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
GRPO is Secretly a Process Reward Model
arXiv cs.AI Research & Papers
Representation Alignment Rests on Linear Structure
arXiv cs.AI Research & Papers
LogDx-CI: Benchmarking Log Reduction Tools for LLM Root-Cause Diagnosis
arXiv cs.AI Research & Papers
Continuity and Ordinality Matter: Constraining Time Series Tokens for Effective Time Seri…
arXiv cs.AI Research & Papers
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
arXiv cs.AI Research & Papers
Mechanistic origins of catastrophic forgetting: why RL preserves circuits better than SFT?
arXiv cs.AI Research & Papers
Topological Order in Neural Wavefunctions
arXiv cs.AI Research & Papers
Evaluating Dataset Watermarking for Fine-tuning Traceability of Customized Diffusion Mode…
arXiv cs.AI Research & Papers
MiAD: Mirage Atom Diffusion for De Novo Crystal Generation
arXiv cs.AI Research & Papers
Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions
arXiv cs.AI Research & Papers
An accuracy-aware extension to LRP-based pruning for CNNs to prevent cascading accuracy d…
arXiv cs.AI Research & Papers
How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Ca…
arXiv cs.AI Research & Papers
LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
arXiv cs.AI Research & Papers
Transcribing Children's Speech: ASR Performance and Obtaining Reliable Orthographic Trans…
arXiv cs.AI Research & Papers
GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling
arXiv cs.AI Research & Papers
Orthogonal Concept Erasure for Diffusion Models
arXiv cs.AI Security & Safety
Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening
arXiv cs.AI Research & Papers
Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation
arXiv cs.AI Research & Papers
SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations
arXiv cs.AI Research & Papers
Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Compon…
arXiv cs.AI Research & Papers
ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive In…
arXiv cs.AI Research & Papers
When Should Models Change Their Minds? Contextual Belief Management in Large Language Mod…
arXiv cs.AI Research & Papers
VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior T…
arXiv cs.AI Research & Papers
Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication …
arXiv cs.AI Research & Papers
KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning
arXiv cs.AI Research & Papers
Formalizing Mathematics at Scale
arXiv cs.AI Research & Papers
Toward AI Systems That Understand Self and Others: A Multi-Phase Inference Framework for …
arXiv cs.AI Research & Papers
Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation
arXiv cs.AI Research & Papers
SkillBrew: Multi-Objective Curation of Skill Banks for LLM Agents
arXiv cs.AI Research & Papers
Quantifying and Optimizing Simplicity via Polynomial Representations