Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
arXiv cs.AI Research & Papers
BioELX: Cross-lingual Biomedical Entity Linking via Alias-based Retrieval and LLM Ranking
arXiv cs.AI Research & Papers
The Alignment Floor: When Persona Customization Is Safe
arXiv cs.AI Research & Papers
From Instructor to Collaborator: What a 90-Participant Study Reveals about Human-Agent Co…
arXiv cs.AI Research & Papers
From AR to Diffusion: Efficiently Adapting Large Language Models with Strictly Causal and…
arXiv cs.AI Research & Papers
DSSE: a drone swarm search environment
arXiv cs.AI Research & Papers
Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization
arXiv cs.AI Research & Papers
EvoSpec: Evolving Speculative Decoding via Real-Time Vocabulary and Parameter AdaptationT…
arXiv cs.AI Research & Papers
Verifiable Process Rewards for Agentic Reasoning
arXiv cs.AI Research & Papers
Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and L…
arXiv cs.AI Research & Papers
Using Zero-Shot LLM-Generated Survey Data for Geographically Explicit Population Synthesis
arXiv cs.AI Research & Papers
Short-Term Gain, Long-Term Fragility: AI Labor Substitution and the Erosion of Sustainabl…
arXiv cs.AI Research & Papers
Tackling Multimodal Learning Challenges with Mixture-of-Expert: A Survey
arXiv cs.AI Research & Papers
Heterogeneous Multi-Agent Modeling for Measurement and Network Analysis of the Data Servi…
arXiv cs.AI Research & Papers
Prominence-Stratified Failure Modes in Retrieval-Augmented Commercial Recommendation: A 3…
arXiv cs.AI Research & Papers
AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems
arXiv cs.AI Research & Papers
Comparative Analysis of Liquid Neural Networks and LSTM for Sequential Pattern Recognitio…
arXiv cs.AI Research & Papers
HEAL: Resilient and Self-* Hub-based Learning
arXiv cs.AI Research & Papers
Debate Helps Weak Judges Reward Stronger Models
arXiv cs.AI Research & Papers
Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Sys…
arXiv cs.AI Research & Papers
The Future of Facts: Tracing the Factual Generation-Verification Gap
arXiv cs.AI Research & Papers
Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for A…
arXiv cs.AI Research & Papers
Who Uses AI? Platform Selection and the Measurement of Occupational AI Exposure
arXiv cs.AI Research & Papers
Aligning LLMs with Human Uncertainty: A Beta-Bernoulli Calibrator for LLM Forecasting
arXiv cs.AI Research & Papers
UserHarness: Harnessing User Minds for Stronger Agent Theory-of-Mind
arXiv cs.AI Research & Papers
Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancie…
arXiv cs.AI Research & Papers
High-Fidelity Industrial Crash Dynamics Prediction via Geometry-Aware Operator Learning w…
arXiv cs.AI Research & Papers
Delay-Aware Reinforcement Learning for Highway On-Ramp Merging under Stochastic Communica…
arXiv cs.AI Research & Papers
ChildEval: When large language models meet children's personalities
arXiv cs.AI Research & Papers
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions