Español

Explorar

Noticias de IA

22114 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
The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric …
arXiv cs.AI Research & Papers
Instrumented data for causal scientific machine learning
arXiv cs.AI Research & Papers
More Bang for the Buck: Improving the Inference of Large Language Models at a Fixed Budge…
arXiv cs.AI Research & Papers
Agentic multi-fidelity learning of quasiparticle and excitonic properties
arXiv cs.AI Research & Papers
Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence
arXiv cs.AI Research & Papers
Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team …
arXiv cs.AI Research & Papers
FF-JEPA: Long-Horizon Planning in World Models with Latent Planners
arXiv cs.AI Research & Papers
SLMJury: Can Small Language Models Judge as Well as Large Ones?
arXiv cs.AI Research & Papers
Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Ast…
arXiv cs.AI Research & Papers
Multi-planar 2D-U-Net Segmentation of 3D-CT Abdominal Organs augmented by Spatial Occurre…
arXiv cs.AI Research & Papers
Attention at the Theoretical Minimum: A Mathematics of Arrays Framework for Memory-Optima…
arXiv cs.AI Research & Papers
MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials …
arXiv cs.AI Research & Papers
Rosetta Memory: Adaptive Memory for Cross-LLM Agents
arXiv cs.AI Research & Papers
MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models
arXiv cs.AI Research & Papers
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large La…
arXiv cs.AI Research & Papers
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
arXiv cs.AI Research & Papers
How Much Dense Attention is Necessary? Oracle-Guided Sparse Prefill for Full/GQA Layers i…
arXiv cs.AI Research & Papers
EvoCSFL: Surrogate-Assisted Evolutionary Client Selection for Efficient and Robust Federa…
arXiv cs.AI Research & Papers
Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Int…
arXiv cs.AI Research & Papers
TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research
arXiv cs.AI Research & Papers
Adversarial Robustness of Activation Steering in Large Language Models
arXiv cs.AI Research & Papers
DSFNet: Learning Dual-Domain Spectral Operators for Multi-Modality Spatio-Temporal Foreca…
arXiv cs.AI Research & Papers
BCG-FM: A Foundation Model for Ambient Cardiac Health Sensing
arXiv cs.AI Research & Papers
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
arXiv cs.AI Research & Papers
Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environme…
arXiv cs.AI Research & Papers
Systematic LLM Translation of Legacy Scientific Code to Differentiable Frameworks: Applic…
arXiv cs.AI Research & Papers
A Hierarchical Feature Engineering Framework for Automated Classification of Phonotraumat…
arXiv cs.AI Research & Papers
Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents
arXiv cs.AI Research & Papers
Seq103: A Unified Neuroevolution Framework for Compact Sequence Architecture Discovery
arXiv cs.AI Research & Papers
MM-Matryoshka: Towards Budget-Elastic Visual Document Retrieval via a 2D Multimodal Matry…