Español

Explorar

Noticias de IA

27413 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
Optimal and Diffusion Transports in Machine Learning
arXiv cs.AI Research & Papers
HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex…
arXiv cs.AI Research & Papers
Differential syntactic and semantic encoding in LLMs
arXiv cs.AI Research & Papers
The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic V…
arXiv cs.AI Research & Papers
The Well-Tempered Classifier: Some Elementary Properties of Temperature Scaling
arXiv cs.AI Research & Papers
Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Polic…
arXiv cs.AI Research & Papers
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendati…
arXiv cs.AI Research & Papers
UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind
arXiv cs.AI Research & Papers
Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancie…
arXiv cs.AI Research & Papers
High-Fidelity Industrial Crash Dynamics Prediction via Geometry-Aware Operator Learning w…
arXiv cs.AI Research & Papers
ChildEval: When large language models meet children's personalities
arXiv cs.AI Research & Papers
Compositional Consistency-Guided Decoding for Three-Way Logical Question Answering
arXiv cs.AI Research & Papers
LASER: Learning Active Sensing for Continuum Field Reconstruction
arXiv cs.AI Research & Papers
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
arXiv cs.AI Research & Papers
DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervis…
arXiv cs.AI Research & Papers
Singular Vectors of Attention Heads Align with Features
arXiv cs.AI Research & Papers
SPAR: Support-Preserving Action Rectification
arXiv cs.AI Research & Papers
Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning
arXiv cs.AI Research & Papers
Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
arXiv cs.AI Research & Papers
SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
arXiv cs.AI Research & Papers
Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance a…
arXiv cs.AI Research & Papers
Learning Compositional Latent Structure with Vector Networks
arXiv cs.AI Research & Papers
Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
arXiv cs.AI Research & Papers
StoryLens: Preference-Aligned Story Rewriting via Context-Aware Narrative Enrichment
arXiv cs.AI Research & Papers
Snowveil: A Framework for Decentralised Preference Discovery
arXiv cs.AI Research & Papers
Feature Learning Dynamics in Infinite-Depth Neural Networks
arXiv cs.AI Research & Papers
EigeNet: Geometry-Informed Multi-Modal Learning for Few-shot Novel View RIR Prediction
arXiv cs.AI Research & Papers
Cultural Fidelity in English-to-Hindi Translation: A Preservation-Fluency Frontier for Ge…
arXiv cs.AI Research & Papers
On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation
arXiv cs.AI Research & Papers
Learning Tangent Bundles and Characteristic Classes with Autoencoder Atlases