Español

Explorar

Noticias de IA

29647 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
FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normal…
arXiv cs.AI Research & Papers
Efficient Exploration for Iterative Nash Preference Optimization
arXiv cs.AI Research & Papers
Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge…
arXiv cs.AI Research & Papers
Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing
arXiv cs.AI Research & Papers
On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection
arXiv cs.AI Research & Papers
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architect…
arXiv cs.AI Research & Papers
Emergent Transfer of a Physics Foundation Model from Simulation to Laboratory Turbulence
arXiv cs.AI Research & Papers
MURMUR: An Efficient Inference System for Long-Form ASR
arXiv cs.AI Research & Papers
LLM Consortium for Software Design Refinement: A Controlled Experiment on Multi-Agent Col…
arXiv cs.AI Security & Safety
ClawHub Security Signals: When VirusTotal, Static Analysis, and SkillSpector Disagree
arXiv cs.AI Research & Papers
Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Tradi…
arXiv cs.AI Research & Papers
Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in…
arXiv cs.AI Research & Papers
TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
arXiv cs.AI Research & Papers
Self-Conditioned Positional HNSW for Overlap-Aware Retrieval in Chunked-Document RAG Syst…
arXiv cs.AI Security & Safety
Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
arXiv cs.AI Research & Papers
DOT-MoE: Differentiable Optimal Transport for MoEfication
arXiv cs.AI Research & Papers
TechGraphRAG: An Agentic Graph-Augmented RAG Framework for Technical Literature Reasoning
arXiv cs.AI Research & Papers
EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
arXiv cs.AI Research & Papers
Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
arXiv cs.AI Research & Papers
A Framework for Graph-Conditioned Hierarchical Shapley Attribution in Patent Valuation
arXiv cs.AI Research & Papers
AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation i…
arXiv cs.AI Research & Papers
PlanarBench: Evaluating LLM Spatial Reasoning via Planar Graph Drawing
arXiv cs.AI Research & Papers
Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical…
arXiv cs.AI Research & Papers
HAIM: Human-AI Music Datasets for AI Music Production Tracking Benchmark
arXiv cs.AI Research & Papers
RPCASSM: Robust PCA State Space Model For Infrared Small Target Detection
arXiv cs.AI Research & Papers
JenBridge: Adaptive Long-Form Video Soundtracking across Scene Transitions
arXiv cs.AI Research & Papers
Fair Finetuning Mitigates Distribution Inference Attacks
arXiv cs.AI Research & Papers
Shortcut to Nowhere: Demystifying Deep Spurious Regression
arXiv cs.AI Research & Papers
Argument Collapse: LLMs Flatten Long-Form Public Debate
arXiv cs.AI Security & Safety
THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Languag…