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
Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, a…
arXiv cs.AI Research & Papers
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Secu…
arXiv cs.AI Research & Papers
SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow
arXiv cs.AI Research & Papers
PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing
arXiv cs.AI Research & Papers
Xetrieval: Mechanistically Explaining Dense Retrieval
arXiv cs.AI Research & Papers
The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions vi…
arXiv cs.AI Research & Papers
OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster…
arXiv cs.AI Research & Papers
ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for …
arXiv cs.AI Research & Papers
When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role…
arXiv cs.AI Research & Papers
TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evalu…
arXiv cs.AI Research & Papers
Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent Trajectories
arXiv cs.AI Research & Papers
It`s All About Speed: AI`s Impact on Workflow in Music Production
arXiv cs.AI Research & Papers
Meta-Programming for Linear-time Temporal Answer Set Programming
arXiv cs.AI Research & Papers
Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
arXiv cs.AI Research & Papers
Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation
arXiv cs.AI Research & Papers
From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
arXiv cs.AI Research & Papers
Finding DoRI: Discovery of Retained Images in Diffusion Models
arXiv cs.AI Research & Papers
Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents
arXiv cs.AI Research & Papers
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
arXiv cs.AI Research & Papers
Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability
arXiv cs.AI Research & Papers
Conformal Certification of Reasoning Trace Prefixes
arXiv cs.AI Research & Papers
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
arXiv cs.AI Research & Papers
Enhancing Multi-Agent Communication through Attention Steering with Context Relevance
arXiv cs.AI Research & Papers
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
arXiv cs.AI Research & Papers
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents
arXiv cs.AI Research & Papers
Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A P…
arXiv cs.AI Research & Papers
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
arXiv cs.AI Research & Papers
Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientifi…
arXiv cs.AI Research & Papers
A comparative study of transformer-based embeddings for topic coherence
arXiv cs.AI Research & Papers
NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs