Español

Explorar

Noticias de IA

37834 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
Navigating the Alignment-Calibration Trade-off: A Pareto-Superior Frontier via Model Merg…
arXiv cs.AI Research & Papers
MedRepBench: A Comprehensive Benchmark for Medical Report Interpretation
arXiv cs.AI Security & Safety
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
arXiv cs.AI Research & Papers
Learning 3D-Gaussian Simulators from RGB Videos
arXiv cs.AI Research & Papers
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
arXiv cs.AI Research & Papers
Self-Gating Attention for Efficient Time Series Forecasting
arXiv cs.AI Research & Papers
Generalization in offline RL: The structure is more important than the amount of pessimism
arXiv cs.AI Research & Papers
Population-Based Multi-Objective Training of Discriminators for Semi-Supervised GANs
arXiv cs.AI Research & Papers
An Exploratory Study on LLM-Generated Code and Comments in Code Repositories
arXiv cs.AI Research & Papers
Decomposer: Learning to Decompile Symbolic Music to Programs
arXiv cs.AI Research & Papers
MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models
arXiv cs.AI Research & Papers
Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpreta…
arXiv cs.AI Research & Papers
Dynamic Neural Graph Encoding of Inference Processes in Deep Weight Space
arXiv cs.AI Research & Papers
ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning
arXiv cs.AI Research & Papers
Evolutionary Wave Function Collapse
arXiv cs.AI Research & Papers
OpenSafeIntent: Evaluating Intent-Calibrated Safe Completion Across Dual-Use Prompt Sets
arXiv cs.AI Research & Papers
Mirror Illusion Art
arXiv cs.AI Research & Papers
Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multige…
arXiv cs.AI Research & Papers
A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification
arXiv cs.AI Research & Papers
Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias
arXiv cs.AI Research & Papers
Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Pr…
arXiv cs.AI Research & Papers
NeoMap: Training-free Novel-View Synthesis from Single Images and Videos
arXiv cs.AI Research & Papers
Challenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resou…
arXiv cs.AI Research & Papers
CoFL-S: Spatially Queryable Sector Flow Fields for Local Language-Conditioned Navigation
arXiv cs.AI Research & Papers
What Types of Human-AI Teams Exist?
arXiv cs.AI Research & Papers
Scene-Conditioned PINN-GNN for Multipath RF Maps: Cross-Scene Generation and In-Scene Com…
arXiv cs.AI Research & Papers
AI Virtue: What is "Good" Knowledge in the Age of Artificial Intelligence?
arXiv cs.AI Research & Papers
Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nons…
arXiv cs.AI Research & Papers
Full Bayesian Reinforcement Learning via LF-IBIS
arXiv cs.AI Research & Papers
Model Merging as Probabilistic Inference in Fine-Tuning Parameter Space