Español

Explorar

Noticias de IA

27413 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
Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs
arXiv cs.AI Research & Papers
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable Origami
arXiv cs.AI Research & Papers
Accelerating Skill Assessment in Chess: A Drift-Diffusion-Enhanced Elo Rating System
arXiv cs.AI Research & Papers
Agentic Analysis for Agentic Infrastructure: An LLM-Powered Pipeline for Comparative Gove…
arXiv cs.AI Research & Papers
Refusal Lives Downstream of Persona in Chat Models
arXiv cs.AI Research & Papers
Life After Benchmark Saturation: A Case Study of CORE-Bench
arXiv cs.AI Research & Papers
IDEA: Insensitive to Dynamics Mismatch via Effect Alignment for Sim-to-Real Transfer in M…
arXiv cs.AI Research & Papers
SpaceRipple: Lightweight Semantic Delivery for Mission-Oriented LEO Earth Observation Sat…
arXiv cs.AI Research & Papers
\textsc{DiARC}: Distinguishing Positive and Negative Samples Helps Improving ARC-like Rea…
arXiv cs.AI Research & Papers
Revisiting the Platonic Representation Hypothesis: An Aristotelian View
arXiv cs.AI Research & Papers
Improved Bounds for Private and Robust Alignment
arXiv cs.AI Research & Papers
Patent Representation Learning via Self-supervision
arXiv cs.AI Research & Papers
Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Languag…
arXiv cs.AI Research & Papers
Byzantine-Robust Aggregation for Securing Decentralized Federated Learning
arXiv cs.AI Research & Papers
Wearable Device-Based Real-Time Monitoring of Physiological Signals: Evaluating Cognitive…
arXiv cs.AI Research & Papers
Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Lib…
arXiv cs.AI Research & Papers
Joint Reward Modeling: Internalizing Chain-of-Thought for Efficient Visual Reward Models
arXiv cs.AI Research & Papers
Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoenc…
arXiv cs.AI Research & Papers
AI Healthcare Chatbots as Information Infrastructure: A Large-Scale Study of User-Reporte…
arXiv cs.AI Research & Papers
Rotary Position Encodings for Graphs
arXiv cs.AI Research & Papers
Through the Looking Glass: A Dual Perspective on Weakly-Supervised Few-Shot Segmentation
arXiv cs.AI Research & Papers
NuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Lan…
arXiv cs.AI Research & Papers
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-A…
arXiv cs.AI Research & Papers
Inverse Design of Compact and Wideband Inverted Doherty Power Amplifiers Using Deep Learn…
arXiv cs.AI Research & Papers
Event-Aware Instructed Assistant for Referring Video Segmentation
arXiv cs.AI Research & Papers
Decision-Aligned Evaluation of Uncertainty Quantification
arXiv cs.AI Research & Papers
ReaORE: Reasoning-Guided Progressive Open Relation Extraction Empowered by Large Reasonin…
arXiv cs.AI Research & Papers
Auditing Framing-Sensitive Behavioral Instability in Large Language Models for Mental Hea…
arXiv cs.AI Research & Papers
Scaling Multi-Reference Image Generation with Dynamic Reward Optimization
arXiv cs.AI Research & Papers
GEOALIGN: Geometric Rollout Curation for Robust LLM Reinforcement Learning