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
Contextual Agentic Memory is a Memo, Not True Memory
arXiv cs.AI Research & Papers
SpecBox: Speculative Sandbox Scheduling for Efficient LLM Agent Serving
arXiv cs.AI Research & Papers
FUSEP: A Multi-Center Benchmark for Diverse Tasks in Early Pregnancy Fetal Ultrasound Scr…
arXiv cs.AI Research & Papers
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
arXiv cs.AI Research & Papers
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
arXiv cs.AI Research & Papers
NSF-HRPT: Neural Semantic Field meets Hierarchical Risk Perception Tree for Safety-Critic…
arXiv cs.AI Research & Papers
Large-Small Model Collaboration for Enhancing Edge-Deployed Small Models
arXiv cs.AI Research & Papers
Zero-shot reasoning for simulating scholarly peer-review
arXiv cs.AI Research & Papers
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
arXiv cs.AI Research & Papers
GRALS: GCN-Guided Redundancy-Aware Local Search for Minimum Vertex Cover
arXiv cs.AI Research & Papers
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
arXiv cs.AI Research & Papers
Chained Recursive Language Models for Multi-Iteration Reasoning
arXiv cs.AI Research & Papers
Robust and Efficient Motion Reasoning for Privacy-Aware Classroom Incident Recognition
arXiv cs.AI Research & Papers
Representational separation between unitary and channel quantum generative models via sha…
arXiv cs.AI Research & Papers
Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Sel…
arXiv cs.AI Research & Papers
VQ-VAD: Vector-quantized Motion Representation Learning for Human-centric Video Anomaly D…
arXiv cs.AI Research & Papers
RepairFormer: Automated Repair of Structured Inputs Using Transformers
arXiv cs.AI Research & Papers
The Effect of Perceived Race and Gender on Police Language Use: Experimental Evidence fro…
arXiv cs.AI Research & Papers
Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning
arXiv cs.AI Security & Safety
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
arXiv cs.AI Research & Papers
ArtAnno: Annotating Implicit Semantics in Artworks through LLM Agent-Driven Bidirectional…
arXiv cs.AI Research & Papers
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
arXiv cs.AI Research & Papers
SVI-DAG: A Structured Variational Inference Approach to Bayesian Causal Discovery
arXiv cs.AI Research & Papers
Consistency-Driven Co-Evolution for Self-Supervised Cross-Representation Learning
arXiv cs.AI Research & Papers
A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Aud…
arXiv cs.AI Research & Papers
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
arXiv cs.AI Research & Papers
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
arXiv cs.AI Research & Papers
A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination
arXiv cs.AI Research & Papers
Towards a satellite image manipulation and deepfake localization benchmark dataset
arXiv cs.AI Research & Papers
Guideline-as-Oracle: Zero-Annotation Training of an Ophthalmic Telephone Triage Agent