Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Efficiency Hallucination: Formalizing and Measuring Behavioral Calibration in LLM-Based C…
arXiv cs.AI Research & Papers
A Responsive Present, a Shared Past, a Social Other: Teens' Overreliance on Companion AI …
arXiv cs.AI Research & Papers
Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language Models
arXiv cs.AI Research & Papers
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
arXiv cs.AI Research & Papers
Adaptive Phase-Switching for Communication-Efficient Federated LoRA Fine-Tuning
arXiv cs.AI Research & Papers
Personalizing Personal Health Interfaces: Co-Design with Generative AI
arXiv cs.AI Research & Papers
Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent Communicat…
arXiv cs.AI Research & Papers
Robust and Efficient Communication for Multi-Agent Learning
arXiv cs.AI Research & Papers
When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learni…
arXiv cs.AI Research & Papers
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
arXiv cs.AI Research & Papers
Specifying Reward Functions for RL Without Environment Sampling
arXiv cs.AI Research & Papers
PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection
arXiv cs.AI Research & Papers
IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Traje…
arXiv cs.AI Research & Papers
Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatica…
arXiv cs.AI Research & Papers
VeriDx: Earning the Right to Diagnose with Disease-Centric Verification
arXiv cs.AI Research & Papers
MOSCOPT: Mixture-of-Skills Collective Optimization for LLM Agents
arXiv cs.AI Research & Papers
AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical …
arXiv cs.AI Research & Papers
DynSTEER: Dynamic Stage-wise Trajectory Evaluation and Execution-time Review for Agents
arXiv cs.AI Research & Papers
Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multip…
arXiv cs.AI Research & Papers
IWC-Bench: Evaluating Web Application Generation from a Software Testing Perspective
arXiv cs.AI Research & Papers
Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with…
arXiv cs.AI Research & Papers
Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models
arXiv cs.AI Research & Papers
Spook the Machine: Gamified Exploration of Human Imagination of Machine Fear
arXiv cs.AI Research & Papers
Interpreting hierarchical organisation of speaker embeddings
arXiv cs.AI Research & Papers
Authorship attribution and aesthetic evaluation of AI poetry: a case study with Haiku
arXiv cs.AI Research & Papers
Rolling Day-Wise Mortality Prediction in Critically Ill Patients With AKI on CRRT Utilizi…
arXiv cs.AI Research & Papers
Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized …
arXiv cs.AI Research & Papers
LePlanner: An Iterative Amortized Controller For World Models
arXiv cs.AI Research & Papers
FedLTLib: A Comprehensive Benchmark for Federated Long-Tail Learning
arXiv cs.AI Research & Papers
Multilingual Agent System for Inclusive Wildfire Evacuation Guidance