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
FDRMFL: Multimodal Federated Feature Extraction Model Based on Information Maximization a…
arXiv cs.AI Research & Papers
Thinking Ahead: Foresight Intelligence in MLLMs and World Model
arXiv cs.AI Research & Papers
Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
arXiv cs.AI Research & Papers
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
arXiv cs.AI Research & Papers
NonTextual Target Attack
arXiv cs.AI Research & Papers
Explain Before You Answer: A Survey on Compositional Visual Reasoning
arXiv cs.AI Research & Papers
LHM-Humanoid: Long-Horizon Human Motion Control for Continuous Object Transport in Clutte…
arXiv cs.AI Research & Papers
A Study of Commonsense Reasoning over Visual Object Properties
arXiv cs.AI Research & Papers
Understanding Two-Layer Neural Networks with Smooth Activation Functions
arXiv cs.AI Research & Papers
Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adapt…
arXiv cs.AI Research & Papers
Digital Fragmentation and Generative AI Use Across 103 Million Application Events
arXiv cs.AI Research & Papers
FMMVCC: Fuzzy Mamba-based Multi-View Contrastive Clustering for Univariate Time Series
arXiv cs.AI Research & Papers
Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity…
arXiv cs.AI Research & Papers
Stability of Flow Models for Graph Signals
arXiv cs.AI Research & Papers
When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial Analys…
arXiv cs.AI Research & Papers
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
arXiv cs.AI Research & Papers
Terminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
arXiv cs.AI Research & Papers
Participatory provenance as representational auditing for AI-mediated public consultation
arXiv cs.AI Research & Papers
Anomaly detection in time-series via inductive biases in the latent space of conditional …
arXiv cs.AI Research & Papers
Power and Limitations of Aggregation in Compound AI Systems
arXiv cs.AI Research & Papers
An Adaptive Differentially Private Federated Learning Framework
arXiv cs.AI Research & Papers
Framing Instability in LLM Ethical Stance: Auditing Negation Sensitivity in Moral Dilemmas
arXiv cs.AI Research & Papers
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympi…
arXiv cs.AI Research & Papers
Neutral Substrates: A Design Constraint for Shared Records Under Persistent Interpretive …
arXiv cs.AI Research & Papers
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Na…
arXiv cs.AI Research & Papers
Co-LMLM: Continuous-Query Limited Memory Language Models
arXiv cs.AI Research & Papers
Breaking Database Lock-in: Agentic Regeneration of High Performance Storage Readers for D…
arXiv cs.AI Research & Papers
Agon: Competitive Cross-Model RL with Implicit Rival Grading of Reasoning
arXiv cs.AI Research & Papers
DiaLLM: An Investigation into the Robustness-Generation Gap in English Dialect Adaptation
arXiv cs.AI Research & Papers
QCNN with Rough Path Signature Kernels