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
From Detection to Mechanism: Cross-Attention Graph Neural Networks Enable Drug-Drug Inter…
arXiv cs.AI Research & Papers
MetaboT: An LLM-based Multi-Agent Frameworkfor Interactive Analysis of Mass SpectrometryM…
arXiv cs.AI Research & Papers
The Fragility of Chain-of-Thought Monitoring Across Typologically Diverse Languages
arXiv cs.AI Research & Papers
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
arXiv cs.AI Research & Papers
Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empiri…
arXiv cs.AI Research & Papers
Let the Results Speak: A Replication-First Paradigm for LLM Behavioral Benchmarking
arXiv cs.AI Research & Papers
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Decep…
arXiv cs.AI Research & Papers
Smaller, Younger, and More Impactful: How AI-Assisted Writing Transforms Research Teams
arXiv cs.AI Research & Papers
ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning
arXiv cs.AI Research & Papers
Singular Vectors of Attention Heads Align with Features
arXiv cs.AI Research & Papers
KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evalua…
arXiv cs.AI Research & Papers
Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting
arXiv cs.AI Research & Papers
Tool Forge: A Validation-Carrying Toolchain for Governed Agentic Execution
arXiv cs.AI Research & Papers
VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning
arXiv cs.AI Research & Papers
I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech …
arXiv cs.AI Research & Papers
SMILE-Next: Teaching Large Language Models to Detect, Classify, and Reason about Laughter
arXiv cs.AI Research & Papers
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reason…
arXiv cs.AI Research & Papers
LLM Watermark Evasion via Bias Inversion
arXiv cs.AI Research & Papers
DEPART: DEcomposing PARiTy across Multilingual LLMs
arXiv cs.AI Research & Papers
BenGER: Benchmarking LLM Systems on Subsumption-Based Legal Reasoning in German Law
arXiv cs.AI Research & Papers
SmartIterator: Visual Analytics Workflows for Supervising Unsupervised Data Grouping
arXiv cs.AI Research & Papers
ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy…
arXiv cs.AI Research & Papers
InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Tra…
arXiv cs.AI Research & Papers
How Far Can Disaggregation Go? A Design-Space Exploration of Attention-FFN Disaggregation…
arXiv cs.AI Research & Papers
Hybrid Neural World Models
arXiv cs.AI Research & Papers
Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization
arXiv cs.AI Research & Papers
On the Origin of Synthetic Information by Means of Steganographic Inheritance
arXiv cs.AI Research & Papers
DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM…
arXiv cs.AI Research & Papers
Discovery Agents for Real-Time Analytics: Toward Proactive Insight Systems
arXiv cs.AI Research & Papers
VULPO: Context-Aware Vulnerability Detection via On-Policy LLM Optimization