Español

Explorar

Noticias de IA

30329 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
Enhanced Evolutionary Multi-Objective Deep Reinforcement Learning for Reliable and Effici…
arXiv cs.AI Research & Papers
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
arXiv cs.AI Research & Papers
LiveStarPro: Proactive Streaming Video Understanding with Hierarchical Memory for Long-Ho…
arXiv cs.AI Research & Papers
A Neuromorphic Trigger for Efficient Audio Event Detection
arXiv cs.AI Research & Papers
Structured Adversarial Camouflage via Voronoi Diagrams
arXiv cs.AI Research & Papers
Vision-language models for chest radiography do not always need the image
arXiv cs.AI Research & Papers
MemTrace: Probing What Final Accuracy Misses in Long-Term Memory
arXiv cs.AI Research & Papers
SegTME-UNI2: A Foundation Model-Based Framework for Generalisable Multiclass Cell Segment…
arXiv cs.AI Research & Papers
SuCo: Sufficiency-guided Continuous Adaptive Reasoning
arXiv cs.AI Research & Papers
See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL
arXiv cs.AI Research & Papers
ASTEROID: A Spatiotemporal Information Transformer for Forecasting Multi-Step Time Series…
arXiv cs.AI Research & Papers
TuneAhead: Predicting Fine-tuning Performance Before Full Training Begins
arXiv cs.AI Research & Papers
When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-Like…
arXiv cs.AI Research & Papers
Correct When Paired, Wrong When Split: Decoupling and Editing Modality-Specific Neurons i…
arXiv cs.AI Research & Papers
A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction
arXiv cs.AI Research & Papers
SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches
arXiv cs.AI Research & Papers
Bounding Box Label Propagation for Re-Annotation of Document Layout Analysis Datasets
arXiv cs.AI Research & Papers
LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks
arXiv cs.AI Research & Papers
Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imag…
arXiv cs.AI Research & Papers
SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-Vie…
arXiv cs.AI Research & Papers
PIVOT: Bridging Black-Scholes Implied-Volatility and Price Objectives via Differentiable …
arXiv cs.AI Research & Papers
Towards Distributed Inference of LLMs on a P2P Network
arXiv cs.AI Research & Papers
The Stanford EDGAR Filings Dataset: Reconstructing U.S. Corporate and Financial Disclosur…
arXiv cs.AI Research & Papers
Offline Preference-Based Trajectory Evaluation
arXiv cs.AI Research & Papers
Reinforcing Dual-Path Reasoning in Spatial Vision Language Models
arXiv cs.AI Research & Papers
OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compressio…
arXiv cs.AI Research & Papers
Scaling Enterprise Agent Routing: Degradation, Diagnosis, and Recovery
arXiv cs.AI Research & Papers
Unlocking LLM Code Correction with Iterative Feedback Loops
arXiv cs.AI Research & Papers
Geometry-Aware Post-Hoc Uncertainty Quantification in Operator Learning
arXiv cs.AI Research & Papers
MagicSim: A Unified Infrastructure for Executable Embodied Interaction