Español

Explorar

Noticias de IA

22318 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
CIGPO: Contextual Information-Gain Policy Optimization for Multi-Turn Evidence-Reading LL…
arXiv cs.AI Research & Papers
Let the Data Decide: Supervision Analysis, Capability Trade-offs, and Adaptive Objective …
arXiv cs.AI Research & Papers
High-accuracy Low-Bit KV-Cache Quantization via Local Distribution Restoration
arXiv cs.AI Research & Papers
An Agentic Interface for End-to-End Probabilistic Seismic Hazard and Risk Analysis
arXiv cs.AI Research & Papers
AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis
arXiv cs.AI Research & Papers
Autonomous mechanistic discovery of colorectal cancer vulnerabilities via multi-scale AI …
arXiv cs.AI Research & Papers
Composable Verification Pipelines for Multi-Agent Systems
arXiv cs.AI Research & Papers
From Intent to Infrastructure: LLM-Driven Agent Compilers for ISAC Networks
arXiv cs.AI Research & Papers
ForensicNet: Lightweight Attention-Enhanced MobileNetV2 for Automated Face Identification
arXiv cs.AI Research & Papers
GenSyn10: A Multi-Generative AI Dataset For Benchmarking Image Classification
arXiv cs.AI Research & Papers
Emergent Hierarchical Monosemantic Neurons from the Group-Contrastive Forward-Forward Alg…
arXiv cs.AI Research & Papers
Efficient EEG Seizure Detection Using INT8 Quantization, Channel Pruning, and Spiking Neu…
arXiv cs.AI Research & Papers
Med-OPD: Improving Medical Vision-Language Models via Evidence-Aware On-Policy Distillati…
arXiv cs.AI Research & Papers
DAUPNet: Domain-Aware Uncertainty Modeling for Reliable Prototype Discrimination in Cross…
arXiv cs.AI Research & Papers
Monte Carlo Dropout Uncertainty and Entropy-Thresholded Selective Prediction for Architec…
arXiv cs.AI Research & Papers
GMoT: Gated Motion-Aware Tokenization for Fine-Grained Micro-Gesture Video Reasoning with…
arXiv cs.AI Research & Papers
DMFNet: Dual-Backbone Multiscale Fusion Network for Urban Scene Classification
arXiv cs.AI Research & Papers
A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-…
arXiv cs.AI Research & Papers
Fantastic Adaptive Taxonomies and How to Use Them
arXiv cs.AI Research & Papers
A Predict-then-Correct Loop Based on Few-Shot Continuous Contextual Bandit for Demand For…
arXiv cs.AI Research & Papers
Retrieval is Enough: Training-Free Interpretability with a Tool-Using Agent
arXiv cs.AI Research & Papers
Committed Before Reasoning: Behavioral Reproduction and Preliminary Activation-Level Evid…
arXiv cs.AI Research & Papers
When to Use Which? Benchmarking Optimisers for Configurable Systems under Varying Budgets
arXiv cs.AI Research & Papers
How Formerly Incarcerated People Envision Technologies for Prison Parole
arXiv cs.AI Research & Papers
Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Lea…
arXiv cs.AI Research & Papers
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipel…
arXiv cs.AI Research & Papers
Privacy Cost as Equity Input: A Group Fairness Criterion for Differentially Private Machi…
arXiv cs.AI Research & Papers
CLOSER-Bench: Evaluating Budgeted Cross-Stage Design Closure for Hardware Agents
arXiv cs.AI Research & Papers
Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteri…
arXiv cs.AI Research & Papers
Position: Explanation Stability Is a Property of the Model Method Pair, Not the Model