Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes…
arXiv cs.AI Research & Papers
Performance Comparison of Classical and Neural Sampling Algorithms for Robotic Navigation
arXiv cs.AI Research & Papers
On the Stability and Realizability of Recurrent Polynomial Surrogate Ternary Logic Gate N…
arXiv cs.AI Research & Papers
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
arXiv cs.AI Research & Papers
FlowPlan-G2P: A Structured Generation Framework for Transforming Scientific Papers into P…
arXiv cs.AI Research & Papers
From Accuracy to Auditability: A Survey of Determinism in Financial AI Systems
arXiv cs.AI Research & Papers
How Many Tools Should an LLM Agent See? A Chance-Corrected Answer
arXiv cs.AI Research & Papers
Cultivating Machine Intelligence: The OMEGA Shift from Top-Down Optimization to Autopoiet…
arXiv cs.AI Research & Papers
AI as Equalizer or Amplifier? Task Complexity as the Moderating Factor for Human Expertis…
arXiv cs.AI Research & Papers
Solving Combinatorial Counting Problems with Weighted First-Order Model Counting
arXiv cs.AI Research & Papers
AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization
arXiv cs.AI Research & Papers
LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy
arXiv cs.AI Research & Papers
DisDop: Distillation with Domain Priors for Open-Vocabulary Aerial Object Detection
arXiv cs.AI Research & Papers
Reducing Credit Assignment Variance via Counterfactual Reasoning Paths
arXiv cs.AI Research & Papers
BODHI: Precise OS Kernel Specification Inference
arXiv cs.AI Research & Papers
Operationalizing Reconstructive Authority: Runtime Construction, Dependency Resolution, a…
arXiv cs.AI Research & Papers
SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons L…
arXiv cs.AI Research & Papers
Uncovering Autoregressive LLM Knowledge of Thematic Fit in Event Representation
arXiv cs.AI Research & Papers
BoxLitE: A Faithful Knowledge Base Embedding Based on Convex Optimization
arXiv cs.AI Research & Papers
Gated Relational Alignment via Confidence-based Distillation for Efficient VLMs
arXiv cs.AI Research & Papers
Self-supervised Hierarchical Visual Reasoning with World Model
arXiv cs.AI Research & Papers
HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
arXiv cs.AI Research & Papers
Towards the Connection between Activation Sparsity and Flat Minima
arXiv cs.AI Research & Papers
VisualOverload: Probing Visual Understanding of VLMs in Really Dense Scenes
arXiv cs.AI Research & Papers
Extreme Region Policy Distillation
arXiv cs.AI Research & Papers
SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculati…
arXiv cs.AI Research & Papers
NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding
arXiv cs.AI Research & Papers
TopoAlign: Topology-Aware Visual Representation Alignment
arXiv cs.AI Research & Papers
HiTeC: Hierarchical Contrastive Learning on Text-Attributed Hypergraph with Semantic-Awar…
arXiv cs.AI Research & Papers
Test-Time Self-Adaptive Conditioning for Stable Audio-Driven Talking-Head Generation