Español

Explorar

Noticias de IA

21031 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
VaaWIT: Visual-Aware Adaptation of Large Language Models for Multilingual Web Image Trans…
arXiv cs.AI Research & Papers
The Path Matters: Learning a Token-Commitment Policy for Diffusion Language Models
arXiv cs.AI Research & Papers
FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models
arXiv cs.AI Research & Papers
Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retr…
arXiv cs.AI Research & Papers
HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos
arXiv cs.AI Research & Papers
From Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language M…
arXiv cs.AI Research & Papers
Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Lang…
arXiv cs.AI Research & Papers
Credit Assignment with Resets in Language Model Reasoning
arXiv cs.AI Research & Papers
Zero-Shot Parkinson's Disease Detection from Speech: Comparing Large Audio and Language M…
arXiv cs.AI Research & Papers
One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adver…
arXiv cs.AI Research & Papers
Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Refl…
arXiv cs.AI Research & Papers
ATWL: A Formal Language for Representing, Comparing, and Reusing Visual Analytics Workflo…
arXiv cs.AI Research & Papers
When Reasoning Hurts: Source-Aware Evaluation of Frontier LLMs for Clinical SOAP Note Gen…
arXiv cs.AI Research & Papers
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series…
arXiv cs.AI Research & Papers
Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steer…
arXiv cs.AI Research & Papers
APT-Agent: Automated Penetration Testing using Large Language Models
arXiv cs.AI Research & Papers
Persona-Model Collapse in Emergent Misalignment
arXiv cs.AI Research & Papers
L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting
arXiv cs.AI Research & Papers
MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing
arXiv cs.AI Research & Papers
Interpretation, Learning, and Empathy as One Constraint: A Residual-Adequacy Architecture…
arXiv cs.AI Research & Papers
Finite-Particle Convergence Rates for Conservative and Non-Conservative Drifting Models
arXiv cs.AI Research & Papers
Scale When Needed: Adaptive Neuron-level Mixed Precision Quantization Aware Training
arXiv cs.AI Research & Papers
GL-LFGNN:A Global-Local Dual-branch Causal Graph Neural Network Based on Liang-Kleeman In…
arXiv cs.AI Research & Papers
Multi-Agent Specification-based Metamorphic Testing of FMU-Based Simulations
arXiv cs.AI Research & Papers
Intrinsically Interpretable Attention via Sparse Post-Training
arXiv cs.AI Research & Papers
Smart Timing for Mining: A Deep Learning Framework for Bitcoin Hardware ROI Prediction
arXiv cs.AI Research & Papers
Evidence-Linked Radiology Reporting: A Human-Supervised Reference Architecture for Struct…
arXiv cs.AI Research & Papers
PageLLM: A Multi-Grained Reward Framework for Whole-Page Optimization with Large Language…
arXiv cs.AI Research & Papers
Uni-DPO: A Unified Paradigm for Dynamic Preference Optimization of LLMs
arXiv cs.AI Research & Papers
FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model