Español

Explorar

Noticias de IA

30663 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
Break Through the Compression Bottleneck: From Theory to Practice
arXiv cs.AI Research & Papers
A New Well-Supported Semantics for Description Logic Programs
arXiv cs.AI Research & Papers
Is MoE Routing a Huffman Code? Discovering the Frequency-Diversity Law in Chain-of-Thought
arXiv cs.AI Research & Papers
Knowledge Injection Exists in MoE? Exploring Expert-Aware Contrast Decoding in MoE for Mi…
arXiv cs.AI Research & Papers
Drive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driv…
arXiv cs.AI Research & Papers
LLM-INSTRUCT at UZH Shared Task 2026: Constraint-Aware Retrieval and Selective Debate for…
arXiv cs.AI Research & Papers
OpenForgeRL: Train Harness-native Agents in Any Environment
arXiv cs.AI Research & Papers
Unsupervised Consensus-Based Anomaly Detection for Spatiotemporal Malaria Incidence in Gh…
arXiv cs.AI Research & Papers
EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based D…
arXiv cs.AI Security & Safety
Robust Critics: Defending LLMs Against Multi-Turn Attacks
arXiv cs.AI Research & Papers
Moir: Let the Model Direct Its Own Story for Robust Cross-Domain Knowledge Editing
arXiv cs.AI Research & Papers
Expectation Alignment of Language Models for Real-World User Expectations
arXiv cs.AI Research & Papers
RUMBA: Russian User Memory Benchmark
arXiv cs.AI Research & Papers
The Boundaries of Automation: A Theory of Persistent Human Participation
arXiv cs.AI Research & Papers
LinearARD: Linear-Memory Attention Distillation for RoPE Restoration
arXiv cs.AI Research & Papers
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle a…
arXiv cs.AI Research & Papers
From Noise to Diversity: Random Embedding Injection in LLM Reasoning
arXiv cs.AI Research & Papers
Toward Continuous Assurance for the Democratization of AI Agent Creation in Industry
arXiv cs.AI Research & Papers
KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback
arXiv cs.AI Research & Papers
Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective
arXiv cs.AI Research & Papers
From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regi…
arXiv cs.AI Research & Papers
StackingNet: Collective Inference Across Independent AI Foundation Models
arXiv cs.AI Research & Papers
Diagnosing Pathological Chain-of-Thought in Reasoning Models
arXiv cs.AI Research & Papers
Agentic coding without the cloud: evaluating open-weight large language models on longitu…
arXiv cs.AI Research & Papers
AREX: Towards a Recursively Self-Improving Agent for Deep Research
arXiv cs.AI Research & Papers
M$^3$-Gen: Interpretable Multimodal Generation of Gene Expression Profiles Using Clinical…
arXiv cs.AI Research & Papers
Bridging the Gap Between Plausibility and Admissibility: Constraint-Aware Flow Maps for D…
arXiv cs.AI Research & Papers
Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog
arXiv cs.AI Research & Papers
Agent-Guided Relational Concept Discovery: Toward Interpretable Surgical Margin Assessment
arXiv cs.AI Research & Papers
Multimodal Pretraining for Generalizable EEG Representation Learning