Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Ne…
arXiv cs.AI Research & Papers
Predicting Wind Turbine Power Using Machine Learning and Weather Forecasts
arXiv cs.AI Research & Papers
From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning C…
arXiv cs.AI Research & Papers
SCIRIGOR:Evaluating Open-Ended Scientific Analysis Beyond Final Scores
arXiv cs.AI Research & Papers
Causal Attribution for Agentic Decisions: Estimators, Coupling, and a Traceability Specif…
arXiv cs.AI Research & Papers
Generator-Independent Runtime Assurance under Partial Observation
arXiv cs.AI Research & Papers
DAREBench: Deployment-Aware and Reliable Evaluation of Models as Agents
arXiv cs.AI Research & Papers
Generating Instance Generators in PDDL Planning
arXiv cs.AI Research & Papers
We Built a Mirror and Mistook It for a Mind: Causal Liability and the Fallacy of AI Consc…
arXiv cs.AI Research & Papers
NormViz: A Benchmark and Framework for Grounding Multimodal Reasoning in Global Cultures
arXiv cs.AI Research & Papers
AgentBrew: Offline Tool-Use Agent Learning from Raw Real-World Trajectories
arXiv cs.AI Research & Papers
When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal Inf…
arXiv cs.AI Research & Papers
More Than Mimicking Reviewers: Evaluating LLMs for Pre-Submission Peer Review
arXiv cs.AI Research & Papers
Beyond Final Decisions: A Process-Centric Benchmark for Transparent AI-Assisted Peer Revi…
arXiv cs.AI Research & Papers
Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Ma…
arXiv cs.AI Research & Papers
Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in Ea…
arXiv cs.AI Research & Papers
Distilling Vision-Language Models for On-Device Fire Understanding
arXiv cs.AI Research & Papers
Learning Counterfactual World Models for Embodied Reasoning under Partial Observability
arXiv cs.AI Research & Papers
Exposing Weaknesses in Emotion Recognition in Conversations
arXiv cs.AI Research & Papers
The Normalization of Deviance in AI Development
arXiv cs.AI Research & Papers
Recovering Temporal and Geographic Signals from Language Model Embeddings
arXiv cs.AI Research & Papers
Beyond Prompts: Measuring and Optimizing LLM Tool-Agent Harnesses
arXiv cs.AI Research & Papers
From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational As…
arXiv cs.AI Research & Papers
Agentic Pressure: The Endogenous Entropy of Reliable Autonomy
arXiv cs.AI Research & Papers
Learning transferable human physiology from two million hours of sleep with SleepFM-2
arXiv cs.AI Research & Papers
The Failure Happens Before the Drift: The Social Dynamics of Values in LLM Agent Societies
arXiv cs.AI Research & Papers
Beyond "AI Helps Humans": Decision-Targeted Evaluation Design for Human-Agent Teams in th…
arXiv cs.AI Research & Papers
Deep belief networks are exact
arXiv cs.AI Research & Papers
SciLitBench: Benchmark and Design Principles for LLM-Powered Systematic Literature Reviews
arXiv cs.AI Research & Papers
Reasoning-Aware Compression: Identifying and Protecting Vulnerable Reasoning Circuits for…