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
When Do Supervised UQ Ensembles Improve LLM Hallucination Detection? A Robustness Study
arXiv cs.AI Research & Papers
MatReplace: A Reference-Free, Conditioning-Aligned Benchmark for Material Replacement in …
arXiv cs.AI Research & Papers
Scalable and Versatile Identification for Hierarchical Structural Causal Models: A New Lo…
arXiv cs.AI Research & Papers
Identifying Latent Declarative Representations of Code for Assisting Repository Migration
arXiv cs.AI Research & Papers
When Less Is More: An Empirical Study of Minimal Responses in Counseling Dialogues and th…
arXiv cs.AI Research & Papers
VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference
arXiv cs.AI Research & Papers
PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understandi…
arXiv cs.AI Research & Papers
Mechanistic Circuit Identification for Controllable Data Generation
arXiv cs.AI Research & Papers
ChorusTIC: Training-Free Multivariate Time Series Classification via Chorus In-Context Le…
arXiv cs.AI Research & Papers
Evaluating Deep Multivariate Imputation Models on Wearable Device Data
arXiv cs.AI Research & Papers
ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal
arXiv cs.AI Research & Papers
Design-to-Plan: A Large Language Model-Based Multi-Agent Framework for Manufacturing Proc…
arXiv cs.AI Research & Papers
StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Ba…
arXiv cs.AI Research & Papers
Hierarchical Skill Retrieval for Data-Efficient Adaptation of Vision-Language-Action Mode…
arXiv cs.AI Research & Papers
A survey detection channel overrides the pixels in an astronomical foundation model, and …
arXiv cs.AI Research & Papers
Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection
arXiv cs.AI Research & Papers
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
arXiv cs.AI Research & Papers
ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
arXiv cs.AI Research & Papers
Quasar: A Programming Language Specialized for LLM Code Actions
arXiv cs.AI Research & Papers
UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with La…
arXiv cs.AI Research & Papers
Robust Motion Generation using Part-level Reliable Data from Videos
arXiv cs.AI Research & Papers
Ollivier-Ricci Curvature of Riemannian Manifolds and Directed Graphs with Applications to…
arXiv cs.AI Research & Papers
Atomic Units of X: The Compression Layer of Intelligence
arXiv cs.AI Research & Papers
The Shadow Price of Intelligence: Quality Degradation in LLM Inference as a Supply Chain …
arXiv cs.AI Research & Papers
SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document U…
arXiv cs.AI Research & Papers
MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models
arXiv cs.AI Research & Papers
PatientHub: A Unified Framework for Patient Simulation
arXiv cs.AI Research & Papers
Score-Based Ideal Observer Approximation via Denoising Score Matching for Signal-Known-Ex…
arXiv cs.AI Research & Papers
Can a Dynamic Internal Field Govern a Transformer's Cognition? Certifiability, not Superi…
arXiv cs.AI Research & Papers
Ethical LLM-Assisted Research: A Framework for Responsible Delegation, Verification, and …