A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture Analysis
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforceme…
Talking to Me or Someone Else? Rethinking Talk-to-Me Detection in Egocentric Videos
Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime Prediction
Symmetry- and Property-Aware Crystal Generation with Reinforcement Learning for Inverse M…
Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from A…
From Visual Feedback to Textual Reviews: A Multi-Agent Vision-Language Framework for Imag…
RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-Attributes
Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache
Refusal Reads Only a Slice of What the Model Knows: Harm-Keyed Routing and Its Exceptions…
Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear
Route, Don't Fix: Regime-Dependent Decoding Correction and a Trajectory-Gated Router for …
EdgeHAR: An Edge-Native Compact Sensor Foundation Model for Human Activity Recognition
Physics Informed Neural Network model for the dynamical study of Abdominal Aortic Aneurysm
LePlanner: An Iterative Amortized Controller For World Models
HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Re…
Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulne…
AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs Inference
Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured R…
TyPatch: Transforming Patches into Typestate Rules for Kernel Bug Detection
Testing the Limits of Truth Directions in LLMs
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise
Phorecaster365: A Human-Supervised Reference Architecture for Hybrid Pharmaceutical Sales…
Proving olympiad geometry theorems on a superconducting quantum processor
AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM Agents
PACE: Progressive Angular-to-Norm Contrastive Embedding
DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis
Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G Networks
ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search