Español

Explorar

Noticias de IA

37834 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
Structural Preservation and the Logical Expressiveness of Graph Neural Networks
arXiv cs.AI Research & Papers
CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressi…
arXiv cs.AI Research & Papers
Decidable By Construction: Design-Time Verification for Trustworthy AI
arXiv cs.AI Research & Papers
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
arXiv cs.AI Research & Papers
How Inference Compute Shapes Frontier LLM Evaluation
arXiv cs.AI Research & Papers
findsylls: A Language-Agnostic Toolkit for Syllable-Level Speech Tokenization and Embeddi…
arXiv cs.AI Research & Papers
Small Initialization Matters for Large Language Models
arXiv cs.AI Research & Papers
Beyond MACs: Hardware Efficient Architecture Design for Vision Backbones
arXiv cs.AI Research & Papers
A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Genera…
arXiv cs.AI Research & Papers
HRDX: A Large-Scale Vector HD-Map Dataset
arXiv cs.AI Research & Papers
Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggrega…
arXiv cs.AI Research & Papers
The Price of Anarchy in Disaggregated Inference
arXiv cs.AI Research & Papers
Enhancing Pathological VLMs with Cross-scale Reasoning
arXiv cs.AI Research & Papers
Evaluating Interactive 2D Visualization as a Sample Selection Strategy for Biomedical Tim…
arXiv cs.AI Research & Papers
ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking
arXiv cs.AI Research & Papers
DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic…
arXiv cs.AI Research & Papers
Spatio-Temporal Fusion Model for Standard View Classification of Echocardiographic Videos
arXiv cs.AI Research & Papers
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framew…
arXiv cs.AI Security & Safety
Membership Inference Attacks against Large Audio Language Models
arXiv cs.AI Research & Papers
From Paper to Program: Knowledge Externalization for AI-Assisted Quantum Many-Body Code G…
arXiv cs.AI Research & Papers
PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
arXiv cs.AI Research & Papers
ZIVARI-TLBO: A Zero-Cost Inter-Group Evaluated-Elite Relay Mechanism for Teaching-Learnin…
arXiv cs.AI Security & Safety
Like a Hammer, It Can Build, It Can Break: Large Language Model Uses, Perceptions, and Ad…
arXiv cs.AI Research & Papers
LLM-as-Judge in Education: A Curriculum-Grounded Marking Pipeline
arXiv cs.AI Research & Papers
DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Mod…
arXiv cs.AI Research & Papers
When Life Gives You BC, Make Q-functions: Extracting Q-values from Behavior Cloning for O…
arXiv cs.AI Research & Papers
Do We Still Need Humans in the Loop? Comparing Human and LLM Annotation in Active Learnin…
arXiv cs.AI Research & Papers
SP-GCRL: Influence Maximization on Incomplete Social Graphs
arXiv cs.AI Research & Papers
Prefill/Decode-Aware Evaluation of LLM Inference on Emerging AI Accelerators
arXiv cs.AI Research & Papers
Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety