Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Developer Tooling
A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture Analysis
arXiv cs.AI Research & Papers
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforceme…
arXiv cs.AI Research & Papers
Talking to Me or Someone Else? Rethinking Talk-to-Me Detection in Egocentric Videos
arXiv cs.AI Research & Papers
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction
arXiv cs.AI Research & Papers
Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse M…
arXiv cs.AI Research & Papers
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from A…
arXiv cs.AI Research & Papers
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
arXiv cs.AI Research & Papers
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
arXiv cs.AI Research & Papers
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
arXiv cs.AI Research & Papers
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
arXiv cs.AI Research & Papers
Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear
arXiv cs.AI Research & Papers
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
arXiv cs.AI Research & Papers
EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition
arXiv cs.AI Research & Papers
Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
arXiv cs.AI Research & Papers
LePlanner: An Iterative Amortized Controller For World Models
arXiv cs.AI Research & Papers
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
arXiv cs.AI Security & Safety
Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulne…
arXiv cs.AI Research & Papers
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
arXiv cs.AI Research & Papers
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured R…
arXiv cs.AI Research & Papers
TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection
arXiv cs.AI Research & Papers
Testing the Limits of Truth Directions in LLMs
arXiv cs.AI Research & Papers
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
arXiv cs.AI Research & Papers
OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise
arXiv cs.AI Research & Papers
Phorecaster365: A Human-Supervised Reference Architecture for Hybrid Pharmaceutical Sales…
arXiv cs.AI Research & Papers
Proving olympiad geometry theorems on a superconducting quantum processor
arXiv cs.AI Research & Papers
AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
arXiv cs.AI Research & Papers
PACE: Progressive Angular-to-Norm Contrastive Embedding
arXiv cs.AI Research & Papers
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
arXiv cs.AI Research & Papers
Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks
arXiv cs.AI Models & Releases
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search