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
SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking
arXiv cs.AI Research & Papers
StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in …
arXiv cs.AI Research & Papers
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
arXiv cs.AI Research & Papers
When Optimization Becomes Manipulation: Defending Generative Search against Malicious Gen…
arXiv cs.AI Research & Papers
Privacy-Preserving Topology-Guided Safety for LLM-Based Multi-Agent Systems via Federated…
arXiv cs.AI Research & Papers
Toward Collective-Centric Evaluation of Preference Inference for Participatory Democracy
arXiv cs.AI Research & Papers
Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL
arXiv cs.AI Research & Papers
The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors
arXiv cs.AI Research & Papers
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric …
arXiv cs.AI Research & Papers
ExecRetrieval: Measuring the Functional-Correctness Gap in Code-Embedding Retrieval
arXiv cs.AI Research & Papers
X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation System
arXiv cs.AI Research & Papers
A Computationally Feasible Framework for Causal Probabilistic Explanation
arXiv cs.AI Research & Papers
Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box…
arXiv cs.AI Research & Papers
Judging LLM-as-a-Judge: Concerning Rubric Artifacts in LLM-based Automated Text Generatio…
arXiv cs.AI Research & Papers
The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent…
arXiv cs.AI Research & Papers
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation
arXiv cs.AI Research & Papers
Counterexamples as Feedback for Agent Self-Correction
arXiv cs.AI Research & Papers
Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Gro…
arXiv cs.AI Research & Papers
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hy…
arXiv cs.AI Research & Papers
Environment Evolution for Terminal Agents
arXiv cs.AI Research & Papers
FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Predicti…
arXiv cs.AI Research & Papers
Instruction Duplication as an Inference-Time Control Primitive
arXiv cs.AI Research & Papers
InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimoda…
arXiv cs.AI Research & Papers
Spurious Advantage Hidden in GRPO
arXiv cs.AI Research & Papers
More Criticism Does Not Make a Better Review: EquiReview-R
arXiv cs.AI Research & Papers
Interface-Induced Trajectory Censoring
arXiv cs.AI Research & Papers
Towards Numerical TOHTN Planning with SMT-based HTN-SAT Encoding
arXiv cs.AI Research & Papers
Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image Auditing
arXiv cs.AI Research & Papers
Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting
arXiv cs.AI Research & Papers
From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Dec…