arXiv cs.AI Research & Papers
Integrated and Cross-Architecture Interpretation of LLM Reasoning
arXiv cs.AI Research & Papers
Calibrating Conservatism for Scalable Oversight
arXiv cs.AI Research & Papers
Where Does Toxicity Live? Mechanistic Localization and Targeted Suppression in Language M…
arXiv cs.AI Research & Papers
RAG-Coding: Enhancing LLM Medical Coding with Structured External Knowledge
arXiv cs.AI Research & Papers
FD-RAG: Federated Dual-System Retrieval-Augmented Generation
arXiv cs.AI Research & Papers
When NPUs Are Not Always Faster: A Stage-Level Analysis of Mobile LLM Inference
arXiv cs.AI Research & Papers
Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Repro…
arXiv cs.AI Research & Papers
A Systematic Evaluation of Retrieval-Augmented Generation and Language Models for Space O…
arXiv cs.AI Research & Papers
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration…
arXiv cs.AI Research & Papers
Cross-Entropy Games and Frost Training