Español

Explorar

Noticias de IA

22115 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
AI-Integrated Scientific Inquiry: A Practice-Centered Vision for Science Education
arXiv cs.AI Research & Papers
Graph-Theoretic Neural Network Fragmentation with Covariant Direct Molecular Force Learni…
arXiv cs.AI Research & Papers
Khondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms
arXiv cs.AI Research & Papers
Cross-Model LLM Code Review: Should you use Claude to review Codex or vice versa?
arXiv cs.AI Research & Papers
SwiftMem: Fast Agentic Memory via Query-aware Indexing
arXiv cs.AI Research & Papers
Probing Speaker Identity Sensitivity in Audio Deepfake Detectors
arXiv cs.AI Research & Papers
LeAct: Learning to Reason from Expert Actions
arXiv cs.AI Research & Papers
Generalized Neural Operator for Parametric and Boundary-Value Problems
arXiv cs.AI Research & Papers
Data Quality over Capacity: Internalizing Documents into LoRA Adapters for Closed-Book QA
arXiv cs.AI Research & Papers
TextSLIP: Text Self-Supervised CLIP for Medical Report Generation
arXiv cs.AI Research & Papers
The Hard Decision Layer: Evidence for Committed Inference in Transformers
arXiv cs.AI Research & Papers
Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning
arXiv cs.AI Research & Papers
Automatic Stability and Recovery for Neural Network Training
arXiv cs.AI Research & Papers
Unified Static-Dynamic Pruning for Efficient LLM Inference
arXiv cs.AI Research & Papers
A Leakage-Free Stacked Ensemble Method for Multiclass Classification
arXiv cs.AI Research & Papers
From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sam…
arXiv cs.AI Research & Papers
Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning
arXiv cs.AI Research & Papers
Sparse by Command: Task-Conditional Compute Skipping for Multi-Task Inference Accelerators
arXiv cs.AI Research & Papers
Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the …
arXiv cs.AI Research & Papers
Benchmarking Text-to-SQL under Role-Based Access Control
arXiv cs.AI Research & Papers
CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coro…
arXiv cs.AI Research & Papers
J-CoT: Chain-of-Thought in J-Space
arXiv cs.AI Research & Papers
DBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents
arXiv cs.AI Research & Papers
Learning Spatiotemporal Decision Priors for Efficient Path Planning under Partial Observa…
arXiv cs.AI Research & Papers
Hyperball May Not Be a Free Lunch
arXiv cs.AI Research & Papers
Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Re…
arXiv cs.AI Research & Papers
Learning to Prepare Molecular Ground States with Transformer Models
Hugging Face Daily Papers Research & Papers
Plato-Bio: verification-first biological novelty screening with temporal rediscovery and …
Hugging Face Daily Papers Research & Papers
MusiChat: Vibe Composing for Music Creation
Hugging Face Daily Papers Research & Papers
Color Fundus Photography Analysis: Co-evolution of Data, Preprocessing, and Modeling towa…