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
Deep Neural Networks: A Formulation Via Non-Archimedean Analysis
arXiv cs.AI Research & Papers
It's About Time: Temporal References in Emergent Communication
arXiv cs.AI Research & Papers
Multi-Grade Deep Learning for Partial Differential Equations with Applications to the Bur…
arXiv cs.AI Research & Papers
LLM Jaggedness Unlocks Scientific Creativity
arXiv cs.AI Research & Papers
Dual-Uncertainty Guided Policy Learning for Multimodal Reasoning
arXiv cs.AI Research & Papers
JE-IRT: A Geometric Lens on LLM Abilities through Joint Embedding Item Response Theory
arXiv cs.AI Research & Papers
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving
arXiv cs.AI Research & Papers
Metacognitive Myopia in Large Language Models
arXiv cs.AI Research & Papers
Rescaling Confidence: What Scale Design Reveals About LLM Metacognition
arXiv cs.AI Research & Papers
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
arXiv cs.AI Research & Papers
The Initial Exploration Problem in Knowledge Graph Exploration
arXiv cs.AI Research & Papers
Adaptive inference and function vectors in deep transformers
arXiv cs.AI Research & Papers
DCP-Prune: Ultra-Low Token Pruning with Distribution Consistency Preservation
arXiv cs.AI Research & Papers
Using AI in engineering education: a balancing act, driven by clear purpose
arXiv cs.AI Research & Papers
VeriGraph: Towards Verifiable Data-Analytic Agents
arXiv cs.AI Research & Papers
Learning Interface Breakup: A Geometry-Conditioned Latent Surrogate for Spray Formation
arXiv cs.AI Research & Papers
Fast When, Careful Who: Dual-Process Multiparty Turn-Taking with Diffusion Augmentation
arXiv cs.AI Research & Papers
PISA: A Pragmatic Psych-Inspired Unified Memory System for Enhanced AI Agency
arXiv cs.AI Research & Papers
Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for …
arXiv cs.AI Research & Papers
Deep Q-Learning on H\"older Spaces
arXiv cs.AI Research & Papers
Robust Dual-Signal Fusion: Hybrid Neuro-Symbolic Gating with Compressed Chain-of-Thought …
arXiv cs.AI Research & Papers
ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in …
arXiv cs.AI Research & Papers
Tying the Loop -- Tied Expert Layers in Mixture-of-Experts Language Models
arXiv cs.AI Research & Papers
Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment f…
arXiv cs.AI Research & Papers
Decision-Weighted Flow Matching for Contextual Stochastic Optimization
arXiv cs.AI Research & Papers
P3B3: A Multi-Turn Conversational Benchmark for Measuring European and Brazilian Portugue…
arXiv cs.AI Research & Papers
The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Imag…
arXiv cs.AI Research & Papers
FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Dual-Modal Vision-Languag…
arXiv cs.AI Research & Papers
TokenPilot: Cache-Efficient Context Management for LLM Agents
arXiv cs.AI Research & Papers
TuneJury: An Open Metric for Improving Music Generation Preference Alignment