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
Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations
arXiv cs.AI Research & Papers
The Dynamics of Intelligence Explosions
arXiv cs.AI Research & Papers
SheetCompass: Hierarchical Relation Graphs for Agentic Spreadsheet Reasoning
arXiv cs.AI Research & Papers
Twin: Playing an Unknown Game with a Test-Time Digital Twin
arXiv cs.AI Research & Papers
Split the Labor: Separating Evidence Interpretation from Decision Aggregation
arXiv cs.AI Research & Papers
Handover of In-Context Learning State Across Session Boundaries
arXiv cs.AI Research & Papers
Proxy-Validated LLM UX Micro-Simulations: An Artifact-First Protocol for Early-Stage Deci…
arXiv cs.AI Research & Papers
Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse…
arXiv cs.AI Research & Papers
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preli…
arXiv cs.AI Research & Papers
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
arXiv cs.AI Research & Papers
The Architect: Interactive Visualization of Deep Learning Mathematics Directly in Microso…
arXiv cs.AI Research & Papers
Interactive Analysis of Global Explanations using Aggregated Class Activation Maps for Ne…
arXiv cs.AI Research & Papers
BCMT: Blockwise Causal Memory Transformer
arXiv cs.AI Research & Papers
From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Ag…
arXiv cs.AI Research & Papers
UltraArUco: A Lightweight Multilingual Library And Framework With Low-Latency Real-Time M…
arXiv cs.AI Research & Papers
IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering
arXiv cs.AI Research & Papers
Secret-Stego Dissimilarity as a Design Axis: Invertible Coverless Image Steganography wit…
arXiv cs.AI Research & Papers
Training-Free Knowledge Transfer Across Model Scales through Activation-Guided Pruning
arXiv cs.AI Research & Papers
Fine-Tuning Qwen3-27B for C-to-Rust Code Translation: A Three-Stage Curriculum of Pretrai…
arXiv cs.AI Research & Papers
SAGE: Surrogate-gradient Adaptation via Attention-Guided Entropy for Spiking Transformers
arXiv cs.AI Research & Papers
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive…
arXiv cs.AI Research & Papers
TeachMateGPT: A Multi-Agent Knowledge-Grounded Framework for Pedagogical Assessment Gener…
arXiv cs.AI Research & Papers
Reading Between The Lines: Modeling and Evaluating Behavioral Realism in Legal Simulation
arXiv cs.AI Research & Papers
Building AI-Intensive Software with AI: Early Results and a Cautionary Tale on Measuring …
arXiv cs.AI Research & Papers
Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and…
arXiv cs.AI Research & Papers
Data-driven techniques for translational neuroscience and personalized neuro-health
arXiv cs.AI Research & Papers
CutClean: Neural Network Pruning for Privacy-Preserving Inference
arXiv cs.AI Research & Papers
Do AI chatbots find what experts would? Effects of model, user role, and sample size on s…
arXiv cs.AI Research & Papers
PPAPlace: Differentiable Cross-Stage Objectives for Chip Placement Optimization
arXiv cs.AI Research & Papers
AdsWorldEngine: A Self-Evolving Conversational Advertising Agent through Orchestrator and…