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
Constraint-Aware Hierarchical Search for Regulation-Driven Fine-Grained Classification
arXiv cs.AI Research & Papers
Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories
arXiv cs.AI Research & Papers
Abstractiveness Metrics for Evaluating Text Summarization: A Refined Formulation with Emp…
arXiv cs.AI Research & Papers
Weight-Adjusted Gradients Reveal Parameter Importance and Failure Modes in LLMs
arXiv cs.AI Research & Papers
Lightning Fast Matching Dependency Discovery with Desbordante
arXiv cs.AI Research & Papers
Multi-Scale Convolution with Optimal Transport Attention Effect on Multivariate Time Seri…
arXiv cs.AI Research & Papers
To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Rein…
arXiv cs.AI Research & Papers
Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrializ…
arXiv cs.AI Research & Papers
PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM In…
arXiv cs.AI Research & Papers
MDQEC-QAS: Meta-Decoding for Quantum Error Correction with Hardware-Aware VQC Search and …
arXiv cs.AI Research & Papers
Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classification
arXiv cs.AI Research & Papers
Answer-Conditioned Chain-of-Thought Distillation for Few-Shot Industrial Vision with Smal…
arXiv cs.AI Research & Papers
Unlocking Parallelism in Autoregressive Language Models via Speculative Decoding with Pro…
arXiv cs.AI Research & Papers
Auditing Construct Overlap in Explainable Machine Learning: Evidence from Burnout-Depress…
arXiv cs.AI Research & Papers
STEC: Evidence Compression for Deep Search in Open-domain Multi-Hop QA
arXiv cs.AI Research & Papers
Instruction Set and Language for Hypergraphs
arXiv cs.AI Research & Papers
World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning
arXiv cs.AI Research & Papers
Anamnesis: An Open-Source Platform for Large-Scale Backstory-Conditioned Survey Simulation
arXiv cs.AI Research & Papers
MemDecay: Region-Aware KV Cache Eviction for Efficient LLM Agent Inference
arXiv cs.AI Research & Papers
DiffUE: Enhancing Utility-Unlearnability Trade-off of Unlearnable Examples via Diffusion …
arXiv cs.AI Research & Papers
Information-seeking failures of large language models in agentic clinical reasoning
arXiv cs.AI Research & Papers
When Does Restricting a Coding Agent to execute_code Help? A Regime $\times$ Agent-Design…
arXiv cs.AI Research & Papers
Tool-Adaptive LLM Reranker
arXiv cs.AI Research & Papers
Motif: Discovering and Automating Personal Web Workflows
arXiv cs.AI Research & Papers
Towards Autonomous and Auditable Medical Imaging Model Development
arXiv cs.AI Research & Papers
Conditional Optimal Bridge for Riemannian Activation Steering
arXiv cs.AI Research & Papers
Comparing Socio-technical Design Principles with Guidelines for Human-centered AI
arXiv cs.AI Research & Papers
Calibrated e-CUSUM Decoding for Quantized Reasoning Models: Why Token Log-Probability Is …
arXiv cs.AI Research & Papers
Confining Nondeterminism: AI-Driven Research Systems as DBMSs for Reliable, Non-Wasteful,…
arXiv cs.AI Research & Papers
Temporary Authority, Permanent Effects: Commit-Time Authorization for LLM Agents