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
Evaluating LLMs on Conversational Text-to-SQL under Chain Ambiguity and Intent Drift
arXiv cs.AI Research & Papers
Autoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
arXiv cs.AI Research & Papers
Personalized Group Relative Policy Optimization for Heterogenous Preference Alignment
arXiv cs.AI Research & Papers
CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action
arXiv cs.AI Research & Papers
Conformal Risk-Averse Decision Making with Optimized Certainty Equivalent Risk Control
arXiv cs.AI Research & Papers
VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learn…
arXiv cs.AI Research & Papers
Generative AI Expands the Intellectual Reach of Course Based Undergraduate Research Exper…
arXiv cs.AI Research & Papers
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
arXiv cs.AI Research & Papers
If Agents Were Angels, No Governance Would Be Necessary: Out-of-Band Policy Enforcement a…
arXiv cs.AI Research & Papers
MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize
arXiv cs.AI Research & Papers
SpecMine: A Large-Scale Corpus of Spec-Driven Development Artifacts
arXiv cs.AI Research & Papers
Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning …
arXiv cs.AI Research & Papers
Optimal Adversarial Testing: Extracting Honest Test Results from Dishonest Test Takers
arXiv cs.AI Research & Papers
A Framework for Object-Centric Predictive Monitoring of Collaborative Processes
arXiv cs.AI Research & Papers
Nested Byte-Level Vocabularies Are Cheap to Deploy and Expensive to Share: A Pre-Register…
arXiv cs.AI Research & Papers
ARC-CT: Anatomy-Routed Contrastive Vision-Language Learning for 3D Chest CT
arXiv cs.AI Research & Papers
LongPIBench: A Long-Context Benchmark for Prompt Injection
arXiv cs.AI Research & Papers
PAPO: Stabilizing Rubric Integration Training via Decoupled Advantage Normalization
arXiv cs.AI Research & Papers
An Enclosed Mode Is a Gauge Choice: Topology Relative to Reach in Certified Code World Mo…
arXiv cs.AI Research & Papers
Learning a Size-Weight Frontier for Synthetic-Augmented Inference
arXiv cs.AI Research & Papers
Rethinking Vacuity for OOD Detection in Evidential Deep Learning
arXiv cs.AI Research & Papers
TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
arXiv cs.AI Research & Papers
AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics
arXiv cs.AI Research & Papers
A Probabilistic Interpretation of KV Cache Eviction
arXiv cs.AI Research & Papers
PanelShield: Verifiable Closed-Loop Safe Planning for Robotic Industrial Panel Operation
arXiv cs.AI Research & Papers
MaCoPlanner: LLM-Assisted Manual-Compiled Task Planning with Proactive Safety Verificatio…
arXiv cs.AI Research & Papers
Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning
arXiv cs.AI Research & Papers
Spatial-Semantic Reasoning using Large Language Models for Efficient UAV Search Operations
arXiv cs.AI Research & Papers
A Method for Layer Bit-Width Allocation in LLM Quantization via Performance Maximization …
arXiv cs.AI Research & Papers
Performative Privacy: When Differential Privacy Maximizes Utility