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
MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs
arXiv cs.AI Research & Papers
FOUNDv2: Learning Unified User Quantized Tokenizers for User Representation
arXiv cs.AI Research & Papers
CLoVE: Personalized Federated Learning through Clustering of Loss Vector Embeddings
arXiv cs.AI Research & Papers
LM-SPT: LM-Aligned Semantic Distillation for Speech Tokenization
arXiv cs.AI Research & Papers
AC-ODM: Actor--Critic Online Data Mixing for Sample-Efficient LLM Pretraining
arXiv cs.AI Research & Papers
Multiple Descents in Deep Learning as a Sequence of Order-Chaos Transitions in LSTM Netwo…
arXiv cs.AI Research & Papers
daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GP…
arXiv cs.AI Research & Papers
HOLO-MPPI: Multi-Scenario Motion Planning via Hierarchical Policy Optimization
arXiv cs.AI Research & Papers
Uncertainty Quality of VGGT: An Analysis on the DTU Benchmark Dataset
arXiv cs.AI Research & Papers
AI systems out-persuade expert humans
arXiv cs.AI Research & Papers
Learning aligned EEG representations with subject-specific encoders
arXiv cs.AI Research & Papers
Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalan…
arXiv cs.AI Research & Papers
EEG-FM-Bench: A Comprehensive Benchmark for the Systematic Evaluation and Diagnostic Anal…
arXiv cs.AI Research & Papers
A biological vision inspired framework for machine perception of abutting grating illusor…
arXiv cs.AI Research & Papers
WorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
arXiv cs.AI Research & Papers
An Attention Mechanism for Robust Multimodal Integration in a Global Workspace Architectu…
arXiv cs.AI Research & Papers
JADE: Expert-Grounded Dynamic Evaluation for Open-Ended Professional Tasks
arXiv cs.AI Research & Papers
RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs
arXiv cs.AI Research & Papers
Edit Knowledge, Not Just Facts via Multi-Step Reasoning over Background Stories
arXiv cs.AI Research & Papers
DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation
arXiv cs.AI Research & Papers
Discovering Symmetry Groups with Flow Matching
arXiv cs.AI Research & Papers
Interpretation as Linear Transformation: A Cognitive-Geometric Model of Concepts and Mean…
arXiv cs.AI Research & Papers
Efficient Flow Matching using Latent Variables
arXiv cs.AI Research & Papers
PURe: A Plug-and-Play Product-Unit Residual Module for Vision Networks
arXiv cs.AI Research & Papers
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
arXiv cs.AI Research & Papers
The Missing Knowledge Layer in Cognitive Architectures for AI Agents
arXiv cs.AI Research & Papers
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
arXiv cs.AI Research & Papers
Beyond Predefined Schemas: TRACE-KG for Context-Enriched Knowledge Graph Generation
arXiv cs.AI Research & Papers
Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
arXiv cs.AI Research & Papers
Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Sta…