Español

Explorar

Noticias de IA

30329 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 Meta-Thought to Execution: Cognitively Aligned Post-Training for Generalizable and R…
arXiv cs.AI Research & Papers
TANDEM: Temporal-Aware Neural Detection for Multimodal Hate Speech
arXiv cs.AI Research & Papers
SCOPE: Prompt Evolution for Enhancing Agent Effectiveness
arXiv cs.AI Research & Papers
Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agents
arXiv cs.AI Research & Papers
Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
arXiv cs.AI Research & Papers
Causal-JEPA: Learning World Models through Object-Level Latent Masking
arXiv cs.AI Research & Papers
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
arXiv cs.AI Research & Papers
RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large L…
arXiv cs.AI Research & Papers
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-…
arXiv cs.AI Research & Papers
SCoOP: Semantic Consistent Opinion Pooling for Uncertainty Quantification in Multiple Vis…
arXiv cs.AI Research & Papers
MemCollab: Cross-Model Memory Collaboration via Contrastive Trajectory Distillation
arXiv cs.AI Research & Papers
Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in M…
arXiv cs.AI Research & Papers
Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configurat…
arXiv cs.AI Research & Papers
SVSR: A Self-Verification and Self-Rectification Paradigm for Multimodal Reasoning
arXiv cs.AI Research & Papers
SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scient…
arXiv cs.AI Research & Papers
Human-Guided Harm Recovery for Computer Use Agents
arXiv cs.AI Research & Papers
AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligence
arXiv cs.AI Research & Papers
NOVA: Fundamental Limits of Knowledge Discovery Through AI
arXiv cs.AI Security & Safety
Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
arXiv cs.AI Research & Papers
Are LLMs Socially Adaptive? Contrasting Belief Evolution in Large Language Models and Hum…
arXiv cs.AI Research & Papers
Crafting Desirable Climate Trajectories with RL Explored Socio-Environmental Simulations
arXiv cs.AI Research & Papers
GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object Det…
arXiv cs.AI Research & Papers
PhoneWorld: Scaling Phone-Use Agent Environments
arXiv cs.AI Research & Papers
Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generati…
arXiv cs.AI Research & Papers
Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Mul…
arXiv cs.AI Research & Papers
Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference
arXiv cs.AI Research & Papers
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignmen…
arXiv cs.AI Research & Papers
TRACER: Persistent Regularization for Robust Multimodal Finetuning
arXiv cs.AI Research & Papers
The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
arXiv cs.AI Research & Papers
EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents