Español

Explorar

Noticias de IA

29341 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
Goose: Anisotropic Speculation Trees for Training-Free Speculative Decoding
arXiv cs.AI Research & Papers
Not an A11y: How Android Accessibility Exposes Mobile AI Agents to Indirect Prompt Inject…
arXiv cs.AI Research & Papers
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards
arXiv cs.AI Research & Papers
MedPixel: A Unified Pixel-Language Model for Medical Reasoning and Segmentation
arXiv cs.AI Research & Papers
Ultraconstructive Model Theory via Bounded Adversarial Finite Structures
arXiv cs.AI Research & Papers
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for…
arXiv cs.AI Research & Papers
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
arXiv cs.AI Research & Papers
SuperNeuroMAT: An Efficient Matrix-based Simulator for Spiking Neural Networks
arXiv cs.AI Research & Papers
CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
arXiv cs.AI Research & Papers
C2L-Net: A Data-Driven Model for State-of-Charge Estimation of Lithium-Ion Batteries Duri…
arXiv cs.AI Research & Papers
Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Mode…
arXiv cs.AI Research & Papers
Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasonin…
arXiv cs.AI Research & Papers
Time-Series Forecasting in Safety-Critical Environments: An Open-Source Package for EU-AI…
arXiv cs.AI Research & Papers
DRBENCHER: Can Your Agent Identify the Entity, Retrieve Its Properties and Do the Math?
arXiv cs.AI Research & Papers
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
arXiv cs.AI Research & Papers
FinTrace: Holistic Trajectory-Level Evaluation of LLM Tool Calling for Long-Horizon Finan…
arXiv cs.AI Research & Papers
Mesh-Attention: A New Communication-Efficient Distributed Attention with Improved Data Lo…
arXiv cs.AI Research & Papers
A Statistical Framework for Auditing Behavioral Dependence and Induced Bias in LLM Judges
arXiv cs.AI Research & Papers
Temporal Sepsis Modeling: a Relational and Explainable-by-Design Framework
arXiv cs.AI Research & Papers
ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems
arXiv cs.AI Research & Papers
Reproducing and Stress-Testing Two Approaches to LLM Reasoning Reliability: Test-Time Pro…
arXiv cs.AI Research & Papers
NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
arXiv cs.AI Research & Papers
A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scali…
arXiv cs.AI Research & Papers
MonitorBench: A Comprehensive Benchmark for Chain-of-Thought Monitorability in Large Lang…
arXiv cs.AI Research & Papers
Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection…
arXiv cs.AI Research & Papers
Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehens…
arXiv cs.AI Research & Papers
Adaptive Symmetry Discovery for Dynamical System Identification
arXiv cs.AI Research & Papers
Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
arXiv cs.AI Research & Papers
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule O…
arXiv cs.AI Research & Papers
Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Pr…