Español

Explorar

Noticias de IA

27413 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
Verbatim Chunks Beat Extracted Artifacts: A Controlled Ablation of Memory Representations…
arXiv cs.AI Research & Papers
LLM-Powered AI Agent Systems and Their Applications in Industry
arXiv cs.AI Research & Papers
ANSR-DT: A Neuro-Symbolic Framework for Adaptive and Explainable Digital Twins
arXiv cs.AI Research & Papers
Learning Coordinated Preference for Multi-Objective Multi-Agent Reinforcement Learning
arXiv cs.AI Research & Papers
Flood and Harvest: The Provable Necessity of Trivia for Generating Valuable Mathematics v…
arXiv cs.AI Research & Papers
CottonLeafVision: An Explainable and Robust Deep Learning Framework for Cotton Leaf Disea…
arXiv cs.AI Research & Papers
Cross-Dataset Bloom Question Classification: Supervised Models and Prompted LLMs
arXiv cs.AI Research & Papers
A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecast…
arXiv cs.AI Research & Papers
AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Langua…
arXiv cs.AI Research & Papers
When Good Verifiers Go Bad: Self-Improving VLMs Can Regress on New Tasks
arXiv cs.AI Research & Papers
Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op…
arXiv cs.AI Research & Papers
The Coin Flip Judge? Reliability and Bias in LLM-as-a-Judge Evaluation
arXiv cs.AI Research & Papers
When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production…
arXiv cs.AI Research & Papers
Sensitivity Shaping for Latent Modeling
arXiv cs.AI Research & Papers
CARE: Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientif…
arXiv cs.AI Research & Papers
SIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World Model
arXiv cs.AI Research & Papers
TRACE: Trajectory-Routed Causal Memory for Delayed-Evidence Visuomotor Imitation
arXiv cs.AI Research & Papers
Fodor and Pylyshyn's Systematicity Challenge Still Stands
arXiv cs.AI Research & Papers
Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks
arXiv cs.AI Research & Papers
No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30…
arXiv cs.AI Research & Papers
PLAIground: SLO-Driven Runtime Model Selection for Compound AI Systems in the Edge-Cloud-…
arXiv cs.AI Research & Papers
Achieving Precise Text-To-Cypher Via Grounded Knowledge Graph Data Generation
arXiv cs.AI Research & Papers
Thinking Outside the [Chat]Box: Bridging Computer Science and Industrial Design for Cogni…
arXiv cs.AI Research & Papers
Pix2Pix-Hybrid: Structure-Guided Conditional Synthesis of Hajj Crowd Images with Multi-Ch…
arXiv cs.AI Research & Papers
DIFF-ERO: A Conformance-Aware Loss for Deep Learning in Process Mining
arXiv cs.AI Research & Papers
An Agentic Retrieval Framework for Autonomous Context-Aware Data Quality Assessment
arXiv cs.AI Research & Papers
Selective Agentic Recovery for UAV Autonomy with a Persistent Mission Runtime
arXiv cs.AI Research & Papers
Universal Manipulation Exoskeleton: Learning Compliant Whole-body Policies with Real-time…
arXiv cs.AI Research & Papers
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Mo…
arXiv cs.AI Research & Papers
OdysSim: Building Foundation Models for Human Behavior Simulation