Español

Explorar

Noticias de IA

30585 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
Tapered Language Models
arXiv cs.AI Research & Papers
RECALL: Recovery Experience Collection for Active Lifelong Learning in Vision-Language-Ac…
arXiv cs.AI Research & Papers
Discovering Latent Groups for Robust Classification
arXiv cs.AI Research & Papers
Polycepta: Object-Centric Appearance Estimation for Multi-Object Tracking
arXiv cs.AI Research & Papers
A Generative Model for Closed-Loop Microsimulation of Signalized Intersections
arXiv cs.AI Research & Papers
Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse
arXiv cs.AI Research & Papers
Solve for the Hyperparameter, Skip the Search: Kolmogorov-Optimal Scaling Laws for Spline…
arXiv cs.AI Research & Papers
The Energy Consumption of Transformer Fine-Tuning: A Roofline-Inspired Scaling Model
arXiv cs.AI Research & Papers
War in the Abstract: The Rise and Consequences of Militarized Language in Scientific Comm…
arXiv cs.AI Security & Safety
Detecting Malicious Agent Skills in the Wild using Attention
arXiv cs.AI Research & Papers
UnBias-Plus: Detect, Explain, and Rewrite Bias
arXiv cs.AI Research & Papers
HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffus…
arXiv cs.AI Research & Papers
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Mod…
arXiv cs.AI Research & Papers
Automated Semantic Fault Localization in SysML v2: A Human-in-the-Loop Framework Using Kn…
arXiv cs.AI Research & Papers
Energy-Based Transformers as Predictors of Reading Difficulty
arXiv cs.AI Research & Papers
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
arXiv cs.AI Research & Papers
Rethinking Molecular Graph Backdoors under Chemistry-aware Admission
arXiv cs.AI Research & Papers
Adaptive Hard-Soft Physics-Informed Neural Networks for Robust Boundary-Constrained PDE S…
arXiv cs.AI Research & Papers
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
arXiv cs.AI Research & Papers
P-JEPA: Procedural Video Representation Learning via Joint Embedding Predictive Architect…
arXiv cs.AI Research & Papers
SteerVTE: Seamless Video Text Editing with Style and Glyph Control
arXiv cs.AI Research & Papers
MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations
arXiv cs.AI Research & Papers
Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory
arXiv cs.AI Research & Papers
PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation
arXiv cs.AI Security & Safety
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
arXiv cs.AI Research & Papers
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
arXiv cs.AI Research & Papers
From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection
arXiv cs.AI Research & Papers
HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems
arXiv cs.AI Research & Papers
Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?
arXiv cs.AI Research & Papers
The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Region…