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
CS-CLIP: Compositional Scene Graph-guided CLIP for Robust Compositional Reasoning
arXiv cs.AI Research & Papers
Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evalu…
arXiv cs.AI Research & Papers
ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testi…
arXiv cs.AI Research & Papers
MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Dam…
arXiv cs.AI Research & Papers
ReST-RL: Reinforcing LLM Reasoning through Unified Self-Training and Value-Guided Search
arXiv cs.AI Research & Papers
Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Ma…
arXiv cs.AI Research & Papers
The Role of Gradient Modification in Heavy-Tailed Nonconvex Stochastic Min-Max Optimizati…
arXiv cs.AI Security & Safety
Structurally Close, Temporally Distant: Measuring Security Exposure in Long-Horizon LLM A…
arXiv cs.AI Research & Papers
Sparse Data Augmentation for Optimization with Provable Guarantees
arXiv cs.AI Research & Papers
KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
arXiv cs.AI Research & Papers
CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Delet…
arXiv cs.AI Research & Papers
Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Un…
arXiv cs.AI Research & Papers
A New Strategy for Artificial Intelligence: Training Foundation Models Directly on Human …
arXiv cs.AI Research & Papers
Parameterized and Streaming Algorithms for Euclidean Fair $k$-Center Clustering
arXiv cs.AI Research & Papers
Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation
arXiv cs.AI Research & Papers
HyCO: A Hybrid Neural Solver for Combinatorial Optimization
arXiv cs.AI Research & Papers
One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware …
arXiv cs.AI Research & Papers
Safety boundary maintenance in consumer AI systems responding to pediatric health queries…
arXiv cs.AI Research & Papers
OntoKG-EQ: A provenance-grounded, competency-question-governed knowledge graph for audita…
arXiv cs.AI Research & Papers
Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels f…
arXiv cs.AI Research & Papers
AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis …
arXiv cs.AI Research & Papers
Neural Symbollic Regression Using Deep Learning and Sparse Modelling
arXiv cs.AI Research & Papers
A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content
arXiv cs.AI Research & Papers
TDDN: Text-aligned Diffused DINO Network for Puzzle Understanding
arXiv cs.AI Research & Papers
STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient L…
arXiv cs.AI Research & Papers
TD-STGT: A Spatio-Temporal Graph Transformer for Mobile Traffic Demand Forecasting
arXiv cs.AI Research & Papers
DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning
arXiv cs.AI Research & Papers
WSPolypNet: Weakly Supervised Polyp Localization in Colonoscopy Videos
arXiv cs.AI Research & Papers
SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives
arXiv cs.AI Research & Papers
Certifying cooperation: a novel approach to cooperative multi-agent task generation