Español

Explorar

Noticias de IA

29349 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
HDST-GNN: Heterogeneous Dynamic Spatiotemporal Graph Neural Networks for Multi-Object Tra…
arXiv cs.AI Research & Papers
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
arXiv cs.AI Research & Papers
Synapse: Federated Tool Routing via Typed Compendium Artifacts
arXiv cs.AI Research & Papers
Your GFlowNet Secretly Learns an Optimal Transport Plan
arXiv cs.AI Research & Papers
FUSAR-GPT : A Spatiotemporal Feature-Embedded and Two-Stage Decoupled Visual Language Mod…
arXiv cs.AI Research & Papers
MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-A…
arXiv cs.AI Security & Safety
From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monit…
arXiv cs.AI Research & Papers
Learning to replenish: A hybrid deep reinforcement learning for dynamic inventory managem…
arXiv cs.AI Research & Papers
WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation
arXiv cs.AI Research & Papers
Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing
arXiv cs.AI Research & Papers
RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
arXiv cs.AI Research & Papers
From Kinematics to Dynamics: Learning to Refine Hybrid Plans for Physically Feasible Exec…
arXiv cs.AI Research & Papers
A Survey on Diffusion Language Models
arXiv cs.AI Research & Papers
Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning
arXiv cs.AI Research & Papers
HypRAG: Hyperbolic Dense Retrieval for Retrieval Augmented Generation
arXiv cs.AI Research & Papers
TOKI: A Bitemporal Operator Algebra for Contradiction Resolution in LLM-Agent Persistent …
arXiv cs.AI Research & Papers
In-Training Defenses against Emergent Misalignment in Language Models
arXiv cs.AI Research & Papers
SciVisAgentSkills: Design and Evaluation of Agent Skills for Scientific Data Analysis and…
arXiv cs.AI Research & Papers
Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation
arXiv cs.AI Research & Papers
The Virtual Roundtable: Multi-Agent Personas Simulating the Dynamics of Human Brainstormi…
arXiv cs.AI Research & Papers
You Only Index Once: Cross-Layer Sparse Attention with Shared Routing
arXiv cs.AI Research & Papers
Self-Augmenting Retrieval for Diffusion Language Models
arXiv cs.AI Research & Papers
Next-Generation Parallel Decoder for LPDR: Architectural Optimization and Class-Balanced …
arXiv cs.AI Research & Papers
Scaling Laws and Spectra of Shallow Neural Networks in the Feature Learning Regime
arXiv cs.AI Research & Papers
Path-Coupled Bellman Flows for Distributional Reinforcement Learning
arXiv cs.AI Research & Papers
Reformulating Neural Operators in $d+1$ Dimensions for Embedding Evolution
arXiv cs.AI Research & Papers
Agents' Last Exam
arXiv cs.AI Security & Safety
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
arXiv cs.AI Research & Papers
CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspecti…
arXiv cs.AI Research & Papers
Residual Modeling for High-Fidelity Learned Compression of Scientific Data