Español

Explorar

Noticias de IA

30696 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
Logic-Guided Data Extraction with Answer Set Programming and Large Language Models
arXiv cs.AI Research & Papers
Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large…
arXiv cs.AI Research & Papers
AdaRoPE: Not All Attention Heads Should Rotate and Scale Equally
arXiv cs.AI Research & Papers
Lifted Representation Hypothesis in Language Models
arXiv cs.AI Research & Papers
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv cs.AI Research & Papers
Understanding Developer Pain Points in Federated Learning: Insights from Stack Overflow a…
arXiv cs.AI Research & Papers
Information Discernment in Large Language Models
arXiv cs.AI Research & Papers
Adaptive Capitulation: A Structural Failure Mode of LLM Responses in Vulnerability Contex…
arXiv cs.AI Research & Papers
FormulaSPIN: Self-Play Fine-Tuning for Natural Language to Spreadsheet Formula Generation
arXiv cs.AI Research & Papers
Benchmarking Confidential GPU Inference on NVIDIA H100 under Intel TDX
arXiv cs.AI Research & Papers
Hybrid LSTM-Graph Neural Framework for Robust Financial Fraud Detection and Adversarial R…
arXiv cs.AI Research & Papers
Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Sear…
arXiv cs.AI Research & Papers
PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization
arXiv cs.AI Research & Papers
Reference-Free Evaluation of Reasoning in Open-Ended Question Answering
arXiv cs.AI Research & Papers
SLPO: Scaling Latent Reasoning via a Surrogate Policy
arXiv cs.AI Research & Papers
PhenSPINE: A Standardized Benchmark for Spine Pathology Diagnosis
arXiv cs.AI Research & Papers
Personalized Recommendation Tool Learning via Autonomous Language Agents
arXiv cs.AI Security & Safety
An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intellige…
arXiv cs.AI Research & Papers
The World Model Remembers, the Actor Forgets: Dream Rehearsal for Continual Model-Based RL
arXiv cs.AI Research & Papers
Learning the Arabic Dialect Continuum as a Continuous Space: A Regression Approach to Spe…
arXiv cs.AI Research & Papers
An Isotropy-Preserving Spectral Cap for Muon: Theory and Three Case Studies
arXiv cs.AI Research & Papers
Physics-Aware Complex-Valued State Space Model with Scattering-Prior Feature Modulation f…
arXiv cs.AI Research & Papers
OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optim…
arXiv cs.AI Research & Papers
Beyond Fail-to-Pass: Iterative Hardening of Co-Generated Bug Reproduction Tests and Fixes
arXiv cs.AI Research & Papers
Auto-Fill: Learning to Predict Missing Values Accurately with Specialist Language Models
arXiv cs.AI Research & Papers
Memory-Augmented Multimodal Large Language Models for Small Object Understanding in Strea…
arXiv cs.AI Research & Papers
REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement …
arXiv cs.AI Research & Papers
PRISM-DR: Per-lesion Retinal Inference with Specialist Models for Diabetic Retinopathy
arXiv cs.AI Research & Papers
Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
arXiv cs.AI Research & Papers
OSVE: One Step Video Editing with One Step Diffusion Models